From a4b6b0b775d8dcf1249d70ed3d606ad71edb894e Mon Sep 17 00:00:00 2001 From: yiling Date: Wed, 22 Jul 2026 12:04:07 +0800 Subject: [PATCH] refactor(core): split generated providers into per-provider files --- .../core/src/generated/providers.generated.ts | 16933 +--------------- .../src/generated/providers/amazon-bedrock.ts | 1867 ++ .../core/src/generated/providers/ant-ling.ts | 65 + .../core/src/generated/providers/anthropic.ts | 252 + .../providers/azure-openai-responses.ts | 796 + .../core/src/generated/providers/cerebras.ts | 65 + .../providers/cloudflare-ai-gateway.ts | 729 + .../providers/cloudflare-workers-ai.ts | 235 + .../core/src/generated/providers/deepseek.ts | 48 + .../core/src/generated/providers/fireworks.ts | 286 + .../src/generated/providers/github-copilot.ts | 544 + .../src/generated/providers/google-vertex.ts | 184 + .../core/src/generated/providers/google.ts | 320 + packages/core/src/generated/providers/groq.ts | 133 + .../src/generated/providers/huggingface.ts | 847 + .../src/generated/providers/kimi-coding.ts | 65 + .../src/generated/providers/minimax-cn.ts | 65 + .../core/src/generated/providers/minimax.ts | 65 + .../core/src/generated/providers/mistral.ts | 524 + .../src/generated/providers/moonshotai-cn.ts | 184 + .../src/generated/providers/moonshotai.ts | 184 + .../core/src/generated/providers/nvidia.ts | 337 + .../src/generated/providers/openai-codex.ts | 178 + .../core/src/generated/providers/openai.ts | 859 + .../src/generated/providers/opencode-go.ts | 269 + .../core/src/generated/providers/opencode.ts | 966 + .../src/generated/providers/openrouter.ts | 4655 +++++ .../generated/providers/qwen-token-plan-cn.ts | 269 + .../generated/providers/qwen-token-plan.ts | 269 + .../core/src/generated/providers/together.ts | 286 + .../generated/providers/vercel-ai-gateway.ts | 3278 +++ packages/core/src/generated/providers/xai.ts | 65 + .../providers/xiaomi-token-plan-ams.ts | 65 + .../providers/xiaomi-token-plan-cn.ts | 65 + .../providers/xiaomi-token-plan-sgp.ts | 65 + .../core/src/generated/providers/xiaomi.ts | 116 + .../src/generated/providers/zai-coding-cn.ts | 116 + packages/core/src/generated/providers/zai.ts | 116 + scripts/generate-builtin-providers.ts | 165 +- 39 files changed, 19616 insertions(+), 16914 deletions(-) create mode 100644 packages/core/src/generated/providers/amazon-bedrock.ts create mode 100644 packages/core/src/generated/providers/ant-ling.ts create mode 100644 packages/core/src/generated/providers/anthropic.ts create mode 100644 packages/core/src/generated/providers/azure-openai-responses.ts create mode 100644 packages/core/src/generated/providers/cerebras.ts create mode 100644 packages/core/src/generated/providers/cloudflare-ai-gateway.ts create mode 100644 packages/core/src/generated/providers/cloudflare-workers-ai.ts create mode 100644 packages/core/src/generated/providers/deepseek.ts create mode 100644 packages/core/src/generated/providers/fireworks.ts create mode 100644 packages/core/src/generated/providers/github-copilot.ts create mode 100644 packages/core/src/generated/providers/google-vertex.ts create mode 100644 packages/core/src/generated/providers/google.ts create mode 100644 packages/core/src/generated/providers/groq.ts create mode 100644 packages/core/src/generated/providers/huggingface.ts create mode 100644 packages/core/src/generated/providers/kimi-coding.ts create mode 100644 packages/core/src/generated/providers/minimax-cn.ts create mode 100644 packages/core/src/generated/providers/minimax.ts create mode 100644 packages/core/src/generated/providers/mistral.ts create mode 100644 packages/core/src/generated/providers/moonshotai-cn.ts create mode 100644 packages/core/src/generated/providers/moonshotai.ts create mode 100644 packages/core/src/generated/providers/nvidia.ts create mode 100644 packages/core/src/generated/providers/openai-codex.ts create mode 100644 packages/core/src/generated/providers/openai.ts create mode 100644 packages/core/src/generated/providers/opencode-go.ts create mode 100644 packages/core/src/generated/providers/opencode.ts create mode 100644 packages/core/src/generated/providers/openrouter.ts create mode 100644 packages/core/src/generated/providers/qwen-token-plan-cn.ts create mode 100644 packages/core/src/generated/providers/qwen-token-plan.ts create mode 100644 packages/core/src/generated/providers/together.ts create mode 100644 packages/core/src/generated/providers/vercel-ai-gateway.ts create mode 100644 packages/core/src/generated/providers/xai.ts create mode 100644 packages/core/src/generated/providers/xiaomi-token-plan-ams.ts create mode 100644 packages/core/src/generated/providers/xiaomi-token-plan-cn.ts create mode 100644 packages/core/src/generated/providers/xiaomi-token-plan-sgp.ts create mode 100644 packages/core/src/generated/providers/xiaomi.ts create mode 100644 packages/core/src/generated/providers/zai-coding-cn.ts create mode 100644 packages/core/src/generated/providers/zai.ts diff --git a/packages/core/src/generated/providers.generated.ts b/packages/core/src/generated/providers.generated.ts index d7cf9f1b..fcc55bbe 100644 --- a/packages/core/src/generated/providers.generated.ts +++ b/packages/core/src/generated/providers.generated.ts @@ -1,16863 +1,80 @@ // This file is auto-generated by scripts/generate-builtin-providers.ts // Do not edit manually - run 'bun run generate-providers' to update +import { providerConfig as openai } from './providers/openai' +import { providerConfig as anthropic } from './providers/anthropic' +import { providerConfig as google } from './providers/google' +import { providerConfig as deepseek } from './providers/deepseek' +import { providerConfig as groq } from './providers/groq' +import { providerConfig as openrouter } from './providers/openrouter' +import { providerConfig as mistral } from './providers/mistral' +import { providerConfig as amazonBedrock } from './providers/amazon-bedrock' +import { providerConfig as antLing } from './providers/ant-ling' +import { providerConfig as azureOpenaiResponses } from './providers/azure-openai-responses' +import { providerConfig as cerebras } from './providers/cerebras' +import { providerConfig as cloudflareAiGateway } from './providers/cloudflare-ai-gateway' +import { providerConfig as cloudflareWorkersAi } from './providers/cloudflare-workers-ai' +import { providerConfig as fireworks } from './providers/fireworks' +import { providerConfig as githubCopilot } from './providers/github-copilot' +import { providerConfig as googleVertex } from './providers/google-vertex' +import { providerConfig as huggingface } from './providers/huggingface' +import { providerConfig as kimiCoding } from './providers/kimi-coding' +import { providerConfig as minimax } from './providers/minimax' +import { providerConfig as minimaxCn } from './providers/minimax-cn' +import { providerConfig as moonshotai } from './providers/moonshotai' +import { providerConfig as moonshotaiCn } from './providers/moonshotai-cn' +import { providerConfig as nvidia } from './providers/nvidia' +import { providerConfig as openaiCodex } from './providers/openai-codex' +import { providerConfig as opencode } from './providers/opencode' +import { providerConfig as opencodeGo } from './providers/opencode-go' +import { providerConfig as qwenTokenPlan } from './providers/qwen-token-plan' +import { providerConfig as qwenTokenPlanCn } from './providers/qwen-token-plan-cn' +import { providerConfig as together } from './providers/together' +import { providerConfig as vercelAiGateway } from './providers/vercel-ai-gateway' +import { providerConfig as xai } from './providers/xai' +import { providerConfig as xiaomi } from './providers/xiaomi' +import { providerConfig as xiaomiTokenPlanAms } from './providers/xiaomi-token-plan-ams' +import { providerConfig as xiaomiTokenPlanCn } from './providers/xiaomi-token-plan-cn' +import { providerConfig as xiaomiTokenPlanSgp } from './providers/xiaomi-token-plan-sgp' +import { providerConfig as zai } from './providers/zai' +import { providerConfig as zaiCodingCn } from './providers/zai-coding-cn' + export const builtinProviders: Record = { - openai: { - name: 'openai', - config: { - api: 'openai-responses', - baseUrl: 'https://api.openai.com/v1', - apiKey: 'OPENAI_API_KEY', - }, - models: [ - { - modelId: 'gpt-4', - name: 'GPT-4', - config: { - api: 'openai-responses', - reasoning: false, - input: ['text'], - contextWindow: 8192, - maxTokens: 8192, - cost: { - input: 30, - output: 60, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-4-turbo', - name: 'GPT-4 Turbo', - config: { - api: 'openai-responses', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 4096, - cost: { - input: 10, - output: 30, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-4.1', - name: 'GPT-4.1', - config: { - api: 'openai-responses', - reasoning: false, - input: ['text', 'image'], - contextWindow: 1047576, - maxTokens: 32768, - cost: { - input: 2, - output: 8, - cacheRead: 0.5, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-4.1-mini', - name: 'GPT-4.1 mini', - config: { - api: 'openai-responses', - reasoning: false, - input: ['text', 'image'], - contextWindow: 1047576, - maxTokens: 32768, - cost: { - input: 0.4, - output: 1.6, - cacheRead: 0.1, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-4.1-nano', - name: 'GPT-4.1 nano', - config: { - api: 'openai-responses', - reasoning: false, - input: ['text', 'image'], - contextWindow: 1047576, - maxTokens: 32768, - cost: { - input: 0.1, - output: 0.4, - cacheRead: 0.025, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-4o', - name: 'GPT-4o', - config: { - api: 'openai-responses', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 2.5, - output: 10, - cacheRead: 1.25, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-4o-2024-05-13', - name: 'GPT-4o (2024-05-13)', - config: { - api: 'openai-responses', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 4096, - cost: { - input: 5, - output: 15, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-4o-2024-08-06', - name: 'GPT-4o (2024-08-06)', - config: { - api: 'openai-responses', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 2.5, - output: 10, - cacheRead: 1.25, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-4o-2024-11-20', - name: 'GPT-4o (2024-11-20)', - config: { - api: 'openai-responses', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 2.5, - output: 10, - cacheRead: 1.25, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-4o-mini', - name: 'GPT-4o mini', - config: { - api: 'openai-responses', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 0.15, - output: 0.6, - cacheRead: 0.075, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5', - name: 'GPT-5', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.25, - output: 10, - cacheRead: 0.125, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5-chat-latest', - name: 'GPT-5 Chat Latest', - config: { - api: 'openai-responses', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 1.25, - output: 10, - cacheRead: 0.125, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5-codex', - name: 'GPT-5-Codex', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.25, - output: 10, - cacheRead: 0.125, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5-mini', - name: 'GPT-5 Mini', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 0.25, - output: 2, - cacheRead: 0.025, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5-nano', - name: 'GPT-5 Nano', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 0.05, - output: 0.4, - cacheRead: 0.005, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5-pro', - name: 'GPT-5 Pro', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 15, - output: 120, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.1', - name: 'GPT-5.1', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.25, - output: 10, - cacheRead: 0.125, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.1-chat-latest', - name: 'GPT-5.1 Chat', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 1.25, - output: 10, - cacheRead: 0.125, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.1-codex', - name: 'GPT-5.1 Codex', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.25, - output: 10, - cacheRead: 0.125, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.1-codex-max', - name: 'GPT-5.1 Codex Max', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.25, - output: 10, - cacheRead: 0.125, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.1-codex-mini', - name: 'GPT-5.1 Codex mini', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 0.25, - output: 2, - cacheRead: 0.025, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.2', - name: 'GPT-5.2', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.75, - output: 14, - cacheRead: 0.175, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.2-chat-latest', - name: 'GPT-5.2 Chat', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 1.75, - output: 14, - cacheRead: 0.175, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.2-codex', - name: 'GPT-5.2 Codex', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.75, - output: 14, - cacheRead: 0.175, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.2-pro', - name: 'GPT-5.2 Pro', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 21, - output: 168, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.3-chat-latest', - name: 'GPT-5.3 Chat (latest)', - config: { - api: 'openai-responses', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 1.75, - output: 14, - cacheRead: 0.175, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.3-codex', - name: 'GPT-5.3 Codex', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.75, - output: 14, - cacheRead: 0.175, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.3-codex-spark', - name: 'GPT-5.3 Codex Spark', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 32000, - cost: { - input: 1.75, - output: 14, - cacheRead: 0.175, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.4', - name: 'GPT-5.4', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 272000, - maxTokens: 128000, - cost: { - input: 2.5, - output: 15, - cacheRead: 0.25, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.4-mini', - name: 'GPT-5.4 mini', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 0.75, - output: 4.5, - cacheRead: 0.075, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.4-nano', - name: 'GPT-5.4 nano', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 0.2, - output: 1.25, - cacheRead: 0.02, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.4-pro', - name: 'GPT-5.4 Pro', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1050000, - maxTokens: 128000, - cost: { - input: 30, - output: 180, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.5', - name: 'GPT-5.5', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 272000, - maxTokens: 128000, - cost: { - input: 5, - output: 30, - cacheRead: 0.5, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.5-pro', - name: 'GPT-5.5 Pro', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1050000, - maxTokens: 128000, - cost: { - input: 30, - output: 180, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'o1', - name: 'o1', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 100000, - cost: { - input: 15, - output: 60, - cacheRead: 7.5, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'o1-pro', - name: 'o1-pro', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 100000, - cost: { - input: 150, - output: 600, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'o3', - name: 'o3', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 100000, - cost: { - input: 2, - output: 8, - cacheRead: 0.5, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'o3-deep-research', - name: 'o3-deep-research', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 100000, - cost: { - input: 10, - output: 40, - cacheRead: 2.5, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'o3-mini', - name: 'o3-mini', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text'], - contextWindow: 200000, - maxTokens: 100000, - cost: { - input: 1.1, - output: 4.4, - cacheRead: 0.55, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'o3-pro', - name: 'o3-pro', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 100000, - cost: { - input: 20, - output: 80, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'o4-mini', - name: 'o4-mini', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 100000, - cost: { - input: 1.1, - output: 4.4, - cacheRead: 0.275, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'o4-mini-deep-research', - name: 'o4-mini-deep-research', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 100000, - cost: { - input: 2, - output: 8, - cacheRead: 0.5, - cacheWrite: 0, - }, - }, - }, - ], - }, - anthropic: { - name: 'anthropic', - config: { - api: 'anthropic-messages', - baseUrl: 'https://api.anthropic.com', - apiKey: 'ANTHROPIC_API_KEY', - }, - models: [ - { - modelId: 'claude-3-5-haiku-20241022', - name: 'Claude Haiku 3.5', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 8192, - cost: { - input: 0.8, - output: 4, - cacheRead: 0.08, - cacheWrite: 1, - }, - }, - }, - { - modelId: 'claude-3-5-haiku-latest', - name: 'Claude Haiku 3.5 (latest)', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 8192, - cost: { - input: 0.8, - output: 4, - cacheRead: 0.08, - cacheWrite: 1, - }, - }, - }, - { - modelId: 'claude-3-5-sonnet-20240620', - name: 'Claude Sonnet 3.5', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 8192, - cost: { - input: 3, - output: 15, - cacheRead: 0.3, - cacheWrite: 3.75, - }, - }, - }, - { - modelId: 'claude-3-5-sonnet-20241022', - name: 'Claude Sonnet 3.5 v2', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 8192, - cost: { - input: 3, - output: 15, - cacheRead: 0.3, - cacheWrite: 3.75, - }, - }, - }, - { - modelId: 'claude-3-7-sonnet-20250219', - name: 'Claude Sonnet 3.7', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 3, - output: 15, - cacheRead: 0.3, - cacheWrite: 3.75, - }, - }, - }, - { - modelId: 'claude-3-haiku-20240307', - name: 'Claude Haiku 3', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 4096, - cost: { - input: 0.25, - output: 1.25, - cacheRead: 0.03, - cacheWrite: 0.3, - }, - }, - }, - { - modelId: 'claude-3-opus-20240229', - name: 'Claude Opus 3', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 4096, - cost: { - input: 15, - output: 75, - cacheRead: 1.5, - cacheWrite: 18.75, - }, - }, - }, - { - modelId: 'claude-3-sonnet-20240229', - name: 'Claude Sonnet 3', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 4096, - cost: { - input: 3, - output: 15, - cacheRead: 0.3, - cacheWrite: 0.3, - }, - }, - }, - { - modelId: 'claude-fable-5', - name: 'Claude Fable 5', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 10, - output: 50, - cacheRead: 1, - cacheWrite: 12.5, - }, - }, - }, - { - modelId: 'claude-haiku-4-5', - name: 'Claude Haiku 4.5 (latest)', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 1, - output: 5, - cacheRead: 0.1, - cacheWrite: 1.25, - }, - }, - }, - { - modelId: 'claude-haiku-4-5-20251001', - name: 'Claude Haiku 4.5', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 1, - output: 5, - cacheRead: 0.1, - cacheWrite: 1.25, - }, - }, - }, - { - modelId: 'claude-opus-4-0', - name: 'Claude Opus 4 (latest)', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 32000, - cost: { - input: 15, - output: 75, - cacheRead: 1.5, - cacheWrite: 18.75, - }, - }, - }, - { - modelId: 'claude-opus-4-1', - name: 'Claude Opus 4.1 (latest)', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 32000, - cost: { - input: 15, - output: 75, - cacheRead: 1.5, - cacheWrite: 18.75, - }, - }, - }, - { - modelId: 'claude-opus-4-1-20250805', - name: 'Claude Opus 4.1', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 32000, - cost: { - input: 15, - output: 75, - cacheRead: 1.5, - cacheWrite: 18.75, - }, - }, - }, - { - modelId: 'claude-opus-4-20250514', - name: 'Claude Opus 4', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 32000, - cost: { - input: 15, - output: 75, - cacheRead: 1.5, - cacheWrite: 18.75, - }, - }, - }, - { - modelId: 'claude-opus-4-5', - name: 'Claude Opus 4.5 (latest)', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'claude-opus-4-5-20251101', - name: 'Claude Opus 4.5', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'claude-opus-4-6', - name: 'Claude Opus 4.6', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'claude-opus-4-7', - name: 'Claude Opus 4.7', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'claude-opus-4-8', - name: 'Claude Opus 4.8', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'claude-sonnet-4-0', - name: 'Claude Sonnet 4 (latest)', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 3, - output: 15, - cacheRead: 0.3, - cacheWrite: 3.75, - }, - }, - }, - { - modelId: 'claude-sonnet-4-20250514', - name: 'Claude Sonnet 4', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 3, - output: 15, - cacheRead: 0.3, - cacheWrite: 3.75, - }, - }, - }, - { - modelId: 'claude-sonnet-4-5', - name: 'Claude Sonnet 4.5 (latest)', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 3, - output: 15, - cacheRead: 0.3, - cacheWrite: 3.75, - }, - }, - }, - { - modelId: 'claude-sonnet-4-5-20250929', - name: 'Claude Sonnet 4.5', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 3, - output: 15, - cacheRead: 0.3, - cacheWrite: 3.75, - }, - }, - }, - { - modelId: 'claude-sonnet-4-6', - name: 'Claude Sonnet 4.6', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 64000, - cost: { - input: 3, - output: 15, - cacheRead: 0.3, - cacheWrite: 3.75, - }, - }, - }, - ], - }, - google: { - name: 'google', - config: { - api: 'google-generative-ai', - baseUrl: 'https://generativelanguage.googleapis.com/v1beta', - apiKey: 'GEMINI_API_KEY', - }, - models: [ - { - modelId: 'gemini-2.0-flash', - name: 'Gemini 2.0 Flash', - config: { - api: 'google-generative-ai', - reasoning: false, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 8192, - cost: { - input: 0.1, - output: 0.4, - cacheRead: 0.025, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gemini-2.0-flash-lite', - name: 'Gemini 2.0 Flash-Lite', - config: { - api: 'google-generative-ai', - reasoning: false, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 8192, - cost: { - input: 0.075, - output: 0.3, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gemini-2.5-flash', - name: 'Gemini 2.5 Flash', - config: { - api: 'google-generative-ai', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 65536, - cost: { - input: 0.3, - output: 2.5, - cacheRead: 0.03, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gemini-2.5-flash-lite', - name: 'Gemini 2.5 Flash-Lite', - config: { - api: 'google-generative-ai', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 65536, - cost: { - input: 0.1, - output: 0.4, - cacheRead: 0.01, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gemini-2.5-pro', - name: 'Gemini 2.5 Pro', - config: { - api: 'google-generative-ai', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 65536, - cost: { - input: 1.25, - output: 10, - cacheRead: 0.125, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gemini-3-flash-preview', - name: 'Gemini 3 Flash Preview', - config: { - api: 'google-generative-ai', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 65536, - cost: { - input: 0.5, - output: 3, - cacheRead: 0.05, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gemini-3-pro-preview', - name: 'Gemini 3 Pro Preview', - config: { - api: 'google-generative-ai', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 65536, - cost: { - input: 2, - output: 12, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gemini-3.1-flash-lite', - name: 'Gemini 3.1 Flash Lite', - config: { - api: 'google-generative-ai', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 65536, - cost: { - input: 0.25, - output: 1.5, - cacheRead: 0.025, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gemini-3.1-flash-lite-preview', - name: 'Gemini 3.1 Flash Lite Preview', - config: { - api: 'google-generative-ai', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 65536, - cost: { - input: 0.25, - output: 1.5, - cacheRead: 0.025, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gemini-3.1-pro-preview', - name: 'Gemini 3.1 Pro Preview', - config: { - api: 'google-generative-ai', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 65536, - cost: { - input: 2, - output: 12, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gemini-3.1-pro-preview-customtools', - name: 'Gemini 3.1 Pro Preview Custom Tools', - config: { - api: 'google-generative-ai', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 65536, - cost: { - input: 2, - output: 12, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gemini-3.5-flash', - name: 'Gemini 3.5 Flash', - config: { - api: 'google-generative-ai', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 65536, - cost: { - input: 1.5, - output: 9, - cacheRead: 0.15, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gemini-flash-latest', - name: 'Gemini Flash Latest', - config: { - api: 'google-generative-ai', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 65536, - cost: { - input: 0.3, - output: 2.5, - cacheRead: 0.075, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gemini-flash-lite-latest', - name: 'Gemini Flash-Lite Latest', - config: { - api: 'google-generative-ai', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 65536, - cost: { - input: 0.1, - output: 0.4, - cacheRead: 0.025, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gemma-4-26b-a4b-it', - name: 'Gemma 4 26B A4B IT', - config: { - api: 'google-generative-ai', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 32768, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gemma-4-31b-it', - name: 'Gemma 4 31B IT', - config: { - api: 'google-generative-ai', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 32768, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gemma-4-E2B-it', - name: 'Gemma 4 E2B IT', - config: { - api: 'google-generative-ai', - reasoning: true, - input: ['text', 'image'], - contextWindow: 131072, - maxTokens: 8192, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gemma-4-E4B-it', - name: 'Gemma 4 E4B IT', - config: { - api: 'google-generative-ai', - reasoning: true, - input: ['text', 'image'], - contextWindow: 131072, - maxTokens: 8192, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - ], - }, - deepseek: { - name: 'deepseek', - config: { - api: 'openai-completions', - baseUrl: 'https://api.deepseek.com', - apiKey: 'DEEPSEEK_API_KEY', - }, - models: [ - { - modelId: 'deepseek-v4-flash', - name: 'DeepSeek V4 Flash', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 1000000, - maxTokens: 384000, - cost: { - input: 0.14, - output: 0.28, - cacheRead: 0.0028, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'deepseek-v4-pro', - name: 'DeepSeek V4 Pro', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 1000000, - maxTokens: 384000, - cost: { - input: 0.435, - output: 0.87, - cacheRead: 0.003625, - cacheWrite: 0, - }, - }, - }, - ], - }, - groq: { - name: 'groq', - config: { - api: 'openai-completions', - baseUrl: 'https://api.groq.com/openai/v1', - apiKey: 'GROQ_API_KEY', - }, - models: [ - { - modelId: 'llama-3.1-8b-instant', - name: 'Llama 3.1 8B', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 131072, - maxTokens: 131072, - cost: { - input: 0.05, - output: 0.08, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'llama-3.3-70b-versatile', - name: 'Llama 3.3 70B', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 131072, - maxTokens: 32768, - cost: { - input: 0.59, - output: 0.79, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'meta-llama/llama-4-scout-17b-16e-instruct', - name: 'Llama 4 Scout 17B 16E', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 131072, - maxTokens: 8192, - cost: { - input: 0.11, - output: 0.34, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-oss-120b', - name: 'GPT OSS 120B', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 65536, - cost: { - input: 0.15, - output: 0.6, - cacheRead: 0.075, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-oss-20b', - name: 'GPT OSS 20B', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 65536, - cost: { - input: 0.075, - output: 0.3, - cacheRead: 0.0375, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-oss-safeguard-20b', - name: 'Safety GPT OSS 20B', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 65536, - cost: { - input: 0.075, - output: 0.3, - cacheRead: 0.037, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen/qwen3-32b', - name: 'Qwen3-32B', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 40960, - cost: { - input: 0.29, - output: 0.59, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - ], - }, - openrouter: { - name: 'openrouter', - config: { - api: 'openai-completions', - baseUrl: 'https://openrouter.ai/api/v1', - apiKey: 'OPENROUTER_API_KEY', - }, - models: [ - { - modelId: 'ai21/jamba-large-1.7', - name: 'AI21: Jamba Large 1.7', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 256000, - maxTokens: 4096, - cost: { - input: 2, - output: 8, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'amazon/nova-2-lite-v1', - name: 'Amazon: Nova 2 Lite', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 65535, - cost: { - input: 0.3, - output: 2.5, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'amazon/nova-lite-v1', - name: 'Amazon: Nova Lite 1.0', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 300000, - maxTokens: 5120, - cost: { - input: 0.06, - output: 0.24, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'amazon/nova-micro-v1', - name: 'Amazon: Nova Micro 1.0', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 128000, - maxTokens: 5120, - cost: { - input: 0.035, - output: 0.14, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'amazon/nova-premier-v1', - name: 'Amazon: Nova Premier 1.0', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 32000, - cost: { - input: 2.5, - output: 12.5, - cacheRead: 0.625, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'amazon/nova-pro-v1', - name: 'Amazon: Nova Pro 1.0', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 300000, - maxTokens: 5120, - cost: { - input: 0.8, - output: 3.2, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'anthropic/claude-3-haiku', - name: 'Anthropic: Claude 3 Haiku', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 4096, - cost: { - input: 0.25, - output: 1.25, - cacheRead: 0.03, - cacheWrite: 0.3, - }, - }, - }, - { - modelId: 'anthropic/claude-3.5-haiku', - name: 'Anthropic: Claude 3.5 Haiku', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 8192, - cost: { - input: 0.8, - output: 4, - cacheRead: 0.08, - cacheWrite: 1, - }, - }, - }, - { - modelId: 'anthropic/claude-fable-5', - name: 'Anthropic: Claude Fable 5', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 10, - output: 50, - cacheRead: 1, - cacheWrite: 12.5, - }, - }, - }, - { - modelId: 'anthropic/claude-haiku-4.5', - name: 'Anthropic: Claude Haiku 4.5', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 1, - output: 5, - cacheRead: 0.1, - cacheWrite: 1.25, - }, - }, - }, - { - modelId: 'anthropic/claude-opus-4', - name: 'Anthropic: Claude Opus 4', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 32000, - cost: { - input: 15, - output: 75, - cacheRead: 1.5, - cacheWrite: 18.75, - }, - }, - }, - { - modelId: 'anthropic/claude-opus-4.1', - name: 'Anthropic: Claude Opus 4.1', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 32000, - cost: { - input: 15, - output: 75, - cacheRead: 1.5, - cacheWrite: 18.75, - }, - }, - }, - { - modelId: 'anthropic/claude-opus-4.5', - name: 'Anthropic: Claude Opus 4.5', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'anthropic/claude-opus-4.6', - name: 'Anthropic: Claude Opus 4.6', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'anthropic/claude-opus-4.6-fast', - name: 'Anthropic: Claude Opus 4.6 (Fast)', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 30, - output: 150, - cacheRead: 3, - cacheWrite: 37.5, - }, - }, - }, - { - modelId: 'anthropic/claude-opus-4.7', - name: 'Anthropic: Claude Opus 4.7', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'anthropic/claude-opus-4.7-fast', - name: 'Anthropic: Claude Opus 4.7 (Fast)', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 30, - output: 150, - cacheRead: 3, - cacheWrite: 37.5, - }, - }, - }, - { - modelId: 'anthropic/claude-opus-4.8', - name: 'Anthropic: Claude Opus 4.8', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'anthropic/claude-opus-4.8-fast', - name: 'Anthropic: Claude Opus 4.8 (Fast)', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 10, - output: 50, - cacheRead: 1, - cacheWrite: 12.5, - }, - }, - }, - { - modelId: 'anthropic/claude-sonnet-4', - name: 'Anthropic: Claude Sonnet 4', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 64000, - cost: { - input: 3, - output: 15, - cacheRead: 0.3, - cacheWrite: 3.75, - }, - }, - }, - { - modelId: 'anthropic/claude-sonnet-4.5', - name: 'Anthropic: Claude Sonnet 4.5', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 64000, - cost: { - input: 3, - output: 15, - cacheRead: 0.3, - cacheWrite: 3.75, - }, - }, - }, - { - modelId: 'anthropic/claude-sonnet-4.6', - name: 'Anthropic: Claude Sonnet 4.6', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 3, - output: 15, - cacheRead: 0.3, - cacheWrite: 3.75, - }, - }, - }, - { - modelId: 'arcee-ai/trinity-large-thinking', - name: 'Arcee AI: Trinity Large Thinking', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 0.22, - output: 0.85, - cacheRead: 0.06, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'arcee-ai/trinity-mini', - name: 'Arcee AI: Trinity Mini', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 131072, - cost: { - input: 0.045, - output: 0.15, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'arcee-ai/virtuoso-large', - name: 'Arcee AI: Virtuoso Large', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 131072, - maxTokens: 64000, - cost: { - input: 0.75, - output: 1.2, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'auto', - name: 'Auto', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 2000000, - maxTokens: 30000, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'bytedance-seed/seed-1.6', - name: 'ByteDance Seed: Seed 1.6', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 32768, - cost: { - input: 0.25, - output: 2, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'bytedance-seed/seed-1.6-flash', - name: 'ByteDance Seed: Seed 1.6 Flash', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 32768, - cost: { - input: 0.075, - output: 0.3, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'bytedance-seed/seed-2.0-lite', - name: 'ByteDance Seed: Seed-2.0-Lite', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 131072, - cost: { - input: 0.25, - output: 2, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'bytedance-seed/seed-2.0-mini', - name: 'ByteDance Seed: Seed-2.0-Mini', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 131072, - cost: { - input: 0.1, - output: 0.4, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'cohere/command-r-08-2024', - name: 'Cohere: Command R (08-2024)', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 128000, - maxTokens: 4000, - cost: { - input: 0.15, - output: 0.6, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'cohere/command-r-plus-08-2024', - name: 'Cohere: Command R+ (08-2024)', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 128000, - maxTokens: 4000, - cost: { - input: 2.5, - output: 10, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'deepseek/deepseek-chat', - name: 'DeepSeek: DeepSeek V3', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 131072, - maxTokens: 16000, - cost: { - input: 0.2002, - output: 0.8001, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'deepseek/deepseek-chat-v3-0324', - name: 'DeepSeek: DeepSeek V3 0324', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 163840, - maxTokens: 16384, - cost: { - input: 0.2, - output: 0.77, - cacheRead: 0.135, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'deepseek/deepseek-chat-v3.1', - name: 'DeepSeek: DeepSeek V3.1', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 163840, - maxTokens: 32768, - cost: { - input: 0.21, - output: 0.79, - cacheRead: 0.13, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'deepseek/deepseek-r1', - name: 'DeepSeek: R1', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 163840, - maxTokens: 16000, - cost: { - input: 0.7, - output: 2.5, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'deepseek/deepseek-r1-0528', - name: 'DeepSeek: R1 0528', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 163840, - maxTokens: 32768, - cost: { - input: 0.5, - output: 2.15, - cacheRead: 0.35, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'deepseek/deepseek-v3.1-terminus', - name: 'DeepSeek: DeepSeek V3.1 Terminus', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 163840, - maxTokens: 32768, - cost: { - input: 0.27, - output: 0.95, - cacheRead: 0.13, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'deepseek/deepseek-v3.2', - name: 'DeepSeek: DeepSeek V3.2', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 64000, - cost: { - input: 0.2288, - output: 0.3432, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'deepseek/deepseek-v3.2-exp', - name: 'DeepSeek: DeepSeek V3.2 Exp', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 163840, - maxTokens: 65536, - cost: { - input: 0.27, - output: 0.41, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'deepseek/deepseek-v4-flash', - name: 'DeepSeek: DeepSeek V4 Flash', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 1048576, - maxTokens: 65536, - cost: { - input: 0.09, - output: 0.18, - cacheRead: 0.02, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'deepseek/deepseek-v4-pro', - name: 'DeepSeek: DeepSeek V4 Pro', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 1048576, - maxTokens: 384000, - cost: { - input: 0.435, - output: 0.87, - cacheRead: 0.003625, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'essentialai/rnj-1-instruct', - name: 'EssentialAI: Rnj 1 Instruct', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 32768, - maxTokens: 4096, - cost: { - input: 0.15, - output: 0.15, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'google/gemini-2.5-flash', - name: 'Google: Gemini 2.5 Flash', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 65535, - cost: { - input: 0.3, - output: 2.5, - cacheRead: 0.03, - cacheWrite: 0.083333, - }, - }, - }, - { - modelId: 'google/gemini-2.5-flash-lite', - name: 'Google: Gemini 2.5 Flash Lite', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 65535, - cost: { - input: 0.1, - output: 0.4, - cacheRead: 0.01, - cacheWrite: 0.083333, - }, - }, - }, - { - modelId: 'google/gemini-2.5-flash-lite-preview-09-2025', - name: 'Google: Gemini 2.5 Flash Lite Preview 09-2025', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 65535, - cost: { - input: 0.1, - output: 0.4, - cacheRead: 0.01, - cacheWrite: 0.083333, - }, - }, - }, - { - modelId: 'google/gemini-2.5-pro', - name: 'Google: Gemini 2.5 Pro', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 65536, - cost: { - input: 1.25, - output: 10, - cacheRead: 0.125, - cacheWrite: 0.375, - }, - }, - }, - { - modelId: 'google/gemini-2.5-pro-preview', - name: 'Google: Gemini 2.5 Pro Preview 06-05', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 65536, - cost: { - input: 1.25, - output: 10, - cacheRead: 0.125, - cacheWrite: 0.375, - }, - }, - }, - { - modelId: 'google/gemini-2.5-pro-preview-05-06', - name: 'Google: Gemini 2.5 Pro Preview 05-06', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 65535, - cost: { - input: 1.25, - output: 10, - cacheRead: 0.125, - cacheWrite: 0.375, - }, - }, - }, - { - modelId: 'google/gemini-3-flash-preview', - name: 'Google: Gemini 3 Flash Preview', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 65536, - cost: { - input: 0.5, - output: 3, - cacheRead: 0.05, - cacheWrite: 0.083333, - }, - }, - }, - { - modelId: 'google/gemini-3.1-flash-lite', - name: 'Google: Gemini 3.1 Flash Lite', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 65536, - cost: { - input: 0.25, - output: 1.5, - cacheRead: 0.025, - cacheWrite: 0.083333, - }, - }, - }, - { - modelId: 'google/gemini-3.1-flash-lite-preview', - name: 'Google: Gemini 3.1 Flash Lite Preview', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 65536, - cost: { - input: 0.25, - output: 1.5, - cacheRead: 0.025, - cacheWrite: 0.083333, - }, - }, - }, - { - modelId: 'google/gemini-3.1-pro-preview', - name: 'Google: Gemini 3.1 Pro Preview', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 65536, - cost: { - input: 2, - output: 12, - cacheRead: 0.2, - cacheWrite: 0.375, - }, - }, - }, - { - modelId: 'google/gemini-3.1-pro-preview-customtools', - name: 'Google: Gemini 3.1 Pro Preview Custom Tools', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048756, - maxTokens: 65536, - cost: { - input: 2, - output: 12, - cacheRead: 0.2, - cacheWrite: 0.375, - }, - }, - }, - { - modelId: 'google/gemini-3.5-flash', - name: 'Google: Gemini 3.5 Flash', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 65536, - cost: { - input: 1.5, - output: 9, - cacheRead: 0.15, - cacheWrite: 0.083333, - }, - }, - }, - { - modelId: 'google/gemma-3-12b-it', - name: 'Google: Gemma 3 12B', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 131072, - maxTokens: 16384, - cost: { - input: 0.05, - output: 0.15, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'google/gemma-3-27b-it', - name: 'Google: Gemma 3 27B', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 131072, - maxTokens: 16384, - cost: { - input: 0.08, - output: 0.16, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'google/gemma-4-26b-a4b-it', - name: 'Google: Gemma 4 26B A4B ', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 4096, - cost: { - input: 0.06, - output: 0.33, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'google/gemma-4-26b-a4b-it:free', - name: 'Google: Gemma 4 26B A4B (free)', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 32768, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'google/gemma-4-31b-it', - name: 'Google: Gemma 4 31B', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 0.12, - output: 0.35, - cacheRead: 0.09, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'google/gemma-4-31b-it:free', - name: 'Google: Gemma 4 31B (free)', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 32768, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'ibm-granite/granite-4.1-8b', - name: 'IBM: Granite 4.1 8B', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 131072, - maxTokens: 131072, - cost: { - input: 0.05, - output: 0.1, - cacheRead: 0.05, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'inception/mercury-2', - name: 'Inception: Mercury 2', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 128000, - maxTokens: 50000, - cost: { - input: 0.25, - output: 0.75, - cacheRead: 0.025, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'inclusionai/ling-2.6-1t', - name: 'inclusionAI: Ling-2.6-1T', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 262144, - maxTokens: 32768, - cost: { - input: 0.075, - output: 0.625, - cacheRead: 0.015, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'inclusionai/ling-2.6-flash', - name: 'inclusionAI: Ling-2.6-flash', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 262144, - maxTokens: 32768, - cost: { - input: 0.01, - output: 0.03, - cacheRead: 0.002, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'inclusionai/ring-2.6-1t', - name: 'inclusionAI: Ring-2.6-1T', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 262144, - maxTokens: 65536, - cost: { - input: 0.075, - output: 0.625, - cacheRead: 0.015, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'kwaipilot/kat-coder-pro-v2', - name: 'Kwaipilot: KAT-Coder-Pro V2', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 256000, - maxTokens: 80000, - cost: { - input: 0.3, - output: 1.2, - cacheRead: 0.06, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'meta-llama/llama-3.1-70b-instruct', - name: 'Meta: Llama 3.1 70B Instruct', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 131072, - maxTokens: 16384, - cost: { - input: 0.4, - output: 0.4, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'meta-llama/llama-3.1-8b-instruct', - name: 'Meta: Llama 3.1 8B Instruct', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 131072, - maxTokens: 16384, - cost: { - input: 0.02, - output: 0.03, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'meta-llama/llama-3.3-70b-instruct', - name: 'Meta: Llama 3.3 70B Instruct', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 131072, - maxTokens: 16384, - cost: { - input: 0.1, - output: 0.32, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'meta-llama/llama-3.3-70b-instruct:free', - name: 'Meta: Llama 3.3 70B Instruct (free)', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 131072, - maxTokens: 4096, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'meta-llama/llama-4-maverick', - name: 'Meta: Llama 4 Maverick', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 16384, - cost: { - input: 0.15, - output: 0.6, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'meta-llama/llama-4-scout', - name: 'Meta: Llama 4 Scout', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 10000000, - maxTokens: 16384, - cost: { - input: 0.1, - output: 0.3, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'minimax/minimax-m1', - name: 'MiniMax: MiniMax M1', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 1000000, - maxTokens: 40000, - cost: { - input: 0.4, - output: 2.2, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'minimax/minimax-m2', - name: 'MiniMax: MiniMax M2', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 204800, - maxTokens: 196608, - cost: { - input: 0.255, - output: 1, - cacheRead: 0.03, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'minimax/minimax-m2.1', - name: 'MiniMax: MiniMax M2.1', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 204800, - maxTokens: 196608, - cost: { - input: 0.29, - output: 0.95, - cacheRead: 0.03, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'minimax/minimax-m2.5', - name: 'MiniMax: MiniMax M2.5', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 204800, - maxTokens: 196608, - cost: { - input: 0.15, - output: 0.9, - cacheRead: 0.05, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'minimax/minimax-m2.7', - name: 'MiniMax: MiniMax M2.7', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 204800, - maxTokens: 131072, - cost: { - input: 0.25, - output: 1, - cacheRead: 0.05, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'minimax/minimax-m3', - name: 'MiniMax: MiniMax M3', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 512000, - cost: { - input: 0.3, - output: 1.2, - cacheRead: 0.06, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistralai/codestral-2508', - name: 'Mistral: Codestral 2508', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 256000, - maxTokens: 4096, - cost: { - input: 0.3, - output: 0.9, - cacheRead: 0.03, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistralai/devstral-2512', - name: 'Mistral: Devstral 2 2512', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 262144, - maxTokens: 4096, - cost: { - input: 0.4, - output: 2, - cacheRead: 0.04, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistralai/ministral-14b-2512', - name: 'Mistral: Ministral 3 14B 2512', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 4096, - cost: { - input: 0.2, - output: 0.2, - cacheRead: 0.02, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistralai/ministral-3b-2512', - name: 'Mistral: Ministral 3 3B 2512', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 131072, - maxTokens: 4096, - cost: { - input: 0.1, - output: 0.1, - cacheRead: 0.01, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistralai/ministral-8b-2512', - name: 'Mistral: Ministral 3 8B 2512', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 4096, - cost: { - input: 0.15, - output: 0.15, - cacheRead: 0.015, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistralai/mistral-large', - name: 'Mistral Large', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 128000, - maxTokens: 4096, - cost: { - input: 2, - output: 6, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistralai/mistral-large-2407', - name: 'Mistral Large 2407', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 131072, - maxTokens: 4096, - cost: { - input: 2, - output: 6, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistralai/mistral-large-2512', - name: 'Mistral: Mistral Large 3 2512', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 4096, - cost: { - input: 0.5, - output: 1.5, - cacheRead: 0.05, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistralai/mistral-medium-3', - name: 'Mistral: Mistral Medium 3', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 131072, - maxTokens: 4096, - cost: { - input: 0.4, - output: 2, - cacheRead: 0.04, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistralai/mistral-medium-3-5', - name: 'Mistral: Mistral Medium 3.5', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 4096, - cost: { - input: 1.5, - output: 7.5, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistralai/mistral-medium-3.1', - name: 'Mistral: Mistral Medium 3.1', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 131072, - maxTokens: 4096, - cost: { - input: 0.4, - output: 2, - cacheRead: 0.04, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistralai/mistral-nemo', - name: 'Mistral: Mistral Nemo', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 131072, - maxTokens: 4096, - cost: { - input: 0.02, - output: 0.03, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistralai/mistral-saba', - name: 'Mistral: Saba', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 32768, - maxTokens: 4096, - cost: { - input: 0.2, - output: 0.6, - cacheRead: 0.02, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistralai/mistral-small-2603', - name: 'Mistral: Mistral Small 4', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 4096, - cost: { - input: 0.15, - output: 0.6, - cacheRead: 0.015, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistralai/mistral-small-3.2-24b-instruct', - name: 'Mistral: Mistral Small 3.2 24B', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 0.075, - output: 0.2, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistralai/mixtral-8x22b-instruct', - name: 'Mistral: Mixtral 8x22B Instruct', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 65536, - maxTokens: 4096, - cost: { - input: 2, - output: 6, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistralai/voxtral-small-24b-2507', - name: 'Mistral: Voxtral Small 24B 2507', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 32000, - maxTokens: 4096, - cost: { - input: 0.1, - output: 0.3, - cacheRead: 0.01, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'moonshotai/kimi-k2', - name: 'MoonshotAI: Kimi K2 0711', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 131072, - maxTokens: 32768, - cost: { - input: 0.57, - output: 2.3, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'moonshotai/kimi-k2-0905', - name: 'MoonshotAI: Kimi K2 0905', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 0.6, - output: 2.5, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'moonshotai/kimi-k2-thinking', - name: 'MoonshotAI: Kimi K2 Thinking', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 0.6, - output: 2.5, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'moonshotai/kimi-k2.5', - name: 'MoonshotAI: Kimi K2.5', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 4096, - cost: { - input: 0.41, - output: 2.06, - cacheRead: 0.07, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'moonshotai/kimi-k2.6', - name: 'MoonshotAI: Kimi K2.6', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 262142, - cost: { - input: 0.68, - output: 3.41, - cacheRead: 0.34, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'moonshotai/kimi-k2.7-code', - name: 'MoonshotAI: Kimi K2.7 Code', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 0.75, - output: 3.5, - cacheRead: 0.16, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'nex-agi/nex-n2-pro:free', - name: 'Nex AGI: Nex-N2-Pro (free)', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'nvidia/llama-3.3-nemotron-super-49b-v1.5', - name: 'NVIDIA: Llama 3.3 Nemotron Super 49B V1.5', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 16384, - cost: { - input: 0.4, - output: 0.4, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'nvidia/nemotron-3-nano-30b-a3b', - name: 'NVIDIA: Nemotron 3 Nano 30B A3B', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 262144, - maxTokens: 228000, - cost: { - input: 0.05, - output: 0.2, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'nvidia/nemotron-3-nano-30b-a3b:free', - name: 'NVIDIA: Nemotron 3 Nano 30B A3B (free)', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 256000, - maxTokens: 4096, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free', - name: 'NVIDIA: Nemotron 3 Nano Omni (free)', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 256000, - maxTokens: 65536, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'nvidia/nemotron-3-super-120b-a12b', - name: 'NVIDIA: Nemotron 3 Super', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 1000000, - maxTokens: 4096, - cost: { - input: 0.09, - output: 0.45, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'nvidia/nemotron-3-super-120b-a12b:free', - name: 'NVIDIA: Nemotron 3 Super (free)', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 1000000, - maxTokens: 262144, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'nvidia/nemotron-3-ultra-550b-a55b', - name: 'NVIDIA: Nemotron 3 Ultra', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 1000000, - maxTokens: 16384, - cost: { - input: 0.5, - output: 2.5, - cacheRead: 0.15, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'nvidia/nemotron-3-ultra-550b-a55b:free', - name: 'NVIDIA: Nemotron 3 Ultra (free)', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 1000000, - maxTokens: 65536, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'nvidia/nemotron-nano-12b-v2-vl:free', - name: 'NVIDIA: Nemotron Nano 12B 2 VL (free)', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 128000, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'nvidia/nemotron-nano-9b-v2:free', - name: 'NVIDIA: Nemotron Nano 9B V2 (free)', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 128000, - maxTokens: 4096, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-3.5-turbo', - name: 'OpenAI: GPT-3.5 Turbo', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 16385, - maxTokens: 4096, - cost: { - input: 0.5, - output: 1.5, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-3.5-turbo-0613', - name: 'OpenAI: GPT-3.5 Turbo (older v0613)', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 4095, - maxTokens: 4096, - cost: { - input: 1, - output: 2, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-3.5-turbo-16k', - name: 'OpenAI: GPT-3.5 Turbo 16k', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 16385, - maxTokens: 4096, - cost: { - input: 3, - output: 4, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-4', - name: 'OpenAI: GPT-4', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 8191, - maxTokens: 4096, - cost: { - input: 30, - output: 60, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-4-turbo', - name: 'OpenAI: GPT-4 Turbo', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 4096, - cost: { - input: 10, - output: 30, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-4-turbo-preview', - name: 'OpenAI: GPT-4 Turbo Preview', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 128000, - maxTokens: 4096, - cost: { - input: 10, - output: 30, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-4.1', - name: 'OpenAI: GPT-4.1', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 1047576, - maxTokens: 4096, - cost: { - input: 2, - output: 8, - cacheRead: 0.5, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-4.1-mini', - name: 'OpenAI: GPT-4.1 Mini', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 1047576, - maxTokens: 32768, - cost: { - input: 0.4, - output: 1.6, - cacheRead: 0.1, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-4.1-nano', - name: 'OpenAI: GPT-4.1 Nano', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 1047576, - maxTokens: 32768, - cost: { - input: 0.1, - output: 0.4, - cacheRead: 0.025, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-4o', - name: 'OpenAI: GPT-4o', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 2.5, - output: 10, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-4o-2024-05-13', - name: 'OpenAI: GPT-4o (2024-05-13)', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 4096, - cost: { - input: 5, - output: 15, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-4o-2024-08-06', - name: 'OpenAI: GPT-4o (2024-08-06)', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 2.5, - output: 10, - cacheRead: 1.25, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-4o-2024-11-20', - name: 'OpenAI: GPT-4o (2024-11-20)', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 2.5, - output: 10, - cacheRead: 1.25, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-4o-mini', - name: 'OpenAI: GPT-4o-mini', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 0.15, - output: 0.6, - cacheRead: 0.075, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-4o-mini-2024-07-18', - name: 'OpenAI: GPT-4o-mini (2024-07-18)', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 0.15, - output: 0.6, - cacheRead: 0.075, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5', - name: 'OpenAI: GPT-5', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.25, - output: 10, - cacheRead: 0.125, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5-codex', - name: 'OpenAI: GPT-5 Codex', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.25, - output: 10, - cacheRead: 0.125, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5-mini', - name: 'OpenAI: GPT-5 Mini', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 0.25, - output: 2, - cacheRead: 0.025, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5-nano', - name: 'OpenAI: GPT-5 Nano', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 4096, - cost: { - input: 0.05, - output: 0.4, - cacheRead: 0.01, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5-pro', - name: 'OpenAI: GPT-5 Pro', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 15, - output: 120, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5.1', - name: 'OpenAI: GPT-5.1', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.25, - output: 10, - cacheRead: 0.13, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5.1-chat', - name: 'OpenAI: GPT-5.1 Chat', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 32000, - cost: { - input: 1.25, - output: 10, - cacheRead: 0.13, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5.1-codex', - name: 'OpenAI: GPT-5.1-Codex', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.25, - output: 10, - cacheRead: 0.13, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5.1-codex-max', - name: 'OpenAI: GPT-5.1-Codex-Max', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.25, - output: 10, - cacheRead: 0.125, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5.1-codex-mini', - name: 'OpenAI: GPT-5.1-Codex-Mini', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 100000, - cost: { - input: 0.25, - output: 2, - cacheRead: 0.025, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5.2', - name: 'OpenAI: GPT-5.2', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.75, - output: 14, - cacheRead: 0.175, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5.2-chat', - name: 'OpenAI: GPT-5.2 Chat', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 1.75, - output: 14, - cacheRead: 0.175, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5.2-codex', - name: 'OpenAI: GPT-5.2-Codex', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.75, - output: 14, - cacheRead: 0.175, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5.2-pro', - name: 'OpenAI: GPT-5.2 Pro', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 21, - output: 168, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5.3-chat', - name: 'OpenAI: GPT-5.3 Chat', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 1.75, - output: 14, - cacheRead: 0.175, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5.3-codex', - name: 'OpenAI: GPT-5.3-Codex', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.75, - output: 14, - cacheRead: 0.175, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5.4', - name: 'OpenAI: GPT-5.4', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1050000, - maxTokens: 128000, - cost: { - input: 2.5, - output: 15, - cacheRead: 0.25, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5.4-mini', - name: 'OpenAI: GPT-5.4 Mini', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 0.75, - output: 4.5, - cacheRead: 0.075, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5.4-nano', - name: 'OpenAI: GPT-5.4 Nano', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 0.2, - output: 1.25, - cacheRead: 0.02, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5.4-pro', - name: 'OpenAI: GPT-5.4 Pro', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1050000, - maxTokens: 128000, - cost: { - input: 30, - output: 180, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5.5', - name: 'OpenAI: GPT-5.5', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1050000, - maxTokens: 128000, - cost: { - input: 5, - output: 30, - cacheRead: 0.5, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5.5-pro', - name: 'OpenAI: GPT-5.5 Pro', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1050000, - maxTokens: 128000, - cost: { - input: 30, - output: 180, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-audio', - name: 'OpenAI: GPT Audio', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 2.5, - output: 10, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-audio-mini', - name: 'OpenAI: GPT Audio Mini', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 0.6, - output: 2.4, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-chat-latest', - name: 'OpenAI: GPT Chat Latest', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 5, - output: 30, - cacheRead: 0.5, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-oss-120b', - name: 'OpenAI: gpt-oss-120b', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 4096, - cost: { - input: 0.039, - output: 0.18, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-oss-120b:free', - name: 'OpenAI: gpt-oss-120b (free)', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 131072, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-oss-20b', - name: 'OpenAI: gpt-oss-20b', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 4096, - cost: { - input: 0.029, - output: 0.14, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-oss-20b:free', - name: 'OpenAI: gpt-oss-20b (free)', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 8192, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-oss-safeguard-20b', - name: 'OpenAI: gpt-oss-safeguard-20b', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 65536, - cost: { - input: 0.075, - output: 0.3, - cacheRead: 0.037, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/o1', - name: 'OpenAI: o1', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 100000, - cost: { - input: 15, - output: 60, - cacheRead: 7.5, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/o3', - name: 'OpenAI: o3', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 100000, - cost: { - input: 2, - output: 8, - cacheRead: 0.5, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/o3-deep-research', - name: 'OpenAI: o3 Deep Research', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 100000, - cost: { - input: 10, - output: 40, - cacheRead: 2.5, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/o3-mini', - name: 'OpenAI: o3 Mini', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 200000, - maxTokens: 100000, - cost: { - input: 1.1, - output: 4.4, - cacheRead: 0.55, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/o3-mini-high', - name: 'OpenAI: o3 Mini High', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 200000, - maxTokens: 100000, - cost: { - input: 1.1, - output: 4.4, - cacheRead: 0.55, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/o3-pro', - name: 'OpenAI: o3 Pro', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 100000, - cost: { - input: 20, - output: 80, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/o4-mini', - name: 'OpenAI: o4 Mini', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 100000, - cost: { - input: 1.1, - output: 4.4, - cacheRead: 0.275, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/o4-mini-deep-research', - name: 'OpenAI: o4 Mini Deep Research', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 100000, - cost: { - input: 2, - output: 8, - cacheRead: 0.5, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/o4-mini-high', - name: 'OpenAI: o4 Mini High', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 100000, - cost: { - input: 1.1, - output: 4.4, - cacheRead: 0.275, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openrouter/auto', - name: 'Auto Router', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 2000000, - maxTokens: 4096, - cost: { - input: -1000000, - output: -1000000, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openrouter/free', - name: 'Free Models Router', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 4096, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openrouter/owl-alpha', - name: 'Owl Alpha', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 1048756, - maxTokens: 262144, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'poolside/laguna-m.1:free', - name: 'Poolside: Laguna M.1 (free)', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 262144, - maxTokens: 32768, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'poolside/laguna-xs.2:free', - name: 'Poolside: Laguna XS.2 (free)', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 262144, - maxTokens: 32768, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'prime-intellect/intellect-3', - name: 'Prime Intellect: INTELLECT-3', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 131072, - cost: { - input: 0.2, - output: 1.1, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen/qwen-2.5-72b-instruct', - name: 'Qwen2.5 72B Instruct', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 131072, - maxTokens: 16384, - cost: { - input: 0.36, - output: 0.4, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen/qwen-plus', - name: 'Qwen: Qwen-Plus', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 1000000, - maxTokens: 32768, - cost: { - input: 0.26, - output: 0.78, - cacheRead: 0.052, - cacheWrite: 0.325, - }, - }, - }, - { - modelId: 'qwen/qwen-plus-2025-07-28', - name: 'Qwen: Qwen Plus 0728', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 1000000, - maxTokens: 32768, - cost: { - input: 0.26, - output: 0.78, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen/qwen-plus-2025-07-28:thinking', - name: 'Qwen: Qwen Plus 0728 (thinking)', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 1000000, - maxTokens: 32768, - cost: { - input: 0.26, - output: 0.78, - cacheRead: 0, - cacheWrite: 0.325, - }, - }, - }, - { - modelId: 'qwen/qwen3-14b', - name: 'Qwen: Qwen3 14B', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 131702, - maxTokens: 40960, - cost: { - input: 0.1, - output: 0.24, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen/qwen3-235b-a22b', - name: 'Qwen: Qwen3 235B A22B', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 8192, - cost: { - input: 0.455, - output: 1.82, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen/qwen3-235b-a22b-2507', - name: 'Qwen: Qwen3 235B A22B Instruct 2507', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 262144, - maxTokens: 16384, - cost: { - input: 0.09, - output: 0.1, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen/qwen3-235b-a22b-thinking-2507', - name: 'Qwen: Qwen3 235B A22B Thinking 2507', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 0.1, - output: 0.1, - cacheRead: 0.1, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen/qwen3-30b-a3b', - name: 'Qwen: Qwen3 30B A3B', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 16384, - cost: { - input: 0.12, - output: 0.5, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen/qwen3-30b-a3b-instruct-2507', - name: 'Qwen: Qwen3 30B A3B Instruct 2507', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 131072, - maxTokens: 32000, - cost: { - input: 0.04815, - output: 0.19305, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen/qwen3-30b-a3b-thinking-2507', - name: 'Qwen: Qwen3 30B A3B Thinking 2507', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 131072, - cost: { - input: 0.08, - output: 0.4, - cacheRead: 0.08, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen/qwen3-32b', - name: 'Qwen: Qwen3 32B', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 16384, - cost: { - input: 0.08, - output: 0.28, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen/qwen3-8b', - name: 'Qwen: Qwen3 8B', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 8192, - cost: { - input: 0.05, - output: 0.4, - cacheRead: 0.05, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen/qwen3-coder', - name: 'Qwen: Qwen3 Coder 480B A35B', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 1048576, - maxTokens: 65536, - cost: { - input: 0.22, - output: 1.8, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen/qwen3-coder-30b-a3b-instruct', - name: 'Qwen: Qwen3 Coder 30B A3B Instruct', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 160000, - maxTokens: 32768, - cost: { - input: 0.07, - output: 0.27, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen/qwen3-coder-flash', - name: 'Qwen: Qwen3 Coder Flash', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 1000000, - maxTokens: 65536, - cost: { - input: 0.195, - output: 0.975, - cacheRead: 0.039, - cacheWrite: 0.24375, - }, - }, - }, - { - modelId: 'qwen/qwen3-coder-next', - name: 'Qwen: Qwen3 Coder Next', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 0.11, - output: 0.8, - cacheRead: 0.07, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen/qwen3-coder-plus', - name: 'Qwen: Qwen3 Coder Plus', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 1000000, - maxTokens: 65536, - cost: { - input: 0.65, - output: 3.25, - cacheRead: 0.13, - cacheWrite: 0.8125, - }, - }, - }, - { - modelId: 'qwen/qwen3-coder:free', - name: 'Qwen: Qwen3 Coder 480B A35B (free)', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 1048576, - maxTokens: 262000, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen/qwen3-max', - name: 'Qwen: Qwen3 Max', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 262144, - maxTokens: 32768, - cost: { - input: 0.78, - output: 3.9, - cacheRead: 0.156, - cacheWrite: 0.975, - }, - }, - }, - { - modelId: 'qwen/qwen3-max-thinking', - name: 'Qwen: Qwen3 Max Thinking', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 262144, - maxTokens: 32768, - cost: { - input: 0.78, - output: 3.9, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen/qwen3-next-80b-a3b-instruct', - name: 'Qwen: Qwen3 Next 80B A3B Instruct', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 262144, - maxTokens: 16384, - cost: { - input: 0.09, - output: 1.1, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen/qwen3-next-80b-a3b-instruct:free', - name: 'Qwen: Qwen3 Next 80B A3B Instruct (free)', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 262144, - maxTokens: 4096, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen/qwen3-next-80b-a3b-thinking', - name: 'Qwen: Qwen3 Next 80B A3B Thinking', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 262144, - maxTokens: 32768, - cost: { - input: 0.0975, - output: 0.78, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen/qwen3-vl-235b-a22b-instruct', - name: 'Qwen: Qwen3 VL 235B A22B Instruct', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 16384, - cost: { - input: 0.2, - output: 0.88, - cacheRead: 0.11, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen/qwen3-vl-235b-a22b-thinking', - name: 'Qwen: Qwen3 VL 235B A22B Thinking', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 131072, - maxTokens: 32768, - cost: { - input: 0.26, - output: 2.6, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen/qwen3-vl-30b-a3b-instruct', - name: 'Qwen: Qwen3 VL 30B A3B Instruct', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 32768, - cost: { - input: 0.13, - output: 0.52, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen/qwen3-vl-30b-a3b-thinking', - name: 'Qwen: Qwen3 VL 30B A3B Thinking', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 131072, - maxTokens: 32768, - cost: { - input: 0.13, - output: 1.56, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen/qwen3-vl-32b-instruct', - name: 'Qwen: Qwen3 VL 32B Instruct', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 32768, - cost: { - input: 0.104, - output: 0.416, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen/qwen3-vl-8b-instruct', - name: 'Qwen: Qwen3 VL 8B Instruct', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 256000, - maxTokens: 32768, - cost: { - input: 0.08, - output: 0.5, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen/qwen3-vl-8b-thinking', - name: 'Qwen: Qwen3 VL 8B Thinking', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 256000, - maxTokens: 32768, - cost: { - input: 0.117, - output: 1.365, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen/qwen3.5-122b-a10b', - name: 'Qwen: Qwen3.5-122B-A10B', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 0.26, - output: 2.08, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen/qwen3.5-27b', - name: 'Qwen: Qwen3.5-27B', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 65536, - cost: { - input: 0.195, - output: 1.56, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen/qwen3.5-35b-a3b', - name: 'Qwen: Qwen3.5-35B-A3B', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 0.14, - output: 1, - cacheRead: 0.05, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen/qwen3.5-397b-a17b', - name: 'Qwen: Qwen3.5 397B A17B', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 65536, - cost: { - input: 0.39, - output: 2.34, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen/qwen3.5-9b', - name: 'Qwen: Qwen3.5-9B', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 0.1, - output: 0.15, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen/qwen3.5-flash-02-23', - name: 'Qwen: Qwen3.5-Flash', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 65536, - cost: { - input: 0.065, - output: 0.26, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen/qwen3.5-plus-02-15', - name: 'Qwen: Qwen3.5 Plus 2026-02-15', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 65536, - cost: { - input: 0.26, - output: 1.56, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen/qwen3.5-plus-20260420', - name: 'Qwen: Qwen3.5 Plus 2026-04-20', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 65536, - cost: { - input: 0.3, - output: 1.8, - cacheRead: 0, - cacheWrite: 0.375, - }, - }, - }, - { - modelId: 'qwen/qwen3.6-27b', - name: 'Qwen: Qwen3.6 27B', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 262140, - cost: { - input: 0.2885, - output: 3.17, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen/qwen3.6-35b-a3b', - name: 'Qwen: Qwen3.6 35B A3B', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 0.15, - output: 1, - cacheRead: 0.05, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen/qwen3.6-flash', - name: 'Qwen: Qwen3.6 Flash', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 65536, - cost: { - input: 0.1875, - output: 1.125, - cacheRead: 0, - cacheWrite: 0.234375, - }, - }, - }, - { - modelId: 'qwen/qwen3.6-max-preview', - name: 'Qwen: Qwen3.6 Max Preview', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 262144, - maxTokens: 65536, - cost: { - input: 1.04, - output: 6.24, - cacheRead: 0, - cacheWrite: 1.3, - }, - }, - }, - { - modelId: 'qwen/qwen3.6-plus', - name: 'Qwen: Qwen3.6 Plus', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 65536, - cost: { - input: 0.325, - output: 1.95, - cacheRead: 0, - cacheWrite: 0.40625, - }, - }, - }, - { - modelId: 'qwen/qwen3.7-max', - name: 'Qwen: Qwen3.7 Max', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 1000000, - maxTokens: 65536, - cost: { - input: 1.25, - output: 3.75, - cacheRead: 0.25, - cacheWrite: 1.5625, - }, - }, - }, - { - modelId: 'qwen/qwen3.7-plus', - name: 'Qwen: Qwen3.7 Plus', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 65536, - cost: { - input: 0.32, - output: 1.28, - cacheRead: 0.064, - cacheWrite: 0.4, - }, - }, - }, - { - modelId: 'rekaai/reka-edge', - name: 'Reka Edge', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 16384, - maxTokens: 16384, - cost: { - input: 0.1, - output: 0.1, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'relace/relace-search', - name: 'Relace: Relace Search', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 256000, - maxTokens: 128000, - cost: { - input: 1, - output: 3, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'sao10k/l3.1-euryale-70b', - name: 'Sao10K: Llama 3.1 Euryale 70B v2.2', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 131072, - maxTokens: 16384, - cost: { - input: 0.85, - output: 0.85, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'stepfun/step-3.5-flash', - name: 'StepFun: Step 3.5 Flash', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 262144, - maxTokens: 16384, - cost: { - input: 0.09, - output: 0.3, - cacheRead: 0.02, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'stepfun/step-3.7-flash', - name: 'StepFun: Step 3.7 Flash', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 256000, - maxTokens: 256000, - cost: { - input: 0.2, - output: 1.15, - cacheRead: 0.04, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'tencent/hy3-preview', - name: 'Tencent: Hy3 preview', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 262144, - maxTokens: 4096, - cost: { - input: 0.063, - output: 0.21, - cacheRead: 0.021, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'thedrummer/rocinante-12b', - name: 'TheDrummer: Rocinante 12B', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 32768, - maxTokens: 32768, - cost: { - input: 0.17, - output: 0.43, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'thedrummer/unslopnemo-12b', - name: 'TheDrummer: UnslopNemo 12B', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 32768, - maxTokens: 32768, - cost: { - input: 0.4, - output: 0.4, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'upstage/solar-pro-3', - name: 'Upstage: Solar Pro 3', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 128000, - maxTokens: 4096, - cost: { - input: 0.15, - output: 0.6, - cacheRead: 0.015, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'x-ai/grok-4.20', - name: 'xAI: Grok 4.20', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 2000000, - maxTokens: 4096, - cost: { - input: 1.25, - output: 2.5, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'x-ai/grok-4.3', - name: 'xAI: Grok 4.3', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 4096, - cost: { - input: 1.25, - output: 2.5, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'x-ai/grok-build-0.1', - name: 'xAI: Grok Build 0.1', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 256000, - maxTokens: 4096, - cost: { - input: 1, - output: 2, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'xiaomi/mimo-v2-flash', - name: 'Xiaomi: MiMo-V2-Flash', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 262144, - maxTokens: 65536, - cost: { - input: 0.1, - output: 0.3, - cacheRead: 0.01, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'xiaomi/mimo-v2.5', - name: 'Xiaomi: MiMo-V2.5', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 131072, - cost: { - input: 0.14, - output: 0.28, - cacheRead: 0.0028, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'xiaomi/mimo-v2.5-pro', - name: 'Xiaomi: MiMo-V2.5-Pro', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 1048576, - maxTokens: 131072, - cost: { - input: 0.435, - output: 0.87, - cacheRead: 0.0036, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'z-ai/glm-4.5', - name: 'Z.ai: GLM 4.5', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 98304, - cost: { - input: 0.6, - output: 2.2, - cacheRead: 0.11, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'z-ai/glm-4.5-air', - name: 'Z.ai: GLM 4.5 Air', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 131070, - cost: { - input: 0.125, - output: 0.85, - cacheRead: 0.06, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'z-ai/glm-4.5v', - name: 'Z.ai: GLM 4.5V', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 65536, - maxTokens: 16384, - cost: { - input: 0.6, - output: 1.8, - cacheRead: 0.11, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'z-ai/glm-4.6', - name: 'Z.ai: GLM 4.6', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 202752, - maxTokens: 131072, - cost: { - input: 0.43, - output: 1.74, - cacheRead: 0.08, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'z-ai/glm-4.6v', - name: 'Z.ai: GLM 4.6V', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 131072, - maxTokens: 32768, - cost: { - input: 0.3, - output: 0.9, - cacheRead: 0.055, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'z-ai/glm-4.7', - name: 'Z.ai: GLM 4.7', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 202752, - maxTokens: 131072, - cost: { - input: 0.4, - output: 1.75, - cacheRead: 0.08, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'z-ai/glm-4.7-flash', - name: 'Z.ai: GLM 4.7 Flash', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 202752, - maxTokens: 16384, - cost: { - input: 0.06, - output: 0.4, - cacheRead: 0.01, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'z-ai/glm-5', - name: 'Z.ai: GLM 5', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 202752, - maxTokens: 4096, - cost: { - input: 0.6, - output: 1.9, - cacheRead: 0.119, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'z-ai/glm-5-turbo', - name: 'Z.ai: GLM 5 Turbo', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 262144, - maxTokens: 131072, - cost: { - input: 1.2, - output: 4, - cacheRead: 0.24, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'z-ai/glm-5.1', - name: 'Z.ai: GLM 5.1', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 202752, - maxTokens: 4096, - cost: { - input: 0.98, - output: 3.08, - cacheRead: 0.182, - cacheWrite: 0, - }, - }, - }, - { - modelId: '~anthropic/claude-fable-latest', - name: 'Anthropic: Claude Fable Latest', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 10, - output: 50, - cacheRead: 1, - cacheWrite: 12.5, - }, - }, - }, - { - modelId: '~anthropic/claude-haiku-latest', - name: 'Anthropic Claude Haiku Latest', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 1, - output: 5, - cacheRead: 0.1, - cacheWrite: 1.25, - }, - }, - }, - { - modelId: '~anthropic/claude-opus-latest', - name: 'Anthropic: Claude Opus Latest', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: '~anthropic/claude-sonnet-latest', - name: 'Anthropic Claude Sonnet Latest', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 3, - output: 15, - cacheRead: 0.3, - cacheWrite: 3.75, - }, - }, - }, - { - modelId: '~google/gemini-flash-latest', - name: 'Google Gemini Flash Latest', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 65536, - cost: { - input: 1.5, - output: 9, - cacheRead: 0.15, - cacheWrite: 0.083333, - }, - }, - }, - { - modelId: '~google/gemini-pro-latest', - name: 'Google Gemini Pro Latest', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 65536, - cost: { - input: 2, - output: 12, - cacheRead: 0.2, - cacheWrite: 0.375, - }, - }, - }, - { - modelId: '~moonshotai/kimi-latest', - name: 'MoonshotAI Kimi Latest', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 262142, - cost: { - input: 0.68, - output: 3.41, - cacheRead: 0.34, - cacheWrite: 0, - }, - }, - }, - { - modelId: '~openai/gpt-latest', - name: 'OpenAI GPT Latest', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1050000, - maxTokens: 128000, - cost: { - input: 5, - output: 30, - cacheRead: 0.5, - cacheWrite: 0, - }, - }, - }, - { - modelId: '~openai/gpt-mini-latest', - name: 'OpenAI GPT Mini Latest', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 0.75, - output: 4.5, - cacheRead: 0.075, - cacheWrite: 0, - }, - }, - }, - ], - }, - mistral: { - name: 'mistral', - config: { - api: 'mistral-conversations', - baseUrl: 'https://api.mistral.ai', - apiKey: 'MISTRAL_API_KEY', - }, - models: [ - { - modelId: 'codestral-latest', - name: 'Codestral (latest)', - config: { - api: 'mistral-conversations', - reasoning: false, - input: ['text'], - contextWindow: 256000, - maxTokens: 4096, - cost: { - input: 0.3, - output: 0.9, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'devstral-2512', - name: 'Devstral 2', - config: { - api: 'mistral-conversations', - reasoning: false, - input: ['text'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 0.4, - output: 2, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'devstral-latest', - name: 'Devstral 2', - config: { - api: 'mistral-conversations', - reasoning: false, - input: ['text'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 0.4, - output: 2, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'devstral-medium-2507', - name: 'Devstral Medium', - config: { - api: 'mistral-conversations', - reasoning: false, - input: ['text'], - contextWindow: 128000, - maxTokens: 128000, - cost: { - input: 0.4, - output: 2, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'devstral-medium-latest', - name: 'Devstral 2 (latest)', - config: { - api: 'mistral-conversations', - reasoning: false, - input: ['text'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 0.4, - output: 2, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'devstral-small-2505', - name: 'Devstral Small 2505', - config: { - api: 'mistral-conversations', - reasoning: false, - input: ['text'], - contextWindow: 128000, - maxTokens: 128000, - cost: { - input: 0.1, - output: 0.3, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'devstral-small-2507', - name: 'Devstral Small', - config: { - api: 'mistral-conversations', - reasoning: false, - input: ['text'], - contextWindow: 128000, - maxTokens: 128000, - cost: { - input: 0.1, - output: 0.3, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'labs-devstral-small-2512', - name: 'Devstral Small 2', - config: { - api: 'mistral-conversations', - reasoning: false, - input: ['text', 'image'], - contextWindow: 256000, - maxTokens: 256000, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'magistral-medium-latest', - name: 'Magistral Medium (latest)', - config: { - api: 'mistral-conversations', - reasoning: true, - input: ['text'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 2, - output: 5, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'magistral-small', - name: 'Magistral Small', - config: { - api: 'mistral-conversations', - reasoning: true, - input: ['text'], - contextWindow: 128000, - maxTokens: 128000, - cost: { - input: 0.5, - output: 1.5, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'ministral-3b-latest', - name: 'Ministral 3B (latest)', - config: { - api: 'mistral-conversations', - reasoning: false, - input: ['text'], - contextWindow: 128000, - maxTokens: 128000, - cost: { - input: 0.04, - output: 0.04, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'ministral-8b-latest', - name: 'Ministral 8B (latest)', - config: { - api: 'mistral-conversations', - reasoning: false, - input: ['text'], - contextWindow: 128000, - maxTokens: 128000, - cost: { - input: 0.1, - output: 0.1, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistral-large-2411', - name: 'Mistral Large 2.1', - config: { - api: 'mistral-conversations', - reasoning: false, - input: ['text'], - contextWindow: 131072, - maxTokens: 16384, - cost: { - input: 2, - output: 6, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistral-large-2512', - name: 'Mistral Large 3', - config: { - api: 'mistral-conversations', - reasoning: false, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 0.5, - output: 1.5, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistral-large-latest', - name: 'Mistral Large (latest)', - config: { - api: 'mistral-conversations', - reasoning: false, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 0.5, - output: 1.5, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistral-medium-2505', - name: 'Mistral Medium 3', - config: { - api: 'mistral-conversations', - reasoning: false, - input: ['text', 'image'], - contextWindow: 131072, - maxTokens: 131072, - cost: { - input: 0.4, - output: 2, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistral-medium-2508', - name: 'Mistral Medium 3.1', - config: { - api: 'mistral-conversations', - reasoning: false, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 0.4, - output: 2, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistral-medium-2604', - name: 'Mistral Medium 3.5', - config: { - api: 'mistral-conversations', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 1.5, - output: 7.5, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistral-medium-3.5', - name: 'Mistral Medium 3.5', - config: { - api: 'mistral-conversations', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 1.5, - output: 7.5, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistral-medium-latest', - name: 'Mistral Medium (latest)', - config: { - api: 'mistral-conversations', - reasoning: false, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 0.4, - output: 2, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistral-nemo', - name: 'Mistral Nemo', - config: { - api: 'mistral-conversations', - reasoning: false, - input: ['text'], - contextWindow: 128000, - maxTokens: 128000, - cost: { - input: 0.15, - output: 0.15, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistral-small-2506', - name: 'Mistral Small 3.2', - config: { - api: 'mistral-conversations', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 0.1, - output: 0.3, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistral-small-2603', - name: 'Mistral Small 4', - config: { - api: 'mistral-conversations', - reasoning: true, - input: ['text', 'image'], - contextWindow: 256000, - maxTokens: 256000, - cost: { - input: 0.15, - output: 0.6, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistral-small-latest', - name: 'Mistral Small (latest)', - config: { - api: 'mistral-conversations', - reasoning: true, - input: ['text', 'image'], - contextWindow: 256000, - maxTokens: 256000, - cost: { - input: 0.15, - output: 0.6, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'open-mistral-7b', - name: 'Mistral 7B', - config: { - api: 'mistral-conversations', - reasoning: false, - input: ['text'], - contextWindow: 8000, - maxTokens: 8000, - cost: { - input: 0.25, - output: 0.25, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'open-mistral-nemo', - name: 'Open Mistral Nemo', - config: { - api: 'mistral-conversations', - reasoning: false, - input: ['text'], - contextWindow: 128000, - maxTokens: 128000, - cost: { - input: 0.15, - output: 0.15, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'open-mixtral-8x22b', - name: 'Mixtral 8x22B', - config: { - api: 'mistral-conversations', - reasoning: false, - input: ['text'], - contextWindow: 64000, - maxTokens: 64000, - cost: { - input: 2, - output: 6, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'open-mixtral-8x7b', - name: 'Mixtral 8x7B', - config: { - api: 'mistral-conversations', - reasoning: false, - input: ['text'], - contextWindow: 32000, - maxTokens: 32000, - cost: { - input: 0.7, - output: 0.7, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'pixtral-12b', - name: 'Pixtral 12B', - config: { - api: 'mistral-conversations', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 128000, - cost: { - input: 0.15, - output: 0.15, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'pixtral-large-latest', - name: 'Pixtral Large (latest)', - config: { - api: 'mistral-conversations', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 128000, - cost: { - input: 2, - output: 6, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - ], - }, - 'amazon-bedrock': { - name: 'amazon-bedrock', - config: { - api: 'bedrock-converse-stream', - baseUrl: 'https://bedrock-runtime.us-east-1.amazonaws.com', - apiKey: '', - }, - models: [ - { - modelId: 'amazon.nova-2-lite-v1:0', - name: 'Nova 2 Lite', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 4096, - cost: { - input: 0.33, - output: 2.75, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'amazon.nova-lite-v1:0', - name: 'Nova Lite', - config: { - api: 'bedrock-converse-stream', - reasoning: false, - input: ['text', 'image'], - contextWindow: 300000, - maxTokens: 8192, - cost: { - input: 0.06, - output: 0.24, - cacheRead: 0.015, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'amazon.nova-micro-v1:0', - name: 'Nova Micro', - config: { - api: 'bedrock-converse-stream', - reasoning: false, - input: ['text'], - contextWindow: 128000, - maxTokens: 8192, - cost: { - input: 0.035, - output: 0.14, - cacheRead: 0.00875, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'amazon.nova-pro-v1:0', - name: 'Nova Pro', - config: { - api: 'bedrock-converse-stream', - reasoning: false, - input: ['text', 'image'], - contextWindow: 300000, - maxTokens: 8192, - cost: { - input: 0.8, - output: 3.2, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'anthropic.claude-haiku-4-5-20251001-v1:0', - name: 'Claude Haiku 4.5', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 1, - output: 5, - cacheRead: 0.1, - cacheWrite: 1.25, - }, - }, - }, - { - modelId: 'anthropic.claude-opus-4-1-20250805-v1:0', - name: 'Claude Opus 4.1', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 32000, - cost: { - input: 15, - output: 75, - cacheRead: 1.5, - cacheWrite: 18.75, - }, - }, - }, - { - modelId: 'anthropic.claude-opus-4-5-20251101-v1:0', - name: 'Claude Opus 4.5', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'anthropic.claude-opus-4-6-v1', - name: 'Claude Opus 4.6', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'anthropic.claude-opus-4-7', - name: 'Claude Opus 4.7', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'anthropic.claude-opus-4-8', - name: 'Claude Opus 4.8', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'anthropic.claude-sonnet-4-5-20250929-v1:0', - name: 'Claude Sonnet 4.5', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 3, - output: 15, - cacheRead: 0.3, - cacheWrite: 3.75, - }, - }, - }, - { - modelId: 'anthropic.claude-sonnet-4-6', - name: 'Claude Sonnet 4.6', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 64000, - cost: { - input: 3, - output: 15, - cacheRead: 0.3, - cacheWrite: 3.75, - }, - }, - }, - { - modelId: 'au.anthropic.claude-haiku-4-5-20251001-v1:0', - name: 'Claude Haiku 4.5 (AU)', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 1, - output: 5, - cacheRead: 0.1, - cacheWrite: 1.25, - }, - }, - }, - { - modelId: 'au.anthropic.claude-opus-4-6-v1', - name: 'AU Anthropic Claude Opus 4.6', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 16.5, - output: 82.5, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'au.anthropic.claude-opus-4-8', - name: 'Claude Opus 4.8 (AU)', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'au.anthropic.claude-sonnet-4-5-20250929-v1:0', - name: 'Claude Sonnet 4.5 (AU)', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 3, - output: 15, - cacheRead: 0.3, - cacheWrite: 3.75, - }, - }, - }, - { - modelId: 'au.anthropic.claude-sonnet-4-6', - name: 'AU Anthropic Claude Sonnet 4.6', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 3.3, - output: 16.5, - cacheRead: 0.33, - cacheWrite: 4.125, - }, - }, - }, - { - modelId: 'deepseek.r1-v1:0', - name: 'DeepSeek-R1', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text'], - contextWindow: 128000, - maxTokens: 32768, - cost: { - input: 1.35, - output: 5.4, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'deepseek.v3-v1:0', - name: 'DeepSeek-V3.1', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text'], - contextWindow: 163840, - maxTokens: 81920, - cost: { - input: 0.58, - output: 1.68, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'deepseek.v3.2', - name: 'DeepSeek-V3.2', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text'], - contextWindow: 163840, - maxTokens: 81920, - cost: { - input: 0.62, - output: 1.85, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'eu.anthropic.claude-fable-5', - name: 'Claude Fable 5 (EU)', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 11, - output: 55, - cacheRead: 1.1, - cacheWrite: 13.75, - }, - }, - }, - { - modelId: 'eu.anthropic.claude-haiku-4-5-20251001-v1:0', - name: 'Claude Haiku 4.5 (EU)', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 1, - output: 5, - cacheRead: 0.1, - cacheWrite: 1.25, - }, - }, - }, - { - modelId: 'eu.anthropic.claude-opus-4-5-20251101-v1:0', - name: 'Claude Opus 4.5 (EU)', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'eu.anthropic.claude-opus-4-6-v1', - name: 'Claude Opus 4.6 (EU)', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 5.5, - output: 27.5, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'eu.anthropic.claude-opus-4-7', - name: 'Claude Opus 4.7 (EU)', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 5.5, - output: 27.5, - cacheRead: 0.55, - cacheWrite: 6.875, - }, - }, - }, - { - modelId: 'eu.anthropic.claude-opus-4-8', - name: 'Claude Opus 4.8 (EU)', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 5.5, - output: 27.5, - cacheRead: 0.55, - cacheWrite: 6.875, - }, - }, - }, - { - modelId: 'eu.anthropic.claude-sonnet-4-5-20250929-v1:0', - name: 'Claude Sonnet 4.5 (EU)', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 3.3, - output: 16.5, - cacheRead: 0.33, - cacheWrite: 4.125, - }, - }, - }, - { - modelId: 'eu.anthropic.claude-sonnet-4-6', - name: 'Claude Sonnet 4.6 (EU)', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 64000, - cost: { - input: 3.3, - output: 16.5, - cacheRead: 0.33, - cacheWrite: 4.125, - }, - }, - }, - { - modelId: 'global.anthropic.claude-fable-5', - name: 'Claude Fable 5 (Global)', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 10, - output: 50, - cacheRead: 1, - cacheWrite: 12.5, - }, - }, - }, - { - modelId: 'global.anthropic.claude-haiku-4-5-20251001-v1:0', - name: 'Claude Haiku 4.5 (Global)', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 1, - output: 5, - cacheRead: 0.1, - cacheWrite: 1.25, - }, - }, - }, - { - modelId: 'global.anthropic.claude-opus-4-5-20251101-v1:0', - name: 'Claude Opus 4.5 (Global)', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'global.anthropic.claude-opus-4-6-v1', - name: 'Claude Opus 4.6 (Global)', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'global.anthropic.claude-opus-4-7', - name: 'Claude Opus 4.7 (Global)', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'global.anthropic.claude-opus-4-8', - name: 'Claude Opus 4.8 (Global)', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'global.anthropic.claude-sonnet-4-5-20250929-v1:0', - name: 'Claude Sonnet 4.5 (Global)', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 3, - output: 15, - cacheRead: 0.3, - cacheWrite: 3.75, - }, - }, - }, - { - modelId: 'global.anthropic.claude-sonnet-4-6', - name: 'Claude Sonnet 4.6 (Global)', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 64000, - cost: { - input: 3, - output: 15, - cacheRead: 0.3, - cacheWrite: 3.75, - }, - }, - }, - { - modelId: 'google.gemma-3-27b-it', - name: 'Google Gemma 3 27B Instruct', - config: { - api: 'bedrock-converse-stream', - reasoning: false, - input: ['text', 'image'], - contextWindow: 202752, - maxTokens: 8192, - cost: { - input: 0.12, - output: 0.2, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'google.gemma-3-4b-it', - name: 'Gemma 3 4B IT', - config: { - api: 'bedrock-converse-stream', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 4096, - cost: { - input: 0.04, - output: 0.08, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'jp.anthropic.claude-opus-4-7', - name: 'Claude Opus 4.7 (JP)', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'jp.anthropic.claude-opus-4-8', - name: 'Claude Opus 4.8 (JP)', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'jp.anthropic.claude-sonnet-4-5-20250929-v1:0', - name: 'Claude Sonnet 4.5 (JP)', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 3, - output: 15, - cacheRead: 0.3, - cacheWrite: 3.75, - }, - }, - }, - { - modelId: 'jp.anthropic.claude-sonnet-4-6', - name: 'Claude Sonnet 4.6 (JP)', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 64000, - cost: { - input: 3, - output: 15, - cacheRead: 0.3, - cacheWrite: 3.75, - }, - }, - }, - { - modelId: 'meta.llama3-1-70b-instruct-v1:0', - name: 'Llama 3.1 70B Instruct', - config: { - api: 'bedrock-converse-stream', - reasoning: false, - input: ['text'], - contextWindow: 128000, - maxTokens: 4096, - cost: { - input: 0.72, - output: 0.72, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'meta.llama3-1-8b-instruct-v1:0', - name: 'Llama 3.1 8B Instruct', - config: { - api: 'bedrock-converse-stream', - reasoning: false, - input: ['text'], - contextWindow: 128000, - maxTokens: 4096, - cost: { - input: 0.22, - output: 0.22, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'meta.llama3-3-70b-instruct-v1:0', - name: 'Llama 3.3 70B Instruct', - config: { - api: 'bedrock-converse-stream', - reasoning: false, - input: ['text'], - contextWindow: 128000, - maxTokens: 4096, - cost: { - input: 0.72, - output: 0.72, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'meta.llama4-maverick-17b-instruct-v1:0', - name: 'Llama 4 Maverick 17B Instruct', - config: { - api: 'bedrock-converse-stream', - reasoning: false, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 16384, - cost: { - input: 0.24, - output: 0.97, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'meta.llama4-scout-17b-instruct-v1:0', - name: 'Llama 4 Scout 17B Instruct', - config: { - api: 'bedrock-converse-stream', - reasoning: false, - input: ['text', 'image'], - contextWindow: 3500000, - maxTokens: 16384, - cost: { - input: 0.17, - output: 0.66, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'minimax.minimax-m2', - name: 'MiniMax M2', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text'], - contextWindow: 204608, - maxTokens: 128000, - cost: { - input: 0.3, - output: 1.2, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'minimax.minimax-m2.1', - name: 'MiniMax M2.1', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text'], - contextWindow: 204800, - maxTokens: 131072, - cost: { - input: 0.3, - output: 1.2, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'minimax.minimax-m2.5', - name: 'MiniMax M2.5', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text'], - contextWindow: 196608, - maxTokens: 98304, - cost: { - input: 0.3, - output: 1.2, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistral.devstral-2-123b', - name: 'Devstral 2 123B', - config: { - api: 'bedrock-converse-stream', - reasoning: false, - input: ['text'], - contextWindow: 256000, - maxTokens: 8192, - cost: { - input: 0.4, - output: 2, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistral.magistral-small-2509', - name: 'Magistral Small 1.2', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 40000, - cost: { - input: 0.5, - output: 1.5, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistral.ministral-3-14b-instruct', - name: 'Ministral 14B 3.0', - config: { - api: 'bedrock-converse-stream', - reasoning: false, - input: ['text'], - contextWindow: 128000, - maxTokens: 4096, - cost: { - input: 0.2, - output: 0.2, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistral.ministral-3-3b-instruct', - name: 'Ministral 3 3B', - config: { - api: 'bedrock-converse-stream', - reasoning: false, - input: ['text', 'image'], - contextWindow: 256000, - maxTokens: 8192, - cost: { - input: 0.1, - output: 0.1, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistral.ministral-3-8b-instruct', - name: 'Ministral 3 8B', - config: { - api: 'bedrock-converse-stream', - reasoning: false, - input: ['text'], - contextWindow: 128000, - maxTokens: 4096, - cost: { - input: 0.15, - output: 0.15, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistral.mistral-large-3-675b-instruct', - name: 'Mistral Large 3', - config: { - api: 'bedrock-converse-stream', - reasoning: false, - input: ['text', 'image'], - contextWindow: 256000, - maxTokens: 8192, - cost: { - input: 0.5, - output: 1.5, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistral.pixtral-large-2502-v1:0', - name: 'Pixtral Large (25.02)', - config: { - api: 'bedrock-converse-stream', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 8192, - cost: { - input: 2, - output: 6, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistral.voxtral-mini-3b-2507', - name: 'Voxtral Mini 3B 2507', - config: { - api: 'bedrock-converse-stream', - reasoning: false, - input: ['text'], - contextWindow: 128000, - maxTokens: 4096, - cost: { - input: 0.04, - output: 0.04, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistral.voxtral-small-24b-2507', - name: 'Voxtral Small 24B 2507', - config: { - api: 'bedrock-converse-stream', - reasoning: false, - input: ['text'], - contextWindow: 32000, - maxTokens: 8192, - cost: { - input: 0.15, - output: 0.35, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'moonshot.kimi-k2-thinking', - name: 'Kimi K2 Thinking', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text'], - contextWindow: 262143, - maxTokens: 16000, - cost: { - input: 0.6, - output: 2.5, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'moonshotai.kimi-k2.5', - name: 'Kimi K2.5', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262143, - maxTokens: 16000, - cost: { - input: 0.6, - output: 3, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'nvidia.nemotron-nano-12b-v2', - name: 'NVIDIA Nemotron Nano 12B v2 VL BF16', - config: { - api: 'bedrock-converse-stream', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 4096, - cost: { - input: 0.2, - output: 0.6, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'nvidia.nemotron-nano-3-30b', - name: 'NVIDIA Nemotron Nano 3 30B', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text'], - contextWindow: 128000, - maxTokens: 4096, - cost: { - input: 0.06, - output: 0.24, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'nvidia.nemotron-nano-9b-v2', - name: 'NVIDIA Nemotron Nano 9B v2', - config: { - api: 'bedrock-converse-stream', - reasoning: false, - input: ['text'], - contextWindow: 128000, - maxTokens: 4096, - cost: { - input: 0.06, - output: 0.23, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'nvidia.nemotron-super-3-120b', - name: 'NVIDIA Nemotron 3 Super 120B A12B', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text'], - contextWindow: 262144, - maxTokens: 131072, - cost: { - input: 0.15, - output: 0.65, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai.gpt-5.4', - name: 'GPT-5.4', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 272000, - maxTokens: 128000, - cost: { - input: 2.75, - output: 16.5, - cacheRead: 0.275, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai.gpt-5.5', - name: 'GPT-5.5', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 272000, - maxTokens: 128000, - cost: { - input: 5.5, - output: 33, - cacheRead: 0.55, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai.gpt-oss-120b', - name: 'gpt-oss-120b', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 0.15, - output: 0.6, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai.gpt-oss-120b-1:0', - name: 'gpt-oss-120b', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 0.15, - output: 0.6, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai.gpt-oss-20b', - name: 'gpt-oss-20b', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 0.07, - output: 0.3, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai.gpt-oss-20b-1:0', - name: 'gpt-oss-20b', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 0.07, - output: 0.3, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai.gpt-oss-safeguard-120b', - name: 'GPT OSS Safeguard 120B', - config: { - api: 'bedrock-converse-stream', - reasoning: false, - input: ['text'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 0.15, - output: 0.6, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai.gpt-oss-safeguard-20b', - name: 'GPT OSS Safeguard 20B', - config: { - api: 'bedrock-converse-stream', - reasoning: false, - input: ['text'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 0.07, - output: 0.2, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen.qwen3-235b-a22b-2507-v1:0', - name: 'Qwen3 235B A22B 2507', - config: { - api: 'bedrock-converse-stream', - reasoning: false, - input: ['text'], - contextWindow: 262144, - maxTokens: 131072, - cost: { - input: 0.22, - output: 0.88, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen.qwen3-32b-v1:0', - name: 'Qwen3 32B (dense)', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text'], - contextWindow: 16384, - maxTokens: 16384, - cost: { - input: 0.15, - output: 0.6, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen.qwen3-coder-30b-a3b-v1:0', - name: 'Qwen3 Coder 30B A3B Instruct', - config: { - api: 'bedrock-converse-stream', - reasoning: false, - input: ['text'], - contextWindow: 262144, - maxTokens: 131072, - cost: { - input: 0.15, - output: 0.6, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen.qwen3-coder-480b-a35b-v1:0', - name: 'Qwen3 Coder 480B A35B Instruct', - config: { - api: 'bedrock-converse-stream', - reasoning: false, - input: ['text'], - contextWindow: 131072, - maxTokens: 65536, - cost: { - input: 0.22, - output: 1.8, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen.qwen3-coder-next', - name: 'Qwen3 Coder Next', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 65536, - cost: { - input: 0.22, - output: 1.8, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen.qwen3-next-80b-a3b', - name: 'Qwen/Qwen3-Next-80B-A3B-Instruct', - config: { - api: 'bedrock-converse-stream', - reasoning: false, - input: ['text'], - contextWindow: 262000, - maxTokens: 262000, - cost: { - input: 0.14, - output: 1.4, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen.qwen3-vl-235b-a22b', - name: 'Qwen/Qwen3-VL-235B-A22B-Instruct', - config: { - api: 'bedrock-converse-stream', - reasoning: false, - input: ['text', 'image'], - contextWindow: 262000, - maxTokens: 262000, - cost: { - input: 0.3, - output: 1.5, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'us.anthropic.claude-fable-5', - name: 'Claude Fable 5 (US)', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 10, - output: 50, - cacheRead: 1, - cacheWrite: 12.5, - }, - }, - }, - { - modelId: 'us.anthropic.claude-haiku-4-5-20251001-v1:0', - name: 'Claude Haiku 4.5 (US)', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 1, - output: 5, - cacheRead: 0.1, - cacheWrite: 1.25, - }, - }, - }, - { - modelId: 'us.anthropic.claude-opus-4-1-20250805-v1:0', - name: 'Claude Opus 4.1 (US)', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 32000, - cost: { - input: 15, - output: 75, - cacheRead: 1.5, - cacheWrite: 18.75, - }, - }, - }, - { - modelId: 'us.anthropic.claude-opus-4-5-20251101-v1:0', - name: 'Claude Opus 4.5 (US)', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'us.anthropic.claude-opus-4-6-v1', - name: 'Claude Opus 4.6 (US)', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'us.anthropic.claude-opus-4-7', - name: 'Claude Opus 4.7 (US)', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'us.anthropic.claude-opus-4-8', - name: 'Claude Opus 4.8 (US)', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'us.anthropic.claude-sonnet-4-5-20250929-v1:0', - name: 'Claude Sonnet 4.5 (US)', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 3, - output: 15, - cacheRead: 0.3, - cacheWrite: 3.75, - }, - }, - }, - { - modelId: 'us.anthropic.claude-sonnet-4-6', - name: 'Claude Sonnet 4.6 (US)', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 64000, - cost: { - input: 3, - output: 15, - cacheRead: 0.3, - cacheWrite: 3.75, - }, - }, - }, - { - modelId: 'us.deepseek.r1-v1:0', - name: 'DeepSeek-R1 (US)', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text'], - contextWindow: 128000, - maxTokens: 32768, - cost: { - input: 1.35, - output: 5.4, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'us.meta.llama4-maverick-17b-instruct-v1:0', - name: 'Llama 4 Maverick 17B Instruct (US)', - config: { - api: 'bedrock-converse-stream', - reasoning: false, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 16384, - cost: { - input: 0.24, - output: 0.97, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'us.meta.llama4-scout-17b-instruct-v1:0', - name: 'Llama 4 Scout 17B Instruct (US)', - config: { - api: 'bedrock-converse-stream', - reasoning: false, - input: ['text', 'image'], - contextWindow: 3500000, - maxTokens: 16384, - cost: { - input: 0.17, - output: 0.66, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'writer.palmyra-x4-v1:0', - name: 'Palmyra X4', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text'], - contextWindow: 122880, - maxTokens: 8192, - cost: { - input: 2.5, - output: 10, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'writer.palmyra-x5-v1:0', - name: 'Palmyra X5', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text'], - contextWindow: 1040000, - maxTokens: 8192, - cost: { - input: 0.6, - output: 6, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'zai.glm-4.7', - name: 'GLM-4.7', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text'], - contextWindow: 204800, - maxTokens: 131072, - cost: { - input: 0.6, - output: 2.2, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'zai.glm-4.7-flash', - name: 'GLM-4.7-Flash', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text'], - contextWindow: 200000, - maxTokens: 131072, - cost: { - input: 0.07, - output: 0.4, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'zai.glm-5', - name: 'GLM-5', - config: { - api: 'bedrock-converse-stream', - reasoning: true, - input: ['text'], - contextWindow: 202752, - maxTokens: 101376, - cost: { - input: 1, - output: 3.2, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - ], - }, - 'ant-ling': { - name: 'ant-ling', - config: { - api: 'openai-completions', - baseUrl: 'https://api.ant-ling.com/v1', - apiKey: '', - }, - models: [ - { - modelId: 'Ling-2.6-1T', - name: 'Ling 2.6 1T', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 262144, - maxTokens: 65536, - cost: { - input: 0.06, - output: 0.25, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'Ling-2.6-flash', - name: 'Ling 2.6 Flash', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 262144, - maxTokens: 65536, - cost: { - input: 0.01, - output: 0.02, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'Ring-2.6-1T', - name: 'Ring 2.6 1T', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 262144, - maxTokens: 65536, - cost: { - input: 0.06, - output: 0.25, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - ], - }, - 'azure-openai-responses': { - name: 'azure-openai-responses', - config: { - api: 'azure-openai-responses', - baseUrl: '', - apiKey: 'AZURE_OPENAI_API_KEY', - }, - models: [ - { - modelId: 'gpt-4', - name: 'GPT-4', - config: { - api: 'azure-openai-responses', - reasoning: false, - input: ['text'], - contextWindow: 8192, - maxTokens: 8192, - cost: { - input: 30, - output: 60, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-4-turbo', - name: 'GPT-4 Turbo', - config: { - api: 'azure-openai-responses', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 4096, - cost: { - input: 10, - output: 30, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-4.1', - name: 'GPT-4.1', - config: { - api: 'azure-openai-responses', - reasoning: false, - input: ['text', 'image'], - contextWindow: 1047576, - maxTokens: 32768, - cost: { - input: 2, - output: 8, - cacheRead: 0.5, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-4.1-mini', - name: 'GPT-4.1 mini', - config: { - api: 'azure-openai-responses', - reasoning: false, - input: ['text', 'image'], - contextWindow: 1047576, - maxTokens: 32768, - cost: { - input: 0.4, - output: 1.6, - cacheRead: 0.1, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-4.1-nano', - name: 'GPT-4.1 nano', - config: { - api: 'azure-openai-responses', - reasoning: false, - input: ['text', 'image'], - contextWindow: 1047576, - maxTokens: 32768, - cost: { - input: 0.1, - output: 0.4, - cacheRead: 0.025, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-4o', - name: 'GPT-4o', - config: { - api: 'azure-openai-responses', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 2.5, - output: 10, - cacheRead: 1.25, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-4o-2024-05-13', - name: 'GPT-4o (2024-05-13)', - config: { - api: 'azure-openai-responses', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 4096, - cost: { - input: 5, - output: 15, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-4o-2024-08-06', - name: 'GPT-4o (2024-08-06)', - config: { - api: 'azure-openai-responses', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 2.5, - output: 10, - cacheRead: 1.25, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-4o-2024-11-20', - name: 'GPT-4o (2024-11-20)', - config: { - api: 'azure-openai-responses', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 2.5, - output: 10, - cacheRead: 1.25, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-4o-mini', - name: 'GPT-4o mini', - config: { - api: 'azure-openai-responses', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 0.15, - output: 0.6, - cacheRead: 0.075, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5', - name: 'GPT-5', - config: { - api: 'azure-openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.25, - output: 10, - cacheRead: 0.125, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5-chat-latest', - name: 'GPT-5 Chat Latest', - config: { - api: 'azure-openai-responses', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 1.25, - output: 10, - cacheRead: 0.125, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5-codex', - name: 'GPT-5-Codex', - config: { - api: 'azure-openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.25, - output: 10, - cacheRead: 0.125, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5-mini', - name: 'GPT-5 Mini', - config: { - api: 'azure-openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 0.25, - output: 2, - cacheRead: 0.025, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5-nano', - name: 'GPT-5 Nano', - config: { - api: 'azure-openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 0.05, - output: 0.4, - cacheRead: 0.005, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5-pro', - name: 'GPT-5 Pro', - config: { - api: 'azure-openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 15, - output: 120, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.1', - name: 'GPT-5.1', - config: { - api: 'azure-openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.25, - output: 10, - cacheRead: 0.125, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.1-chat-latest', - name: 'GPT-5.1 Chat', - config: { - api: 'azure-openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 1.25, - output: 10, - cacheRead: 0.125, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.1-codex', - name: 'GPT-5.1 Codex', - config: { - api: 'azure-openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.25, - output: 10, - cacheRead: 0.125, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.1-codex-max', - name: 'GPT-5.1 Codex Max', - config: { - api: 'azure-openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.25, - output: 10, - cacheRead: 0.125, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.1-codex-mini', - name: 'GPT-5.1 Codex mini', - config: { - api: 'azure-openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 0.25, - output: 2, - cacheRead: 0.025, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.2', - name: 'GPT-5.2', - config: { - api: 'azure-openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.75, - output: 14, - cacheRead: 0.175, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.2-chat-latest', - name: 'GPT-5.2 Chat', - config: { - api: 'azure-openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 1.75, - output: 14, - cacheRead: 0.175, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.2-codex', - name: 'GPT-5.2 Codex', - config: { - api: 'azure-openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.75, - output: 14, - cacheRead: 0.175, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.2-pro', - name: 'GPT-5.2 Pro', - config: { - api: 'azure-openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 21, - output: 168, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.3-chat-latest', - name: 'GPT-5.3 Chat (latest)', - config: { - api: 'azure-openai-responses', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 1.75, - output: 14, - cacheRead: 0.175, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.3-codex', - name: 'GPT-5.3 Codex', - config: { - api: 'azure-openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.75, - output: 14, - cacheRead: 0.175, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.3-codex-spark', - name: 'GPT-5.3 Codex Spark', - config: { - api: 'azure-openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 32000, - cost: { - input: 1.75, - output: 14, - cacheRead: 0.175, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.4', - name: 'GPT-5.4', - config: { - api: 'azure-openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1050000, - maxTokens: 128000, - cost: { - input: 2.5, - output: 15, - cacheRead: 0.25, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.4-mini', - name: 'GPT-5.4 mini', - config: { - api: 'azure-openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 0.75, - output: 4.5, - cacheRead: 0.075, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.4-nano', - name: 'GPT-5.4 nano', - config: { - api: 'azure-openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 0.2, - output: 1.25, - cacheRead: 0.02, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.4-pro', - name: 'GPT-5.4 Pro', - config: { - api: 'azure-openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1050000, - maxTokens: 128000, - cost: { - input: 30, - output: 180, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.5', - name: 'GPT-5.5', - config: { - api: 'azure-openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1050000, - maxTokens: 128000, - cost: { - input: 5, - output: 30, - cacheRead: 0.5, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.5-pro', - name: 'GPT-5.5 Pro', - config: { - api: 'azure-openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1050000, - maxTokens: 128000, - cost: { - input: 30, - output: 180, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'o1', - name: 'o1', - config: { - api: 'azure-openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 100000, - cost: { - input: 15, - output: 60, - cacheRead: 7.5, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'o1-pro', - name: 'o1-pro', - config: { - api: 'azure-openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 100000, - cost: { - input: 150, - output: 600, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'o3', - name: 'o3', - config: { - api: 'azure-openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 100000, - cost: { - input: 2, - output: 8, - cacheRead: 0.5, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'o3-deep-research', - name: 'o3-deep-research', - config: { - api: 'azure-openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 100000, - cost: { - input: 10, - output: 40, - cacheRead: 2.5, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'o3-mini', - name: 'o3-mini', - config: { - api: 'azure-openai-responses', - reasoning: true, - input: ['text'], - contextWindow: 200000, - maxTokens: 100000, - cost: { - input: 1.1, - output: 4.4, - cacheRead: 0.55, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'o3-pro', - name: 'o3-pro', - config: { - api: 'azure-openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 100000, - cost: { - input: 20, - output: 80, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'o4-mini', - name: 'o4-mini', - config: { - api: 'azure-openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 100000, - cost: { - input: 1.1, - output: 4.4, - cacheRead: 0.275, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'o4-mini-deep-research', - name: 'o4-mini-deep-research', - config: { - api: 'azure-openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 100000, - cost: { - input: 2, - output: 8, - cacheRead: 0.5, - cacheWrite: 0, - }, - }, - }, - ], - }, - cerebras: { - name: 'cerebras', - config: { - api: 'openai-completions', - baseUrl: 'https://api.cerebras.ai/v1', - apiKey: 'CEREBRAS_API_KEY', - }, - models: [ - { - modelId: 'gpt-oss-120b', - name: 'GPT OSS 120B', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 40960, - cost: { - input: 0.35, - output: 0.75, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'zai-glm-4.7', - name: 'Z.AI GLM-4.7', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 40960, - cost: { - input: 2.25, - output: 2.75, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - ], - }, - 'cloudflare-ai-gateway': { - name: 'cloudflare-ai-gateway', - config: { - api: 'anthropic-messages', - baseUrl: - 'https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic', - apiKey: 'CLOUDFLARE_API_KEY', - }, - models: [ - { - modelId: 'claude-3-5-haiku', - name: 'Claude Haiku 3.5 (latest)', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 8192, - cost: { - input: 0.8, - output: 4, - cacheRead: 0.08, - cacheWrite: 1, - }, - }, - }, - { - modelId: 'claude-3-haiku', - name: 'Claude Haiku 3', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 4096, - cost: { - input: 0.25, - output: 1.25, - cacheRead: 0.03, - cacheWrite: 0.3, - }, - }, - }, - { - modelId: 'claude-3-opus', - name: 'Claude Opus 3', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 4096, - cost: { - input: 15, - output: 75, - cacheRead: 1.5, - cacheWrite: 18.75, - }, - }, - }, - { - modelId: 'claude-3-sonnet', - name: 'Claude Sonnet 3', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 4096, - cost: { - input: 3, - output: 15, - cacheRead: 0.3, - cacheWrite: 0.3, - }, - }, - }, - { - modelId: 'claude-3.5-haiku', - name: 'Claude Haiku 3.5 (latest)', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 8192, - cost: { - input: 0.8, - output: 4, - cacheRead: 0.08, - cacheWrite: 1, - }, - }, - }, - { - modelId: 'claude-3.5-sonnet', - name: 'Claude Sonnet 3.5 v2', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 8192, - cost: { - input: 3, - output: 15, - cacheRead: 0.3, - cacheWrite: 3.75, - }, - }, - }, - { - modelId: 'claude-fable-5', - name: 'Claude Fable 5', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 10, - output: 50, - cacheRead: 1, - cacheWrite: 12.5, - }, - }, - }, - { - modelId: 'claude-haiku-4-5', - name: 'Claude Haiku 4.5 (latest)', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 1, - output: 5, - cacheRead: 0.1, - cacheWrite: 1.25, - }, - }, - }, - { - modelId: 'claude-opus-4', - name: 'Claude Opus 4 (latest)', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 32000, - cost: { - input: 15, - output: 75, - cacheRead: 1.5, - cacheWrite: 18.75, - }, - }, - }, - { - modelId: 'claude-opus-4-1', - name: 'Claude Opus 4.1 (latest)', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 32000, - cost: { - input: 15, - output: 75, - cacheRead: 1.5, - cacheWrite: 18.75, - }, - }, - }, - { - modelId: 'claude-opus-4-5', - name: 'Claude Opus 4.5 (latest)', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'claude-opus-4-6', - name: 'Claude Opus 4.6 (latest)', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'claude-opus-4-7', - name: 'Claude Opus 4.7', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'claude-opus-4-8', - name: 'Claude Opus 4.8', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'claude-sonnet-4', - name: 'Claude Sonnet 4 (latest)', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 3, - output: 15, - cacheRead: 0.3, - cacheWrite: 3.75, - }, - }, - }, - { - modelId: 'claude-sonnet-4-5', - name: 'Claude Sonnet 4.5 (latest)', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 3, - output: 15, - cacheRead: 0.3, - cacheWrite: 3.75, - }, - }, - }, - { - modelId: 'claude-sonnet-4-6', - name: 'Claude Sonnet 4.6', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 64000, - cost: { - input: 3, - output: 15, - cacheRead: 0.3, - cacheWrite: 3.75, - }, - }, - }, - { - modelId: 'gpt-4', - name: 'GPT-4', - config: { - api: 'openai-responses', - reasoning: false, - input: ['text'], - contextWindow: 8192, - maxTokens: 8192, - cost: { - input: 30, - output: 60, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-4-turbo', - name: 'GPT-4 Turbo', - config: { - api: 'openai-responses', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 4096, - cost: { - input: 10, - output: 30, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-4o', - name: 'GPT-4o', - config: { - api: 'openai-responses', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 2.5, - output: 10, - cacheRead: 1.25, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-4o-mini', - name: 'GPT-4o mini', - config: { - api: 'openai-responses', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 0.15, - output: 0.6, - cacheRead: 0.08, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.1', - name: 'GPT-5.1', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.25, - output: 10, - cacheRead: 0.13, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.1-codex', - name: 'GPT-5.1 Codex', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.25, - output: 10, - cacheRead: 0.125, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.2', - name: 'GPT-5.2', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.75, - output: 14, - cacheRead: 0.175, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.2-codex', - name: 'GPT-5.2 Codex', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.75, - output: 14, - cacheRead: 0.175, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.3-codex', - name: 'GPT-5.3 Codex', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.75, - output: 14, - cacheRead: 0.175, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.4', - name: 'GPT-5.4', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1050000, - maxTokens: 128000, - cost: { - input: 2.5, - output: 15, - cacheRead: 0.25, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.5', - name: 'GPT-5.5', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1050000, - maxTokens: 128000, - cost: { - input: 5, - output: 30, - cacheRead: 0.5, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'o1', - name: 'o1', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 100000, - cost: { - input: 15, - output: 60, - cacheRead: 7.5, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'o3', - name: 'o3', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 100000, - cost: { - input: 2, - output: 8, - cacheRead: 0.5, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'o3-mini', - name: 'o3-mini', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text'], - contextWindow: 200000, - maxTokens: 100000, - cost: { - input: 1.1, - output: 4.4, - cacheRead: 0.55, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'o3-pro', - name: 'o3-pro', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 100000, - cost: { - input: 20, - output: 80, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'o4-mini', - name: 'o4-mini', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 100000, - cost: { - input: 1.1, - output: 4.4, - cacheRead: 0.28, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'workers-ai/@cf/moonshotai/kimi-k2.5', - name: 'Kimi K2.5', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 256000, - maxTokens: 256000, - cost: { - input: 0.6, - output: 3, - cacheRead: 0.1, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'workers-ai/@cf/moonshotai/kimi-k2.6', - name: 'Kimi K2.6', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 256000, - maxTokens: 256000, - cost: { - input: 0.95, - output: 4, - cacheRead: 0.16, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'workers-ai/@cf/nvidia/nemotron-3-120b-a12b', - name: 'Nemotron 3 Super 120B', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 256000, - maxTokens: 256000, - cost: { - input: 0.5, - output: 1.5, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'workers-ai/@cf/zai-org/glm-4.7-flash', - name: 'GLM-4.7-Flash', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 131072, - cost: { - input: 0.06, - output: 0.4, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - ], - }, - 'cloudflare-workers-ai': { - name: 'cloudflare-workers-ai', - config: { - api: 'openai-completions', - baseUrl: 'https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1', - apiKey: 'CLOUDFLARE_API_KEY', - }, - models: [ - { - modelId: '@cf/google/gemma-4-26b-a4b-it', - name: 'Gemma 4 26B A4B IT', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 256000, - maxTokens: 16384, - cost: { - input: 0.1, - output: 0.3, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: '@cf/ibm-granite/granite-4.0-h-micro', - name: 'Granite 4.0 H Micro', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 131000, - maxTokens: 131000, - cost: { - input: 0.017, - output: 0.112, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: '@cf/meta/llama-3.3-70b-instruct-fp8-fast', - name: 'Llama 3.3 70B Instruct fp8 Fast', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 24000, - maxTokens: 24000, - cost: { - input: 0.293, - output: 2.253, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: '@cf/meta/llama-4-scout-17b-16e-instruct', - name: 'Llama 4 Scout 17B 16E Instruct', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 131000, - maxTokens: 16384, - cost: { - input: 0.27, - output: 0.85, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: '@cf/mistralai/mistral-small-3.1-24b-instruct', - name: 'Mistral Small 3.1 24B Instruct', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 128000, - maxTokens: 128000, - cost: { - input: 0.351, - output: 0.555, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: '@cf/moonshotai/kimi-k2.6', - name: 'Kimi K2.6', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 256000, - cost: { - input: 0.95, - output: 4, - cacheRead: 0.16, - cacheWrite: 0, - }, - }, - }, - { - modelId: '@cf/moonshotai/kimi-k2.7-code', - name: 'Kimi K2.7 Code', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 0.95, - output: 4, - cacheRead: 0.19, - cacheWrite: 0, - }, - }, - }, - { - modelId: '@cf/nvidia/nemotron-3-120b-a12b', - name: 'Nemotron 3 Super 120B', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 256000, - maxTokens: 256000, - cost: { - input: 0.5, - output: 1.5, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: '@cf/openai/gpt-oss-120b', - name: 'GPT OSS 120B', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 0.35, - output: 0.75, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: '@cf/openai/gpt-oss-20b', - name: 'GPT OSS 20B', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 0.2, - output: 0.3, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: '@cf/qwen/qwen3-30b-a3b-fp8', - name: 'Qwen3 30B A3b fp8', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 32768, - maxTokens: 32768, - cost: { - input: 0.0509, - output: 0.335, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: '@cf/zai-org/glm-4.7-flash', - name: 'GLM-4.7-Flash', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 131072, - cost: { - input: 0.0605, - output: 0.4, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - ], - }, - fireworks: { - name: 'fireworks', - config: { - api: 'anthropic-messages', - baseUrl: 'https://api.fireworks.ai/inference', - apiKey: 'FIREWORKS_API_KEY', - }, - models: [ - { - modelId: 'accounts/fireworks/models/deepseek-v4-flash', - name: 'DeepSeek V4 Flash', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 1000000, - maxTokens: 384000, - cost: { - input: 0.14, - output: 0.28, - cacheRead: 0.03, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'accounts/fireworks/models/deepseek-v4-pro', - name: 'DeepSeek V4 Pro', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 1000000, - maxTokens: 384000, - cost: { - input: 1.74, - output: 3.48, - cacheRead: 0.145, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'accounts/fireworks/models/glm-5p1', - name: 'GLM 5.1', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 202800, - maxTokens: 131072, - cost: { - input: 1.4, - output: 4.4, - cacheRead: 0.26, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'accounts/fireworks/models/gpt-oss-120b', - name: 'GPT OSS 120B', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 32768, - cost: { - input: 0.15, - output: 0.6, - cacheRead: 0.015, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'accounts/fireworks/models/gpt-oss-20b', - name: 'GPT OSS 20B', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 32768, - cost: { - input: 0.07, - output: 0.3, - cacheRead: 0.035, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'accounts/fireworks/models/kimi-k2p6', - name: 'Kimi K2.6', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262000, - maxTokens: 262000, - cost: { - input: 0.95, - output: 4, - cacheRead: 0.16, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'accounts/fireworks/models/kimi-k2p7-code', - name: 'Kimi K2.7 Code', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262000, - maxTokens: 262000, - cost: { - input: 0.95, - output: 4, - cacheRead: 0.19, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'accounts/fireworks/models/minimax-m2p7', - name: 'MiniMax-M2.7', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 196608, - maxTokens: 196608, - cost: { - input: 0.3, - output: 1.2, - cacheRead: 0.06, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'accounts/fireworks/models/minimax-m3', - name: 'MiniMax-M3', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 512000, - maxTokens: 512000, - cost: { - input: 0.3, - output: 1.2, - cacheRead: 0.06, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'accounts/fireworks/models/qwen3p7-plus', - name: 'Qwen 3.7 Plus', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 65536, - cost: { - input: 0.4, - output: 1.6, - cacheRead: 0.08, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'accounts/fireworks/routers/glm-5p1-fast', - name: 'GLM 5.1 Fast', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 202800, - maxTokens: 131072, - cost: { - input: 2.8, - output: 8.8, - cacheRead: 0.52, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'accounts/fireworks/routers/kimi-k2p6-fast', - name: 'Kimi K2.6 Fast', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262000, - maxTokens: 262000, - cost: { - input: 2, - output: 8, - cacheRead: 0.3, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'accounts/fireworks/routers/kimi-k2p6-turbo', - name: 'Kimi K2.6 Turbo', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262000, - maxTokens: 262000, - cost: { - input: 2, - output: 8, - cacheRead: 0.3, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'accounts/fireworks/routers/kimi-k2p7-code-fast', - name: 'Kimi K2.7 Code Fast', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262000, - maxTokens: 262000, - cost: { - input: 2, - output: 8, - cacheRead: 0.38, - cacheWrite: 0, - }, - }, - }, - ], - }, - 'github-copilot': { - name: 'github-copilot', - config: { - api: 'openai-completions', - baseUrl: 'https://api.individual.githubcopilot.com', - apiKey: 'COPILOT_GITHUB_TOKEN', - }, - models: [ - { - modelId: 'claude-fable-5', - name: 'Claude Fable 5', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 10, - output: 50, - cacheRead: 1, - cacheWrite: 12.5, - }, - }, - }, - { - modelId: 'claude-haiku-4.5', - name: 'Claude Haiku 4.5 (latest)', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 1, - output: 5, - cacheRead: 0.1, - cacheWrite: 1.25, - }, - }, - }, - { - modelId: 'claude-opus-4.5', - name: 'Claude Opus 4.5 (latest)', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 32000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'claude-opus-4.6', - name: 'Claude Opus 4.6', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 32000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'claude-opus-4.7', - name: 'Claude Opus 4.7', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 32000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'claude-opus-4.8', - name: 'Claude Opus 4.8', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'claude-sonnet-4', - name: 'Claude Sonnet 4 (latest)', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 216000, - maxTokens: 16000, - cost: { - input: 3, - output: 15, - cacheRead: 0.3, - cacheWrite: 3.75, - }, - }, - }, - { - modelId: 'claude-sonnet-4.5', - name: 'Claude Sonnet 4.5 (latest)', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 32000, - cost: { - input: 3, - output: 15, - cacheRead: 0.3, - cacheWrite: 3.75, - }, - }, - }, - { - modelId: 'claude-sonnet-4.6', - name: 'Claude Sonnet 4.6', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 32000, - cost: { - input: 3, - output: 15, - cacheRead: 0.3, - cacheWrite: 3.75, - }, - }, - }, - { - modelId: 'gemini-2.5-pro', - name: 'Gemini 2.5 Pro', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 64000, - cost: { - input: 1.25, - output: 10, - cacheRead: 0.125, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gemini-3-flash-preview', - name: 'Gemini 3 Flash Preview', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 64000, - cost: { - input: 0.5, - output: 3, - cacheRead: 0.05, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gemini-3.1-pro-preview', - name: 'Gemini 3.1 Pro Preview', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 2, - output: 12, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gemini-3.5-flash', - name: 'Gemini 3.5 Flash', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 1.5, - output: 9, - cacheRead: 0.15, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-4.1', - name: 'GPT-4.1', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 2, - output: 8, - cacheRead: 0.5, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5-mini', - name: 'GPT-5 Mini', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 264000, - maxTokens: 64000, - cost: { - input: 0.25, - output: 2, - cacheRead: 0.025, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.2', - name: 'GPT-5.2', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.75, - output: 14, - cacheRead: 0.175, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.2-codex', - name: 'GPT-5.2 Codex', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.75, - output: 14, - cacheRead: 0.175, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.3-codex', - name: 'GPT-5.3 Codex', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.75, - output: 14, - cacheRead: 0.175, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.4', - name: 'GPT-5.4', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 2.5, - output: 15, - cacheRead: 0.25, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.4-mini', - name: 'GPT-5.4 mini', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 0.75, - output: 4.5, - cacheRead: 0.075, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.4-nano', - name: 'GPT-5.4 nano', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 0.2, - output: 1.25, - cacheRead: 0.02, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.5', - name: 'GPT-5.5', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 5, - output: 30, - cacheRead: 0.5, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'raptor-mini', - name: 'Raptor mini', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 0.25, - output: 2, - cacheRead: 0.025, - cacheWrite: 0, - }, - }, - }, - ], - }, - 'google-vertex': { - name: 'google-vertex', - config: { - api: 'google-vertex', - baseUrl: 'https://{location}-aiplatform.googleapis.com', - apiKey: 'GOOGLE_CLOUD_API_KEY', - }, - models: [ - { - modelId: 'gemini-1.5-flash', - name: 'Gemini 1.5 Flash (Vertex)', - config: { - api: 'google-vertex', - reasoning: false, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 8192, - cost: { - input: 0.075, - output: 0.3, - cacheRead: 0.01875, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gemini-1.5-flash-8b', - name: 'Gemini 1.5 Flash-8B (Vertex)', - config: { - api: 'google-vertex', - reasoning: false, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 8192, - cost: { - input: 0.0375, - output: 0.15, - cacheRead: 0.01, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gemini-1.5-pro', - name: 'Gemini 1.5 Pro (Vertex)', - config: { - api: 'google-vertex', - reasoning: false, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 8192, - cost: { - input: 1.25, - output: 5, - cacheRead: 0.3125, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gemini-2.0-flash', - name: 'Gemini 2.0 Flash (Vertex)', - config: { - api: 'google-vertex', - reasoning: false, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 8192, - cost: { - input: 0.15, - output: 0.6, - cacheRead: 0.0375, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gemini-2.0-flash-lite', - name: 'Gemini 2.0 Flash Lite (Vertex)', - config: { - api: 'google-vertex', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 65536, - cost: { - input: 0.075, - output: 0.3, - cacheRead: 0.01875, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gemini-2.5-flash', - name: 'Gemini 2.5 Flash (Vertex)', - config: { - api: 'google-vertex', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 65536, - cost: { - input: 0.3, - output: 2.5, - cacheRead: 0.03, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gemini-2.5-flash-lite', - name: 'Gemini 2.5 Flash Lite (Vertex)', - config: { - api: 'google-vertex', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 65536, - cost: { - input: 0.1, - output: 0.4, - cacheRead: 0.01, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gemini-2.5-flash-lite-preview-09-2025', - name: 'Gemini 2.5 Flash Lite Preview 09-25 (Vertex)', - config: { - api: 'google-vertex', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 65536, - cost: { - input: 0.1, - output: 0.4, - cacheRead: 0.01, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gemini-2.5-pro', - name: 'Gemini 2.5 Pro (Vertex)', - config: { - api: 'google-vertex', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 65536, - cost: { - input: 1.25, - output: 10, - cacheRead: 0.125, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gemini-3-flash-preview', - name: 'Gemini 3 Flash Preview (Vertex)', - config: { - api: 'google-vertex', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 65536, - cost: { - input: 0.5, - output: 3, - cacheRead: 0.05, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gemini-3-pro-preview', - name: 'Gemini 3 Pro Preview (Vertex)', - config: { - api: 'google-vertex', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 64000, - cost: { - input: 2, - output: 12, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gemini-3.1-pro-preview', - name: 'Gemini 3.1 Pro Preview (Vertex)', - config: { - api: 'google-vertex', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 65536, - cost: { - input: 2, - output: 12, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gemini-3.1-pro-preview-customtools', - name: 'Gemini 3.1 Pro Preview Custom Tools (Vertex)', - config: { - api: 'google-vertex', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 65536, - cost: { - input: 2, - output: 12, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - ], - }, - huggingface: { - name: 'huggingface', - config: { - api: 'openai-completions', - baseUrl: 'https://router.huggingface.co/v1', - apiKey: 'HF_TOKEN', - }, - models: [ - { - modelId: 'MiniMaxAI/MiniMax-M2.1', - name: 'MiniMax-M2.1', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 204800, - maxTokens: 131072, - cost: { - input: 0.3, - output: 1.2, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'MiniMaxAI/MiniMax-M2.5', - name: 'MiniMax-M2.5', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 204800, - maxTokens: 131072, - cost: { - input: 0.3, - output: 1.2, - cacheRead: 0.03, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'MiniMaxAI/MiniMax-M2.7', - name: 'MiniMax-M2.7', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 204800, - maxTokens: 131072, - cost: { - input: 0.3, - output: 1.2, - cacheRead: 0.06, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'Qwen/Qwen3-235B-A22B-Thinking-2507', - name: 'Qwen3-235B-A22B-Thinking-2507', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 262144, - maxTokens: 131072, - cost: { - input: 0.3, - output: 3, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'Qwen/Qwen3-Coder-480B-A35B-Instruct', - name: 'Qwen3-Coder-480B-A35B-Instruct', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 262144, - maxTokens: 66536, - cost: { - input: 2, - output: 2, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'Qwen/Qwen3-Coder-Next', - name: 'Qwen3-Coder-Next', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 262144, - maxTokens: 65536, - cost: { - input: 0.2, - output: 1.5, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'Qwen/Qwen3-Next-80B-A3B-Instruct', - name: 'Qwen3-Next-80B-A3B-Instruct', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 262144, - maxTokens: 66536, - cost: { - input: 0.25, - output: 1, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'Qwen/Qwen3-Next-80B-A3B-Thinking', - name: 'Qwen3-Next-80B-A3B-Thinking', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 262144, - maxTokens: 131072, - cost: { - input: 0.3, - output: 2, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'Qwen/Qwen3.5-397B-A17B', - name: 'Qwen3.5-397B-A17B', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 32768, - cost: { - input: 0.6, - output: 3.6, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'XiaomiMiMo/MiMo-V2-Flash', - name: 'MiMo-V2-Flash', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 262144, - maxTokens: 4096, - cost: { - input: 0.1, - output: 0.3, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'deepseek-ai/DeepSeek-R1-0528', - name: 'DeepSeek-R1-0528', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 163840, - maxTokens: 163840, - cost: { - input: 3, - output: 5, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'deepseek-ai/DeepSeek-V3.2', - name: 'DeepSeek-V3.2', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 163840, - maxTokens: 65536, - cost: { - input: 0.28, - output: 0.4, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'deepseek-ai/DeepSeek-V4-Pro', - name: 'DeepSeek V4 Pro', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 1048576, - maxTokens: 393216, - cost: { - input: 0.435, - output: 0.87, - cacheRead: 0.003625, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'moonshotai/Kimi-K2-Instruct', - name: 'Kimi-K2-Instruct', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 131072, - maxTokens: 16384, - cost: { - input: 1, - output: 3, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'moonshotai/Kimi-K2-Instruct-0905', - name: 'Kimi-K2-Instruct-0905', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 262144, - maxTokens: 16384, - cost: { - input: 1, - output: 3, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'moonshotai/Kimi-K2-Thinking', - name: 'Kimi-K2-Thinking', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 0.6, - output: 2.5, - cacheRead: 0.15, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'moonshotai/Kimi-K2.5', - name: 'Kimi-K2.5', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 0.6, - output: 3, - cacheRead: 0.1, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'moonshotai/Kimi-K2.6', - name: 'Kimi-K2.6', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 0.95, - output: 4, - cacheRead: 0.16, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'zai-org/GLM-4.7', - name: 'GLM-4.7', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 204800, - maxTokens: 131072, - cost: { - input: 0.6, - output: 2.2, - cacheRead: 0.11, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'zai-org/GLM-4.7-Flash', - name: 'GLM-4.7-Flash', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 200000, - maxTokens: 128000, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'zai-org/GLM-5', - name: 'GLM-5', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 202752, - maxTokens: 131072, - cost: { - input: 1, - output: 3.2, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'zai-org/GLM-5.1', - name: 'GLM-5.1', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 202752, - maxTokens: 131072, - cost: { - input: 1, - output: 3.2, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - ], - }, - 'kimi-coding': { - name: 'kimi-coding', - config: { - api: 'anthropic-messages', - baseUrl: 'https://api.kimi.com/coding', - apiKey: 'KIMI_API_KEY', - }, - models: [ - { - modelId: 'k2p7', - name: 'Kimi K2.7 Code', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 32768, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'kimi-for-coding', - name: 'Kimi For Coding', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 32768, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'kimi-k2-thinking', - name: 'Kimi K2 Thinking', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 262144, - maxTokens: 32768, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - ], - }, - minimax: { - name: 'minimax', - config: { - api: 'anthropic-messages', - baseUrl: 'https://api.minimax.io/anthropic', - apiKey: 'MINIMAX_API_KEY', - }, - models: [ - { - modelId: 'MiniMax-M2.7', - name: 'MiniMax-M2.7', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 204800, - maxTokens: 131072, - cost: { - input: 0.3, - output: 1.2, - cacheRead: 0.06, - cacheWrite: 0.375, - }, - }, - }, - { - modelId: 'MiniMax-M2.7-highspeed', - name: 'MiniMax-M2.7-highspeed', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 204800, - maxTokens: 131072, - cost: { - input: 0.6, - output: 2.4, - cacheRead: 0.06, - cacheWrite: 0.375, - }, - }, - }, - { - modelId: 'MiniMax-M3', - name: 'MiniMax-M3', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 512000, - maxTokens: 128000, - cost: { - input: 0.6, - output: 2.4, - cacheRead: 0.12, - cacheWrite: 0, - }, - }, - }, - ], - }, - 'minimax-cn': { - name: 'minimax-cn', - config: { - api: 'anthropic-messages', - baseUrl: 'https://api.minimaxi.com/anthropic', - apiKey: 'MINIMAX_CN_API_KEY', - }, - models: [ - { - modelId: 'MiniMax-M2.7', - name: 'MiniMax-M2.7', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 204800, - maxTokens: 131072, - cost: { - input: 0.3, - output: 1.2, - cacheRead: 0.06, - cacheWrite: 0.375, - }, - }, - }, - { - modelId: 'MiniMax-M2.7-highspeed', - name: 'MiniMax-M2.7-highspeed', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 204800, - maxTokens: 131072, - cost: { - input: 0.6, - output: 2.4, - cacheRead: 0.06, - cacheWrite: 0.375, - }, - }, - }, - { - modelId: 'MiniMax-M3', - name: 'MiniMax-M3', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 512000, - maxTokens: 128000, - cost: { - input: 0.6, - output: 2.4, - cacheRead: 0.12, - cacheWrite: 0, - }, - }, - }, - ], - }, - moonshotai: { - name: 'moonshotai', - config: { - api: 'openai-completions', - baseUrl: 'https://api.moonshot.ai/v1', - apiKey: 'MOONSHOT_API_KEY', - }, - models: [ - { - modelId: 'kimi-k2-0711-preview', - name: 'Kimi K2 0711', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 131072, - maxTokens: 16384, - cost: { - input: 0.6, - output: 2.5, - cacheRead: 0.15, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'kimi-k2-0905-preview', - name: 'Kimi K2 0905', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 0.6, - output: 2.5, - cacheRead: 0.15, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'kimi-k2-thinking', - name: 'Kimi K2 Thinking', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 0.6, - output: 2.5, - cacheRead: 0.15, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'kimi-k2-thinking-turbo', - name: 'Kimi K2 Thinking Turbo', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 1.15, - output: 8, - cacheRead: 0.15, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'kimi-k2-turbo-preview', - name: 'Kimi K2 Turbo', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 2.4, - output: 10, - cacheRead: 0.6, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'kimi-k2.5', - name: 'Kimi K2.5', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 0.6, - output: 3, - cacheRead: 0.1, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'kimi-k2.6', - name: 'Kimi K2.6', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 0.95, - output: 4, - cacheRead: 0.16, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'kimi-k2.7-code', - name: 'Kimi K2.7 Code', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 0.95, - output: 4, - cacheRead: 0.19, - cacheWrite: 0, - }, - }, - }, - ], - }, - 'moonshotai-cn': { - name: 'moonshotai-cn', - config: { - api: 'openai-completions', - baseUrl: 'https://api.moonshot.cn/v1', - apiKey: 'MOONSHOT_API_KEY', - }, - models: [ - { - modelId: 'kimi-k2-0711-preview', - name: 'Kimi K2 0711', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 131072, - maxTokens: 16384, - cost: { - input: 0.6, - output: 2.5, - cacheRead: 0.15, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'kimi-k2-0905-preview', - name: 'Kimi K2 0905', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 0.6, - output: 2.5, - cacheRead: 0.15, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'kimi-k2-thinking', - name: 'Kimi K2 Thinking', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 0.6, - output: 2.5, - cacheRead: 0.15, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'kimi-k2-thinking-turbo', - name: 'Kimi K2 Thinking Turbo', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 1.15, - output: 8, - cacheRead: 0.15, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'kimi-k2-turbo-preview', - name: 'Kimi K2 Turbo', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 2.4, - output: 10, - cacheRead: 0.6, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'kimi-k2.5', - name: 'Kimi K2.5', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 0.6, - output: 3, - cacheRead: 0.1, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'kimi-k2.6', - name: 'Kimi K2.6', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 0.95, - output: 4, - cacheRead: 0.16, - cacheWrite: 0, - }, - }, - }, - ], - }, - nvidia: { - name: 'nvidia', - config: { - api: 'openai-completions', - baseUrl: 'https://integrate.api.nvidia.com/v1', - apiKey: '', - }, - models: [ - { - modelId: 'meta/llama-3.1-70b-instruct', - name: 'Llama 3.1 70b Instruct', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 128000, - maxTokens: 4096, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'meta/llama-3.1-8b-instruct', - name: 'Llama 3.1 8B Instruct', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 16000, - maxTokens: 4096, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'meta/llama-3.2-11b-vision-instruct', - name: 'Llama 3.2 11b Vision Instruct', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 4096, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'meta/llama-3.2-90b-vision-instruct', - name: 'Llama-3.2-90B-Vision-Instruct', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 8192, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'meta/llama-3.3-70b-instruct', - name: 'Llama 3.3 70b Instruct', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 128000, - maxTokens: 4096, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistralai/mistral-large-3-675b-instruct-2512', - name: 'Mistral Large 3 675B Instruct 2512', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistralai/mistral-small-4-119b-2603', - name: 'mistral-small-4-119b-2603', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 8192, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'moonshotai/kimi-k2.6', - name: 'Kimi K2.6', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'nvidia/nemotron-3-nano-30b-a3b', - name: 'nemotron-3-nano-30b-a3b', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 131072, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'nvidia/nemotron-3-nano-omni-30b-a3b-reasoning', - name: 'Nemotron 3 Nano Omni', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 256000, - maxTokens: 65536, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'nvidia/nemotron-3-super-120b-a12b', - name: 'Nemotron 3 Super', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 0.2, - output: 0.8, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'nvidia/nemotron-3-ultra-550b-a55b', - name: 'Nemotron 3 Ultra 550B A55B', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 1000000, - maxTokens: 65536, - cost: { - input: 0.5, - output: 2.5, - cacheRead: 0.15, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'nvidia/nvidia-nemotron-nano-9b-v2', - name: 'nvidia-nemotron-nano-9b-v2', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 131072, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-oss-120b', - name: 'GPT-OSS-120B', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 128000, - maxTokens: 8192, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-oss-20b', - name: 'GPT OSS 20B', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 32768, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen/qwen3.5-122b-a10b', - name: 'Qwen3.5 122B-A10B', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 65536, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'stepfun-ai/step-3.5-flash', - name: 'Step 3.5 Flash', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 256000, - maxTokens: 16384, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'stepfun-ai/step-3.7-flash', - name: 'Step 3.7 Flash', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 256000, - maxTokens: 16384, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'z-ai/glm-5.1', - name: 'GLM-5.1', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 131072, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - ], - }, - 'openai-codex': { - name: 'openai-codex', - config: { - api: 'openai-codex-responses', - baseUrl: 'https://chatgpt.com/backend-api', - apiKey: '', - }, - models: [ - { - modelId: 'gpt-5.3-codex-spark', - name: 'GPT-5.3 Codex Spark', - config: { - api: 'openai-codex-responses', - reasoning: true, - input: ['text'], - contextWindow: 128000, - maxTokens: 128000, - cost: { - input: 1.75, - output: 14, - cacheRead: 0.175, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.4', - name: 'GPT-5.4', - config: { - api: 'openai-codex-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 272000, - maxTokens: 128000, - cost: { - input: 2.5, - output: 15, - cacheRead: 0.25, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.4-mini', - name: 'GPT-5.4 mini', - config: { - api: 'openai-codex-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 272000, - maxTokens: 128000, - cost: { - input: 0.75, - output: 4.5, - cacheRead: 0.075, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.5', - name: 'GPT-5.5', - config: { - api: 'openai-codex-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 272000, - maxTokens: 128000, - cost: { - input: 5, - output: 30, - cacheRead: 0.5, - cacheWrite: 0, - }, - }, - }, - ], - }, - opencode: { - name: 'opencode', - config: { - api: 'openai-completions', - baseUrl: 'https://opencode.ai/zen/v1', - apiKey: 'OPENCODE_API_KEY', - }, - models: [ - { - modelId: 'big-pickle', - name: 'Big Pickle', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 200000, - maxTokens: 32000, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'claude-haiku-4-5', - name: 'Claude Haiku 4.5', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 1, - output: 5, - cacheRead: 0.1, - cacheWrite: 1.25, - }, - }, - }, - { - modelId: 'claude-opus-4-1', - name: 'Claude Opus 4.1', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 32000, - cost: { - input: 15, - output: 75, - cacheRead: 1.5, - cacheWrite: 18.75, - }, - }, - }, - { - modelId: 'claude-opus-4-5', - name: 'Claude Opus 4.5', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'claude-opus-4-6', - name: 'Claude Opus 4.6', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'claude-opus-4-7', - name: 'Claude Opus 4.7', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'claude-opus-4-8', - name: 'Claude Opus 4.8', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'claude-sonnet-4', - name: 'Claude Sonnet 4', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 3, - output: 15, - cacheRead: 0.3, - cacheWrite: 3.75, - }, - }, - }, - { - modelId: 'claude-sonnet-4-5', - name: 'Claude Sonnet 4.5', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 3, - output: 15, - cacheRead: 0.3, - cacheWrite: 3.75, - }, - }, - }, - { - modelId: 'claude-sonnet-4-6', - name: 'Claude Sonnet 4.6', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 64000, - cost: { - input: 3, - output: 15, - cacheRead: 0.3, - cacheWrite: 3.75, - }, - }, - }, - { - modelId: 'deepseek-v4-flash', - name: 'DeepSeek V4 Flash', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 1000000, - maxTokens: 384000, - cost: { - input: 0.14, - output: 0.28, - cacheRead: 0.028, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'deepseek-v4-flash-free', - name: 'DeepSeek V4 Flash Free', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 200000, - maxTokens: 128000, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'deepseek-v4-pro', - name: 'DeepSeek V4 Pro', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 1000000, - maxTokens: 384000, - cost: { - input: 1.74, - output: 3.84, - cacheRead: 0.145, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gemini-3-flash', - name: 'Gemini 3 Flash', - config: { - api: 'google-generative-ai', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 65536, - cost: { - input: 0.5, - output: 3, - cacheRead: 0.05, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gemini-3.1-pro', - name: 'Gemini 3.1 Pro Preview', - config: { - api: 'google-generative-ai', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 65536, - cost: { - input: 2, - output: 12, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gemini-3.5-flash', - name: 'Gemini 3.5 Flash', - config: { - api: 'google-generative-ai', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 65536, - cost: { - input: 1.5, - output: 9, - cacheRead: 0.15, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'glm-5', - name: 'GLM-5', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 204800, - maxTokens: 131072, - cost: { - input: 1, - output: 3.2, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'glm-5.1', - name: 'GLM-5.1', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 204800, - maxTokens: 131072, - cost: { - input: 1.4, - output: 4.4, - cacheRead: 0.26, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5', - name: 'GPT-5', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.07, - output: 8.5, - cacheRead: 0.107, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5-codex', - name: 'GPT-5 Codex', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.07, - output: 8.5, - cacheRead: 0.107, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5-nano', - name: 'GPT-5 Nano', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 0.05, - output: 0.4, - cacheRead: 0.005, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.1', - name: 'GPT-5.1', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.07, - output: 8.5, - cacheRead: 0.107, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.1-codex', - name: 'GPT-5.1 Codex', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.07, - output: 8.5, - cacheRead: 0.107, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.1-codex-max', - name: 'GPT-5.1 Codex Max', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.25, - output: 10, - cacheRead: 0.125, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.1-codex-mini', - name: 'GPT-5.1 Codex Mini', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 0.25, - output: 2, - cacheRead: 0.025, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.2', - name: 'GPT-5.2', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.75, - output: 14, - cacheRead: 0.175, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.2-codex', - name: 'GPT-5.2 Codex', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.75, - output: 14, - cacheRead: 0.175, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.3-codex', - name: 'GPT-5.3 Codex', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.75, - output: 14, - cacheRead: 0.175, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.4', - name: 'GPT-5.4', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 272000, - maxTokens: 128000, - cost: { - input: 2.5, - output: 15, - cacheRead: 0.25, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.4-mini', - name: 'GPT-5.4 Mini', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 0.75, - output: 4.5, - cacheRead: 0.075, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.4-nano', - name: 'GPT-5.4 Nano', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 0.2, - output: 1.25, - cacheRead: 0.02, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.4-pro', - name: 'GPT-5.4 Pro', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1050000, - maxTokens: 128000, - cost: { - input: 30, - output: 180, - cacheRead: 30, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.5', - name: 'GPT-5.5', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1050000, - maxTokens: 128000, - cost: { - input: 5, - output: 30, - cacheRead: 0.5, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'gpt-5.5-pro', - name: 'GPT-5.5 Pro', - config: { - api: 'openai-responses', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1050000, - maxTokens: 128000, - cost: { - input: 30, - output: 180, - cacheRead: 30, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'grok-build-0.1', - name: 'Grok Build 0.1', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 256000, - maxTokens: 256000, - cost: { - input: 1, - output: 2, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'kimi-k2.5', - name: 'Kimi K2.5', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 65536, - cost: { - input: 0.6, - output: 3, - cacheRead: 0.08, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'kimi-k2.6', - name: 'Kimi K2.6', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 65536, - cost: { - input: 0.95, - output: 4, - cacheRead: 0.16, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mimo-v2.5-free', - name: 'MiMo V2.5 Free', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 32000, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'minimax-m2.5', - name: 'MiniMax M2.5', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 204800, - maxTokens: 131072, - cost: { - input: 0.3, - output: 1.2, - cacheRead: 0.06, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'minimax-m2.7', - name: 'MiniMax M2.7', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 204800, - maxTokens: 131072, - cost: { - input: 0.3, - output: 1.2, - cacheRead: 0.06, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'nemotron-3-ultra-free', - name: 'Nemotron 3 Ultra Free', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'north-mini-code-free', - name: 'North Mini Code Free', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 256000, - maxTokens: 64000, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen3.5-plus', - name: 'Qwen3.5 Plus', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 65536, - cost: { - input: 0.2, - output: 1.2, - cacheRead: 0.02, - cacheWrite: 0.25, - }, - }, - }, - { - modelId: 'qwen3.6-plus', - name: 'Qwen3.6 Plus', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 65536, - cost: { - input: 0.5, - output: 3, - cacheRead: 0.05, - cacheWrite: 0.625, - }, - }, - }, - ], - }, - 'opencode-go': { - name: 'opencode-go', - config: { - api: 'openai-completions', - baseUrl: 'https://opencode.ai/zen/go/v1', - apiKey: 'OPENCODE_API_KEY', - }, - models: [ - { - modelId: 'deepseek-v4-flash', - name: 'DeepSeek V4 Flash', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 1000000, - maxTokens: 384000, - cost: { - input: 0.14, - output: 0.28, - cacheRead: 0.0028, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'deepseek-v4-pro', - name: 'DeepSeek V4 Pro', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 1000000, - maxTokens: 384000, - cost: { - input: 1.74, - output: 3.48, - cacheRead: 0.0145, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'glm-5', - name: 'GLM-5', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 202752, - maxTokens: 32768, - cost: { - input: 1, - output: 3.2, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'glm-5.1', - name: 'GLM-5.1', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 202752, - maxTokens: 32768, - cost: { - input: 1.4, - output: 4.4, - cacheRead: 0.26, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'kimi-k2.6', - name: 'Kimi K2.6', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 65536, - cost: { - input: 0.95, - output: 4, - cacheRead: 0.16, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'kimi-k2.7-code', - name: 'Kimi K2.7 Code', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 0.95, - output: 4, - cacheRead: 0.19, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mimo-v2.5', - name: 'MiMo V2.5', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 0.14, - output: 0.28, - cacheRead: 0.0028, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mimo-v2.5-pro', - name: 'MiMo V2.5 Pro', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 1048576, - maxTokens: 128000, - cost: { - input: 1.74, - output: 3.48, - cacheRead: 0.0145, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'minimax-m2.7', - name: 'MiniMax M2.7', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 204800, - maxTokens: 131072, - cost: { - input: 0.3, - output: 1.2, - cacheRead: 0.06, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'minimax-m3', - name: 'MiniMax M3 (3x usage)', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 512000, - maxTokens: 131072, - cost: { - input: 0.1, - output: 0.4, - cacheRead: 0.02, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'qwen3.6-plus', - name: 'Qwen3.6 Plus', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 65536, - cost: { - input: 0.5, - output: 3, - cacheRead: 0.05, - cacheWrite: 0.625, - }, - }, - }, - { - modelId: 'qwen3.7-max', - name: 'Qwen3.7 Max', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 1000000, - maxTokens: 65536, - cost: { - input: 2.5, - output: 7.5, - cacheRead: 0.5, - cacheWrite: 3.125, - }, - }, - }, - { - modelId: 'qwen3.7-plus', - name: 'Qwen3.7 Plus', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 65536, - cost: { - input: 0.4, - output: 1.6, - cacheRead: 0.04, - cacheWrite: 0.5, - }, - }, - }, - ], - }, - together: { - name: 'together', - config: { - api: 'openai-completions', - baseUrl: 'https://api.together.ai/v1', - apiKey: 'TOGETHER_API_KEY', - }, - models: [ - { - modelId: 'MiniMaxAI/MiniMax-M2.7', - name: 'MiniMax-M2.7', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 202752, - maxTokens: 131072, - cost: { - input: 0.3, - output: 1.2, - cacheRead: 0.06, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'MiniMaxAI/MiniMax-M3', - name: 'MiniMax-M3', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 524288, - maxTokens: 250000, - cost: { - input: 0.3, - output: 1.2, - cacheRead: 0.06, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'Qwen/Qwen2.5-7B-Instruct-Turbo', - name: 'Qwen 2.5 7B Instruct Turbo', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 32768, - maxTokens: 32768, - cost: { - input: 0.3, - output: 0.3, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'Qwen/Qwen3-235B-A22B-Instruct-2507-tput', - name: 'Qwen3 235B A22B Instruct 2507 FP8', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 262144, - maxTokens: 262144, - cost: { - input: 0.2, - output: 0.6, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'Qwen/Qwen3.5-397B-A17B', - name: 'Qwen3.5 397B A17B', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 130000, - cost: { - input: 0.6, - output: 3.6, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'Qwen/Qwen3.5-9B', - name: 'Qwen3.5 9B', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 65536, - cost: { - input: 0.17, - output: 0.25, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'Qwen/Qwen3.6-Plus', - name: 'Qwen3.6 Plus', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 1000000, - maxTokens: 500000, - cost: { - input: 0.5, - output: 3, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'Qwen/Qwen3.7-Max', - name: 'Qwen3.7 Max', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 1000000, - maxTokens: 500000, - cost: { - input: 2.5, - output: 7.5, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'deepseek-ai/DeepSeek-V4-Pro', - name: 'DeepSeek V4 Pro', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 512000, - maxTokens: 384000, - cost: { - input: 1.74, - output: 3.48, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'essentialai/Rnj-1-Instruct', - name: 'Rnj-1 Instruct', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 32768, - maxTokens: 32768, - cost: { - input: 0.15, - output: 0.15, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'google/gemma-4-31B-it', - name: 'Gemma 4 31B Instruct', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 131072, - cost: { - input: 0.39, - output: 0.97, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'meta-llama/Llama-3.3-70B-Instruct-Turbo', - name: 'Llama 3.3 70B', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 131072, - maxTokens: 131072, - cost: { - input: 0.88, - output: 0.88, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'moonshotai/Kimi-K2.6', - name: 'Kimi K2.6', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 131000, - cost: { - input: 1.2, - output: 4.5, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'moonshotai/Kimi-K2.7-Code', - name: 'Kimi K2.7 Code', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 262144, - maxTokens: 131072, - cost: { - input: 0.95, - output: 4, - cacheRead: 0.19, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'nvidia/nemotron-3-ultra-550b-a55b', - name: 'Nemotron 3 Ultra 550B A55B', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 512300, - maxTokens: 512300, - cost: { - input: 0.6, - output: 3.6, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-oss-120b', - name: 'GPT OSS 120B', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 131072, - cost: { - input: 0.15, - output: 0.6, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-oss-20b', - name: 'GPT OSS 20B', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 131072, - cost: { - input: 0.05, - output: 0.2, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'zai-org/GLM-5', - name: 'GLM-5', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 202752, - maxTokens: 131072, - cost: { - input: 1, - output: 3.2, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'zai-org/GLM-5.1', - name: 'GLM-5.1', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 202752, - maxTokens: 131072, - cost: { - input: 1.4, - output: 4.4, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - ], - }, - 'vercel-ai-gateway': { - name: 'vercel-ai-gateway', - config: { - api: 'anthropic-messages', - baseUrl: 'https://ai-gateway.vercel.sh', - apiKey: 'AI_GATEWAY_API_KEY', - }, - models: [ - { - modelId: 'alibaba/qwen-3-14b', - name: 'Qwen3-14B', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 40960, - maxTokens: 16384, - cost: { - input: 0.12, - output: 0.24, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'alibaba/qwen-3-235b', - name: 'Qwen3 235B A22B', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 262144, - maxTokens: 16384, - cost: { - input: 0.22, - output: 0.88, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'alibaba/qwen-3-30b', - name: 'Qwen3-30B-A3B', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 40960, - maxTokens: 16384, - cost: { - input: 0.12, - output: 0.5, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'alibaba/qwen-3-32b', - name: 'Qwen 3 32B', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 128000, - maxTokens: 8192, - cost: { - input: 0.16, - output: 0.64, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'alibaba/qwen-3.6-max-preview', - name: 'Qwen 3.6 Max Preview', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 240000, - maxTokens: 64000, - cost: { - input: 1.3, - output: 7.8, - cacheRead: 0.26, - cacheWrite: 1.625, - }, - }, - }, - { - modelId: 'alibaba/qwen3-235b-a22b-thinking', - name: 'Qwen3 VL 235B A22B Thinking', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 131072, - maxTokens: 32768, - cost: { - input: 0.4, - output: 4, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'alibaba/qwen3-coder', - name: 'Qwen3 Coder 480B A35B Instruct', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 262144, - maxTokens: 65536, - cost: { - input: 1.5, - output: 7.5, - cacheRead: 0.3, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'alibaba/qwen3-coder-30b-a3b', - name: 'Qwen 3 Coder 30B A3B Instruct', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 262144, - maxTokens: 8192, - cost: { - input: 0.15, - output: 0.6, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'alibaba/qwen3-coder-next', - name: 'Qwen3 Coder Next', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 256000, - maxTokens: 256000, - cost: { - input: 0.5, - output: 1.2, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'alibaba/qwen3-coder-plus', - name: 'Qwen3 Coder Plus', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text'], - contextWindow: 1000000, - maxTokens: 65536, - cost: { - input: 1, - output: 5, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'alibaba/qwen3-max', - name: 'Qwen3 Max', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text'], - contextWindow: 262144, - maxTokens: 32768, - cost: { - input: 1.2, - output: 6, - cacheRead: 0.24, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'alibaba/qwen3-max-preview', - name: 'Qwen3 Max Preview', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text'], - contextWindow: 262144, - maxTokens: 32768, - cost: { - input: 1.2, - output: 6, - cacheRead: 0.24, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'alibaba/qwen3-max-thinking', - name: 'Qwen 3 Max Thinking', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 256000, - maxTokens: 65536, - cost: { - input: 1.2, - output: 6, - cacheRead: 0.24, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'alibaba/qwen3-next-80b-a3b-instruct', - name: 'Qwen3 Next 80B A3B Instruct', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text'], - contextWindow: 131072, - maxTokens: 32768, - cost: { - input: 0.15, - output: 1.2, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'alibaba/qwen3-next-80b-a3b-thinking', - name: 'Qwen3 Next 80B A3B Thinking', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 32768, - cost: { - input: 0.15, - output: 1.2, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'alibaba/qwen3-vl-thinking', - name: 'Qwen3 VL 235B A22B Thinking', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 131072, - maxTokens: 32768, - cost: { - input: 0.4, - output: 4, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'alibaba/qwen3.5-flash', - name: 'Qwen 3.5 Flash', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 64000, - cost: { - input: 0.1, - output: 0.4, - cacheRead: 0.001, - cacheWrite: 0.125, - }, - }, - }, - { - modelId: 'alibaba/qwen3.5-plus', - name: 'Qwen 3.5 Plus', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 64000, - cost: { - input: 0.4, - output: 2.4, - cacheRead: 0.04, - cacheWrite: 0.5, - }, - }, - }, - { - modelId: 'alibaba/qwen3.6-27b', - name: 'Qwen 3.6 27B', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 256000, - maxTokens: 256000, - cost: { - input: 0.6, - output: 3.6, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'alibaba/qwen3.6-plus', - name: 'Qwen 3.6 Plus', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 64000, - cost: { - input: 0.5, - output: 3, - cacheRead: 0.1, - cacheWrite: 0.625, - }, - }, - }, - { - modelId: 'alibaba/qwen3.7-max', - name: 'Qwen 3.7 Max', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 991000, - maxTokens: 64000, - cost: { - input: 1.25, - output: 3.75, - cacheRead: 0.25, - cacheWrite: 1.5625, - }, - }, - }, - { - modelId: 'alibaba/qwen3.7-plus', - name: 'Qwen 3.7 Plus', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 64000, - cost: { - input: 0.4, - output: 1.6, - cacheRead: 0.08, - cacheWrite: 0.5, - }, - }, - }, - { - modelId: 'anthropic/claude-3-haiku', - name: 'Claude 3 Haiku', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 4096, - cost: { - input: 0.25, - output: 1.25, - cacheRead: 0.03, - cacheWrite: 0.3, - }, - }, - }, - { - modelId: 'anthropic/claude-3.5-haiku', - name: 'Claude 3.5 Haiku', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 8192, - cost: { - input: 0.8, - output: 4, - cacheRead: 0.08, - cacheWrite: 1, - }, - }, - }, - { - modelId: 'anthropic/claude-haiku-4.5', - name: 'Claude Haiku 4.5', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 1, - output: 5, - cacheRead: 0.1, - cacheWrite: 1.25, - }, - }, - }, - { - modelId: 'anthropic/claude-opus-4', - name: 'Claude Opus 4', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 32000, - cost: { - input: 15, - output: 75, - cacheRead: 1.5, - cacheWrite: 18.75, - }, - }, - }, - { - modelId: 'anthropic/claude-opus-4.1', - name: 'Claude Opus 4.1', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 32000, - cost: { - input: 15, - output: 75, - cacheRead: 1.5, - cacheWrite: 18.75, - }, - }, - }, - { - modelId: 'anthropic/claude-opus-4.5', - name: 'Claude Opus 4.5', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 64000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'anthropic/claude-opus-4.6', - name: 'Claude Opus 4.6', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'anthropic/claude-opus-4.7', - name: 'Claude Opus 4.7', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'anthropic/claude-opus-4.8', - name: 'Claude Opus 4.8', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, - }, - }, - }, - { - modelId: 'anthropic/claude-sonnet-4', - name: 'Claude Sonnet 4', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 64000, - cost: { - input: 3, - output: 15, - cacheRead: 0.3, - cacheWrite: 3.75, - }, - }, - }, - { - modelId: 'anthropic/claude-sonnet-4.5', - name: 'Claude Sonnet 4.5', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 64000, - cost: { - input: 3, - output: 15, - cacheRead: 0.3, - cacheWrite: 3.75, - }, - }, - }, - { - modelId: 'anthropic/claude-sonnet-4.6', - name: 'Claude Sonnet 4.6', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 3, - output: 15, - cacheRead: 0.3, - cacheWrite: 3.75, - }, - }, - }, - { - modelId: 'arcee-ai/trinity-large-preview', - name: 'Trinity Large Preview', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text'], - contextWindow: 131000, - maxTokens: 131000, - cost: { - input: 0.25, - output: 1, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'arcee-ai/trinity-large-thinking', - name: 'Trinity Large Thinking', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 262100, - maxTokens: 80000, - cost: { - input: 0.25, - output: 0.9, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'bytedance/seed-1.6', - name: 'Seed 1.6', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 256000, - maxTokens: 32000, - cost: { - input: 0.25, - output: 2, - cacheRead: 0.05, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'cohere/command-a', - name: 'Command A', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text'], - contextWindow: 256000, - maxTokens: 8000, - cost: { - input: 2.5, - output: 10, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'deepseek/deepseek-r1', - name: 'DeepSeek-R1', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 128000, - maxTokens: 8192, - cost: { - input: 1.35, - output: 5.4, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'deepseek/deepseek-v3', - name: 'DeepSeek V3 0324', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text'], - contextWindow: 163840, - maxTokens: 163840, - cost: { - input: 0.27, - output: 1.12, - cacheRead: 0.135, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'deepseek/deepseek-v3.1', - name: 'DeepSeek V3.1', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 163840, - maxTokens: 8192, - cost: { - input: 0.56, - output: 1.68, - cacheRead: 0.28, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'deepseek/deepseek-v3.1-terminus', - name: 'DeepSeek V3.1 Terminus', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 65536, - cost: { - input: 0.27, - output: 1, - cacheRead: 0.135, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'deepseek/deepseek-v3.2', - name: 'DeepSeek V3.2', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 8000, - cost: { - input: 0.28, - output: 0.42, - cacheRead: 0.028, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'deepseek/deepseek-v3.2-thinking', - name: 'DeepSeek V3.2 Thinking', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 8000, - cost: { - input: 0.62, - output: 1.85, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'deepseek/deepseek-v4-flash', - name: 'DeepSeek V4 Flash', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 384000, - cost: { - input: 0.14, - output: 0.28, - cacheRead: 0.0028, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'deepseek/deepseek-v4-pro', - name: 'DeepSeek V4 Pro', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 1000000, - maxTokens: 384000, - cost: { - input: 0.435, - output: 0.87, - cacheRead: 0.0036, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'google/gemini-2.5-flash', - name: 'Gemini 2.5 Flash', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 65536, - cost: { - input: 0.3, - output: 2.5, - cacheRead: 0.03, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'google/gemini-2.5-flash-lite', - name: 'Gemini 2.5 Flash Lite', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 65536, - cost: { - input: 0.1, - output: 0.4, - cacheRead: 0.01, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'google/gemini-2.5-pro', - name: 'Gemini 2.5 Pro', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 65536, - cost: { - input: 1.25, - output: 10, - cacheRead: 0.125, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'google/gemini-3-flash', - name: 'Gemini 3 Flash', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 65000, - cost: { - input: 0.5, - output: 3, - cacheRead: 0.05, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'google/gemini-3-pro-preview', - name: 'Gemini 3 Pro Preview', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 64000, - cost: { - input: 2, - output: 12, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'google/gemini-3.1-flash-lite', - name: 'Gemini 3.1 Flash Lite', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 65000, - cost: { - input: 0.25, - output: 1.5, - cacheRead: 0.03, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'google/gemini-3.1-flash-lite-preview', - name: 'Gemini 3.1 Flash Lite Preview', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 65000, - cost: { - input: 0.25, - output: 1.5, - cacheRead: 0.03, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'google/gemini-3.1-pro-preview', - name: 'Gemini 3.1 Pro Preview', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 64000, - cost: { - input: 2, - output: 12, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'google/gemini-3.5-flash', - name: 'Gemini 3.5 Flash', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 64000, - cost: { - input: 1.5, - output: 9, - cacheRead: 0.15, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'google/gemma-4-26b-a4b-it', - name: 'Gemma 4 26B A4B IT', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 131072, - cost: { - input: 0.15, - output: 0.6, - cacheRead: 0.015, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'google/gemma-4-31b-it', - name: 'Gemma 4 31B IT', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 131072, - cost: { - input: 0.14, - output: 0.4, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'inception/mercury-2', - name: 'Mercury 2', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 128000, - maxTokens: 128000, - cost: { - input: 0.25, - output: 0.75, - cacheRead: 0.025, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'inception/mercury-coder-small', - name: 'Mercury Coder Small Beta', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text'], - contextWindow: 32000, - maxTokens: 16384, - cost: { - input: 0.25, - output: 1, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'kwaipilot/kat-coder-pro-v2', - name: 'Kat Coder Pro V2', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 256000, - maxTokens: 256000, - cost: { - input: 0.3, - output: 1.2, - cacheRead: 0.06, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'meituan/longcat-flash-chat', - name: 'LongCat Flash Chat', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text'], - contextWindow: 128000, - maxTokens: 100000, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'meta/llama-3.1-70b', - name: 'Llama 3.1 70B Instruct', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text'], - contextWindow: 128000, - maxTokens: 8192, - cost: { - input: 0.72, - output: 0.72, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'meta/llama-3.1-8b', - name: 'Llama 3.1 8B Instruct', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text'], - contextWindow: 128000, - maxTokens: 8192, - cost: { - input: 0.22, - output: 0.22, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'meta/llama-3.2-11b', - name: 'Llama 3.2 11B Vision Instruct', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 8192, - cost: { - input: 0.16, - output: 0.16, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'meta/llama-3.2-90b', - name: 'Llama 3.2 90B Vision Instruct', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 8192, - cost: { - input: 0.72, - output: 0.72, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'meta/llama-3.3-70b', - name: 'Llama 3.3 70B Instruct', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text'], - contextWindow: 128000, - maxTokens: 8192, - cost: { - input: 0.72, - output: 0.72, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'meta/llama-4-maverick', - name: 'Llama 4 Maverick 17B Instruct', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 8192, - cost: { - input: 0.24, - output: 0.97, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'meta/llama-4-scout', - name: 'Llama 4 Scout 17B Instruct', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 8192, - cost: { - input: 0.17, - output: 0.66, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'minimax/minimax-m2', - name: 'MiniMax M2', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 205000, - maxTokens: 205000, - cost: { - input: 0.3, - output: 1.2, - cacheRead: 0.03, - cacheWrite: 0.375, - }, - }, - }, - { - modelId: 'minimax/minimax-m2.1', - name: 'MiniMax M2.1', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 204800, - maxTokens: 131072, - cost: { - input: 0.3, - output: 1.2, - cacheRead: 0.03, - cacheWrite: 0.375, - }, - }, - }, - { - modelId: 'minimax/minimax-m2.1-lightning', - name: 'MiniMax M2.1 Lightning', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 204800, - maxTokens: 131072, - cost: { - input: 0.3, - output: 2.4, - cacheRead: 0.03, - cacheWrite: 0.375, - }, - }, - }, - { - modelId: 'minimax/minimax-m2.5', - name: 'MiniMax M2.5', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 204800, - maxTokens: 131000, - cost: { - input: 0.3, - output: 1.2, - cacheRead: 0.03, - cacheWrite: 0.375, - }, - }, - }, - { - modelId: 'minimax/minimax-m2.5-highspeed', - name: 'MiniMax M2.5 High Speed', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 204800, - maxTokens: 131000, - cost: { - input: 0.6, - output: 2.4, - cacheRead: 0.03, - cacheWrite: 0.375, - }, - }, - }, - { - modelId: 'minimax/minimax-m2.7', - name: 'MiniMax M2.7', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 204800, - maxTokens: 131000, - cost: { - input: 0.3, - output: 1.2, - cacheRead: 0.06, - cacheWrite: 0.375, - }, - }, - }, - { - modelId: 'minimax/minimax-m2.7-highspeed', - name: 'MiniMax M2.7 High Speed', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 204800, - maxTokens: 131100, - cost: { - input: 0.6, - output: 2.4, - cacheRead: 0.06, - cacheWrite: 0.375, - }, - }, - }, - { - modelId: 'minimax/minimax-m3', - name: 'MiniMax M3', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 1000000, - cost: { - input: 0.3, - output: 1.2, - cacheRead: 0.06, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistral/codestral', - name: 'Mistral Codestral', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text'], - contextWindow: 128000, - maxTokens: 4000, - cost: { - input: 0.3, - output: 0.9, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistral/devstral-2', - name: 'Devstral 2', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text'], - contextWindow: 256000, - maxTokens: 256000, - cost: { - input: 0.4, - output: 2, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistral/devstral-small', - name: 'Devstral Small 1.1', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text'], - contextWindow: 128000, - maxTokens: 64000, - cost: { - input: 0.1, - output: 0.3, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistral/devstral-small-2', - name: 'Devstral Small 2', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text'], - contextWindow: 256000, - maxTokens: 256000, - cost: { - input: 0.1, - output: 0.3, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistral/ministral-3b', - name: 'Ministral 3B', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text'], - contextWindow: 128000, - maxTokens: 4000, - cost: { - input: 0.1, - output: 0.1, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistral/ministral-8b', - name: 'Ministral 8B', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text'], - contextWindow: 128000, - maxTokens: 4000, - cost: { - input: 0.15, - output: 0.15, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistral/mistral-medium', - name: 'Mistral Medium 3.1', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 64000, - cost: { - input: 0.4, - output: 2, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistral/mistral-medium-3.5', - name: 'Mistral Medium Latest', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 256000, - maxTokens: 256000, - cost: { - input: 1.5, - output: 7.5, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistral/mistral-nemo', - name: 'Mistral Nemo 12B', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text'], - contextWindow: 131072, - maxTokens: 131072, - cost: { - input: 0.02, - output: 0.04, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistral/mistral-small', - name: 'Mistral Small', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text', 'image'], - contextWindow: 32000, - maxTokens: 4000, - cost: { - input: 0.1, - output: 0.3, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistral/pixtral-12b', - name: 'Pixtral 12B 2409', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 4000, - cost: { - input: 0.15, - output: 0.15, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mistral/pixtral-large', - name: 'Pixtral Large', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 4000, - cost: { - input: 2, - output: 6, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'moonshotai/kimi-k2', - name: 'Kimi K2 Instruct', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text'], - contextWindow: 131072, - maxTokens: 131072, - cost: { - input: 0.57, - output: 2.3, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'moonshotai/kimi-k2-thinking', - name: 'Kimi K2 Thinking', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 262114, - maxTokens: 262114, - cost: { - input: 0.6, - output: 2.5, - cacheRead: 0.15, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'moonshotai/kimi-k2.5', - name: 'Kimi K2.5', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262114, - maxTokens: 262114, - cost: { - input: 0.6, - output: 3, - cacheRead: 0.1, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'moonshotai/kimi-k2.6', - name: 'Kimi K2.6', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262000, - maxTokens: 262000, - cost: { - input: 0.95, - output: 4, - cacheRead: 0.16, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'moonshotai/kimi-k2.7-code', - name: 'Kimi K2.7 Code', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 256000, - maxTokens: 32768, - cost: { - input: 0.95, - output: 4, - cacheRead: 0.19, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'nvidia/nemotron-3-super-120b-a12b', - name: 'NVIDIA Nemotron 3 Super 120B A12B', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 256000, - maxTokens: 32000, - cost: { - input: 0.15, - output: 0.65, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'nvidia/nemotron-3-ultra-550b-a55b', - name: 'Nemotron 3 Ultra', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 1000000, - maxTokens: 65000, - cost: { - input: 0.6, - output: 2.4, - cacheRead: 0.12, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'nvidia/nemotron-nano-12b-v2-vl', - name: 'Nvidia Nemotron Nano 12B V2 VL', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 131072, - maxTokens: 131072, - cost: { - input: 0.2, - output: 0.6, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'nvidia/nemotron-nano-9b-v2', - name: 'Nvidia Nemotron Nano 9B V2', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 131072, - cost: { - input: 0.06, - output: 0.23, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-4-turbo', - name: 'GPT-4 Turbo', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 4096, - cost: { - input: 10, - output: 30, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-4.1', - name: 'GPT-4.1', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text', 'image'], - contextWindow: 1047576, - maxTokens: 32768, - cost: { - input: 2, - output: 8, - cacheRead: 0.5, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-4.1-mini', - name: 'GPT-4.1 mini', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text', 'image'], - contextWindow: 1047576, - maxTokens: 32768, - cost: { - input: 0.4, - output: 1.6, - cacheRead: 0.1, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-4.1-nano', - name: 'GPT-4.1 nano', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text', 'image'], - contextWindow: 1047576, - maxTokens: 32768, - cost: { - input: 0.1, - output: 0.4, - cacheRead: 0.025, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-4o', - name: 'GPT-4o', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 2.5, - output: 10, - cacheRead: 1.25, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-4o-mini', - name: 'GPT-4o mini', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 0.15, - output: 0.6, - cacheRead: 0.075, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5', - name: 'GPT-5', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.25, - output: 10, - cacheRead: 0.125, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5-chat', - name: 'GPT 5 Chat', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 1.25, - output: 10, - cacheRead: 0.125, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5-codex', - name: 'GPT-5-Codex', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.25, - output: 10, - cacheRead: 0.125, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5-mini', - name: 'GPT-5 mini', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 0.25, - output: 2, - cacheRead: 0.025, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5-nano', - name: 'GPT-5 nano', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 0.05, - output: 0.4, - cacheRead: 0.005, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5-pro', - name: 'GPT-5 pro', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 272000, - cost: { - input: 15, - output: 120, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5.1-codex', - name: 'GPT-5.1-Codex', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.25, - output: 10, - cacheRead: 0.125, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5.1-codex-max', - name: 'GPT 5.1 Codex Max', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.25, - output: 10, - cacheRead: 0.125, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5.1-codex-mini', - name: 'GPT 5.1 Codex Mini', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 0.25, - output: 2, - cacheRead: 0.025, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5.1-instant', - name: 'GPT-5.1 Instant', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 1.25, - output: 10, - cacheRead: 0.125, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5.1-thinking', - name: 'GPT 5.1 Thinking', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.25, - output: 10, - cacheRead: 0.125, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5.2', - name: 'GPT 5.2', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.75, - output: 14, - cacheRead: 0.175, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5.2-chat', - name: 'GPT 5.2 Chat', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 1.75, - output: 14, - cacheRead: 0.175, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5.2-codex', - name: 'GPT 5.2 Codex', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.75, - output: 14, - cacheRead: 0.175, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5.2-pro', - name: 'GPT 5.2 ', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 21, - output: 168, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5.3-chat', - name: 'GPT-5.3 Chat', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 16384, - cost: { - input: 1.75, - output: 14, - cacheRead: 0.175, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5.3-codex', - name: 'GPT 5.3 Codex', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 1.75, - output: 14, - cacheRead: 0.175, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5.4', - name: 'GPT 5.4', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1050000, - maxTokens: 128000, - cost: { - input: 2.5, - output: 15, - cacheRead: 0.25, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5.4-mini', - name: 'GPT 5.4 Mini', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 0.75, - output: 4.5, - cacheRead: 0.075, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5.4-nano', - name: 'GPT 5.4 Nano', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 400000, - maxTokens: 128000, - cost: { - input: 0.2, - output: 1.25, - cacheRead: 0.02, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5.4-pro', - name: 'GPT 5.4 Pro', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1050000, - maxTokens: 128000, - cost: { - input: 30, - output: 180, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5.5', - name: 'GPT 5.5', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 5, - output: 30, - cacheRead: 0.5, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-5.5-pro', - name: 'GPT 5.5 Pro', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 30, - output: 180, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-oss-120b', - name: 'GPT OSS 120B', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 131000, - cost: { - input: 0.35, - output: 0.75, - cacheRead: 0.25, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-oss-20b', - name: 'GPT OSS 20B', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 8192, - cost: { - input: 0.05, - output: 0.2, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/gpt-oss-safeguard-20b', - name: 'GPT OSS Safeguard 20B', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 65536, - cost: { - input: 0.075, - output: 0.3, - cacheRead: 0.037, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/o1', - name: 'o1', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 100000, - cost: { - input: 15, - output: 60, - cacheRead: 7.5, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/o3', - name: 'o3', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 100000, - cost: { - input: 2, - output: 8, - cacheRead: 0.5, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/o3-deep-research', - name: 'o3-deep-research', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 100000, - cost: { - input: 10, - output: 40, - cacheRead: 2.5, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/o3-mini', - name: 'o3-mini', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 200000, - maxTokens: 100000, - cost: { - input: 1.1, - output: 4.4, - cacheRead: 0.55, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/o3-pro', - name: 'o3 Pro', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 100000, - cost: { - input: 20, - output: 80, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'openai/o4-mini', - name: 'o4-mini', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 100000, - cost: { - input: 1.1, - output: 4.4, - cacheRead: 0.275, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'perplexity/sonar', - name: 'Sonar', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text', 'image'], - contextWindow: 127000, - maxTokens: 8000, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'perplexity/sonar-pro', - name: 'Sonar Pro', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 8000, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'stepfun/step-3.5-flash', - name: 'StepFun 3.5 Flash', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 262114, - maxTokens: 262114, - cost: { - input: 0.09, - output: 0.3, - cacheRead: 0, - cacheWrite: 0.02, - }, - }, - }, - { - modelId: 'stepfun/step-3.7-flash', - name: 'Step 3.7 Flash', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 256000, - maxTokens: 256000, - cost: { - input: 0.2, - output: 1.15, - cacheRead: 0.04, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'xai/grok-4.1-fast-non-reasoning', - name: 'Grok 4.1 Fast Non-Reasoning', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 1000000, - cost: { - input: 0.2, - output: 0.5, - cacheRead: 0.05, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'xai/grok-4.1-fast-reasoning', - name: 'Grok 4.1 Fast Reasoning', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 1000000, - cost: { - input: 0.2, - output: 0.5, - cacheRead: 0.05, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'xai/grok-4.20-multi-agent', - name: 'Grok 4.20 Multi-Agent', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 2000000, - maxTokens: 2000000, - cost: { - input: 1.25, - output: 2.5, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'xai/grok-4.20-multi-agent-beta', - name: 'Grok 4.20 Multi Agent Beta', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 2000000, - maxTokens: 2000000, - cost: { - input: 1.25, - output: 2.5, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'xai/grok-4.20-non-reasoning', - name: 'Grok 4.20 Non-Reasoning', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text', 'image'], - contextWindow: 2000000, - maxTokens: 2000000, - cost: { - input: 1.25, - output: 2.5, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'xai/grok-4.20-non-reasoning-beta', - name: 'Grok 4.20 Beta Non-Reasoning', - config: { - api: 'anthropic-messages', - reasoning: false, - input: ['text', 'image'], - contextWindow: 2000000, - maxTokens: 2000000, - cost: { - input: 1.25, - output: 2.5, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'xai/grok-4.20-reasoning', - name: 'Grok 4.20 Reasoning', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 2000000, - maxTokens: 2000000, - cost: { - input: 1.25, - output: 2.5, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'xai/grok-4.20-reasoning-beta', - name: 'Grok 4.20 Beta Reasoning', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 2000000, - maxTokens: 2000000, - cost: { - input: 1.25, - output: 2.5, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'xai/grok-4.3', - name: 'Grok 4.3', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 1000000, - cost: { - input: 1.25, - output: 2.5, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'xai/grok-build-0.1', - name: 'Grok Build 0.1', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 256000, - maxTokens: 256000, - cost: { - input: 1, - output: 2, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'xiaomi/mimo-v2-flash', - name: 'MiMo V2 Flash', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 262144, - maxTokens: 32000, - cost: { - input: 0.1, - output: 0.3, - cacheRead: 0.01, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'xiaomi/mimo-v2-pro', - name: 'MiMo V2 Pro', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 1000000, - maxTokens: 128000, - cost: { - input: 1, - output: 3, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'xiaomi/mimo-v2.5', - name: 'MiMo M2.5', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1050000, - maxTokens: 131100, - cost: { - input: 0.14, - output: 0.28, - cacheRead: 0.0028, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'xiaomi/mimo-v2.5-pro', - name: 'MiMo V2.5 Pro', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1050000, - maxTokens: 131000, - cost: { - input: 0.435, - output: 0.87, - cacheRead: 0.0036, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'zai/glm-4.5', - name: 'GLM-4.5', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 128000, - maxTokens: 96000, - cost: { - input: 0.6, - output: 2.2, - cacheRead: 0.11, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'zai/glm-4.5-air', - name: 'GLM 4.5 Air', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 128000, - maxTokens: 96000, - cost: { - input: 0.2, - output: 1.1, - cacheRead: 0.03, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'zai/glm-4.5v', - name: 'GLM 4.5V', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 66000, - maxTokens: 16000, - cost: { - input: 0.6, - output: 1.8, - cacheRead: 0.11, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'zai/glm-4.6', - name: 'GLM 4.6', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 200000, - maxTokens: 96000, - cost: { - input: 0.6, - output: 2.2, - cacheRead: 0.11, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'zai/glm-4.6v', - name: 'GLM-4.6V', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 24000, - cost: { - input: 0.3, - output: 0.9, - cacheRead: 0.05, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'zai/glm-4.6v-flash', - name: 'GLM-4.6V-Flash', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 128000, - maxTokens: 24000, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'zai/glm-4.7', - name: 'GLM 4.7', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 131000, - maxTokens: 40000, - cost: { - input: 2.25, - output: 2.75, - cacheRead: 2.25, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'zai/glm-4.7-flash', - name: 'GLM 4.7 Flash', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 200000, - maxTokens: 131000, - cost: { - input: 0.07, - output: 0.4, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'zai/glm-4.7-flashx', - name: 'GLM 4.7 FlashX', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 200000, - maxTokens: 128000, - cost: { - input: 0.06, - output: 0.4, - cacheRead: 0.01, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'zai/glm-5', - name: 'GLM 5', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 202800, - maxTokens: 131100, - cost: { - input: 1, - output: 3.2, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'zai/glm-5-turbo', - name: 'GLM 5 Turbo', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text'], - contextWindow: 202800, - maxTokens: 131100, - cost: { - input: 1.2, - output: 4, - cacheRead: 0.24, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'zai/glm-5.1', - name: 'GLM 5.1', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 202800, - maxTokens: 64000, - cost: { - input: 1.4, - output: 4.4, - cacheRead: 0.26, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'zai/glm-5v-turbo', - name: 'GLM 5V Turbo', - config: { - api: 'anthropic-messages', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 128000, - cost: { - input: 1.2, - output: 4, - cacheRead: 0.24, - cacheWrite: 0, - }, - }, - }, - ], - }, - xai: { - name: 'xai', - config: { - api: 'openai-completions', - baseUrl: 'https://api.x.ai/v1', - apiKey: 'XAI_API_KEY', - }, - models: [ - { - modelId: 'grok-3', - name: 'Grok 3', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 131072, - maxTokens: 8192, - cost: { - input: 3, - output: 15, - cacheRead: 0.75, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'grok-3-fast', - name: 'Grok 3 Fast', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 131072, - maxTokens: 8192, - cost: { - input: 5, - output: 25, - cacheRead: 1.25, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'grok-4.20-0309-non-reasoning', - name: 'Grok 4.20 (Non-Reasoning)', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 30000, - cost: { - input: 1.25, - output: 2.5, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'grok-4.20-0309-reasoning', - name: 'Grok 4.20 (Reasoning)', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 30000, - cost: { - input: 1.25, - output: 2.5, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'grok-4.3', - name: 'Grok 4.3', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1000000, - maxTokens: 30000, - cost: { - input: 1.25, - output: 2.5, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'grok-build-0.1', - name: 'Grok Build 0.1', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 256000, - maxTokens: 256000, - cost: { - input: 1, - output: 2, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'grok-code-fast-1', - name: 'Grok Code Fast 1', - config: { - api: 'openai-completions', - reasoning: false, - input: ['text'], - contextWindow: 32768, - maxTokens: 8192, - cost: { - input: 0.2, - output: 1.5, - cacheRead: 0.02, - cacheWrite: 0, - }, - }, - }, - ], - }, - xiaomi: { - name: 'xiaomi', - config: { - api: 'openai-completions', - baseUrl: 'https://api.xiaomimimo.com/v1', - apiKey: 'XIAOMI_API_KEY', - }, - models: [ - { - modelId: 'mimo-v2-flash', - name: 'MiMo-V2-Flash', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 262144, - maxTokens: 65536, - cost: { - input: 0.1, - output: 0.3, - cacheRead: 0.01, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mimo-v2-omni', - name: 'MiMo-V2-Omni', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 131072, - cost: { - input: 0.4, - output: 2, - cacheRead: 0.08, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mimo-v2-pro', - name: 'MiMo-V2-Pro', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 1048576, - maxTokens: 131072, - cost: { - input: 1, - output: 3, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mimo-v2.5', - name: 'MiMo-V2.5', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 131072, - cost: { - input: 0.4, - output: 2, - cacheRead: 0.08, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mimo-v2.5-pro', - name: 'MiMo-V2.5-Pro', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 1048576, - maxTokens: 131072, - cost: { - input: 1, - output: 3, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mimo-v2.5-pro-ultraspeed', - name: 'MiMo-V2.5-Pro-UltraSpeed', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 1048576, - maxTokens: 131072, - cost: { - input: 1.305, - output: 2.61, - cacheRead: 0.0108, - cacheWrite: 0, - }, - }, - }, - ], - }, - 'xiaomi-token-plan-ams': { - name: 'xiaomi-token-plan-ams', - config: { - api: 'openai-completions', - baseUrl: 'https://token-plan-ams.xiaomimimo.com/v1', - apiKey: 'XIAOMI_TOKEN_PLAN_AMS_API_KEY', - }, - models: [ - { - modelId: 'mimo-v2-omni', - name: 'MiMo-V2-Omni', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 131072, - cost: { - input: 0.4, - output: 2, - cacheRead: 0.08, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mimo-v2-pro', - name: 'MiMo-V2-Pro', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 1048576, - maxTokens: 131072, - cost: { - input: 1, - output: 3, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mimo-v2.5', - name: 'MiMo-V2.5', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 131072, - cost: { - input: 0.4, - output: 2, - cacheRead: 0.08, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mimo-v2.5-pro', - name: 'MiMo-V2.5-Pro', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 1048576, - maxTokens: 131072, - cost: { - input: 1, - output: 3, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mimo-v2.5-pro-ultraspeed', - name: 'MiMo-V2.5-Pro-UltraSpeed', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 1048576, - maxTokens: 131072, - cost: { - input: 1.305, - output: 2.61, - cacheRead: 0.0108, - cacheWrite: 0, - }, - }, - }, - ], - }, - 'xiaomi-token-plan-cn': { - name: 'xiaomi-token-plan-cn', - config: { - api: 'openai-completions', - baseUrl: 'https://token-plan-cn.xiaomimimo.com/v1', - apiKey: 'XIAOMI_TOKEN_PLAN_CN_API_KEY', - }, - models: [ - { - modelId: 'mimo-v2-omni', - name: 'MiMo-V2-Omni', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 131072, - cost: { - input: 0.4, - output: 2, - cacheRead: 0.08, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mimo-v2-pro', - name: 'MiMo-V2-Pro', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 1048576, - maxTokens: 131072, - cost: { - input: 1, - output: 3, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mimo-v2.5', - name: 'MiMo-V2.5', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 131072, - cost: { - input: 0.4, - output: 2, - cacheRead: 0.08, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mimo-v2.5-pro', - name: 'MiMo-V2.5-Pro', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 1048576, - maxTokens: 131072, - cost: { - input: 1, - output: 3, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mimo-v2.5-pro-ultraspeed', - name: 'MiMo-V2.5-Pro-UltraSpeed', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 1048576, - maxTokens: 131072, - cost: { - input: 1.305, - output: 2.61, - cacheRead: 0.0108, - cacheWrite: 0, - }, - }, - }, - ], - }, - 'xiaomi-token-plan-sgp': { - name: 'xiaomi-token-plan-sgp', - config: { - api: 'openai-completions', - baseUrl: 'https://token-plan-sgp.xiaomimimo.com/v1', - apiKey: 'XIAOMI_TOKEN_PLAN_SGP_API_KEY', - }, - models: [ - { - modelId: 'mimo-v2-omni', - name: 'MiMo-V2-Omni', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 262144, - maxTokens: 131072, - cost: { - input: 0.4, - output: 2, - cacheRead: 0.08, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mimo-v2-pro', - name: 'MiMo-V2-Pro', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 1048576, - maxTokens: 131072, - cost: { - input: 1, - output: 3, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mimo-v2.5', - name: 'MiMo-V2.5', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 1048576, - maxTokens: 131072, - cost: { - input: 0.4, - output: 2, - cacheRead: 0.08, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mimo-v2.5-pro', - name: 'MiMo-V2.5-Pro', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 1048576, - maxTokens: 131072, - cost: { - input: 1, - output: 3, - cacheRead: 0.2, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'mimo-v2.5-pro-ultraspeed', - name: 'MiMo-V2.5-Pro-UltraSpeed', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 1048576, - maxTokens: 131072, - cost: { - input: 1.305, - output: 2.61, - cacheRead: 0.0108, - cacheWrite: 0, - }, - }, - }, - ], - }, - zai: { - name: 'zai', - config: { - api: 'openai-completions', - baseUrl: 'https://api.z.ai/api/coding/paas/v4', - apiKey: 'ZAI_API_KEY', - }, - models: [ - { - modelId: 'glm-4.5-air', - name: 'GLM-4.5-Air', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 98304, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'glm-4.7', - name: 'GLM-4.7', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 204800, - maxTokens: 131072, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'glm-5-turbo', - name: 'GLM-5-Turbo', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 200000, - maxTokens: 131072, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'glm-5.1', - name: 'GLM-5.1', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 200000, - maxTokens: 131072, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'glm-5.2', - name: 'GLM-5.2', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 1000000, - maxTokens: 131072, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'glm-5v-turbo', - name: 'GLM-5V-Turbo', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 131072, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - ], - }, - 'zai-coding-cn': { - name: 'zai-coding-cn', - config: { - api: 'openai-completions', - baseUrl: 'https://open.bigmodel.cn/api/coding/paas/v4', - apiKey: '', - }, - models: [ - { - modelId: 'glm-4.5-air', - name: 'GLM-4.5-Air', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 131072, - maxTokens: 98304, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'glm-4.7', - name: 'GLM-4.7', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 204800, - maxTokens: 131072, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'glm-5-turbo', - name: 'GLM-5-Turbo', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 200000, - maxTokens: 131072, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'glm-5.1', - name: 'GLM-5.1', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 200000, - maxTokens: 131072, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'glm-5.2', - name: 'GLM-5.2', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text'], - contextWindow: 1000000, - maxTokens: 131072, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - { - modelId: 'glm-5v-turbo', - name: 'GLM-5V-Turbo', - config: { - api: 'openai-completions', - reasoning: true, - input: ['text', 'image'], - contextWindow: 200000, - maxTokens: 131072, - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - }, - }, - ], - }, + openai, + anthropic, + google, + deepseek, + groq, + openrouter, + mistral, + 'amazon-bedrock': amazonBedrock, + 'ant-ling': antLing, + 'azure-openai-responses': azureOpenaiResponses, + cerebras, + 'cloudflare-ai-gateway': cloudflareAiGateway, + 'cloudflare-workers-ai': cloudflareWorkersAi, + fireworks, + 'github-copilot': githubCopilot, + 'google-vertex': googleVertex, + huggingface, + 'kimi-coding': kimiCoding, + minimax, + 'minimax-cn': minimaxCn, + moonshotai, + 'moonshotai-cn': moonshotaiCn, + nvidia, + 'openai-codex': openaiCodex, + opencode, + 'opencode-go': opencodeGo, + 'qwen-token-plan': qwenTokenPlan, + 'qwen-token-plan-cn': qwenTokenPlanCn, + together, + 'vercel-ai-gateway': vercelAiGateway, + xai, + xiaomi, + 'xiaomi-token-plan-ams': xiaomiTokenPlanAms, + 'xiaomi-token-plan-cn': xiaomiTokenPlanCn, + 'xiaomi-token-plan-sgp': xiaomiTokenPlanSgp, + zai, + 'zai-coding-cn': zaiCodingCn, } as unknown as Record diff --git a/packages/core/src/generated/providers/amazon-bedrock.ts b/packages/core/src/generated/providers/amazon-bedrock.ts new file mode 100644 index 00000000..fefead86 --- /dev/null +++ b/packages/core/src/generated/providers/amazon-bedrock.ts @@ -0,0 +1,1867 @@ +// This file is auto-generated by scripts/generate-builtin-providers.ts +// Do not edit manually - run 'bun run generate-providers' to update + +export const providerName = 'amazon-bedrock' +export const providerConfig = { + name: 'amazon-bedrock', + config: { + api: 'bedrock-converse-stream', + baseUrl: 'https://bedrock-runtime.us-east-1.amazonaws.com', + apiKey: '', + }, + models: [ + { + modelId: 'amazon.nova-2-lite-v1:0', + name: 'Nova 2 Lite', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 4096, + cost: { + input: 0.33, + output: 2.75, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'amazon.nova-lite-v1:0', + name: 'Nova Lite', + config: { + api: 'bedrock-converse-stream', + reasoning: false, + input: ['text', 'image'], + contextWindow: 300000, + maxTokens: 8192, + cost: { + input: 0.06, + output: 0.24, + cacheRead: 0.015, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'amazon.nova-micro-v1:0', + name: 'Nova Micro', + config: { + api: 'bedrock-converse-stream', + reasoning: false, + input: ['text'], + contextWindow: 128000, + maxTokens: 8192, + cost: { + input: 0.035, + output: 0.14, + cacheRead: 0.00875, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'amazon.nova-pro-v1:0', + name: 'Nova Pro', + config: { + api: 'bedrock-converse-stream', + reasoning: false, + input: ['text', 'image'], + contextWindow: 300000, + maxTokens: 8192, + cost: { + input: 0.8, + output: 3.2, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'anthropic.claude-fable-5', + name: 'Claude Fable 5', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 10, + output: 50, + cacheRead: 1, + cacheWrite: 12.5, + }, + }, + }, + { + modelId: 'anthropic.claude-haiku-4-5-20251001-v1:0', + name: 'Claude Haiku 4.5', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 64000, + cost: { + input: 1, + output: 5, + cacheRead: 0.1, + cacheWrite: 1.25, + }, + }, + }, + { + modelId: 'anthropic.claude-opus-4-1-20250805-v1:0', + name: 'Claude Opus 4.1', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 32000, + cost: { + input: 15, + output: 75, + cacheRead: 1.5, + cacheWrite: 18.75, + }, + }, + }, + { + modelId: 'anthropic.claude-opus-4-5-20251101-v1:0', + name: 'Claude Opus 4.5', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 64000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'anthropic.claude-opus-4-6-v1', + name: 'Claude Opus 4.6', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'anthropic.claude-opus-4-7', + name: 'Claude Opus 4.7', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'anthropic.claude-opus-4-8', + name: 'Claude Opus 4.8', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'anthropic.claude-sonnet-4-5-20250929-v1:0', + name: 'Claude Sonnet 4.5', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 64000, + cost: { + input: 3, + output: 15, + cacheRead: 0.3, + cacheWrite: 3.75, + }, + }, + }, + { + modelId: 'anthropic.claude-sonnet-4-6', + name: 'Claude Sonnet 4.6', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 64000, + cost: { + input: 3, + output: 15, + cacheRead: 0.3, + cacheWrite: 3.75, + }, + }, + }, + { + modelId: 'anthropic.claude-sonnet-5', + name: 'Claude Sonnet 5', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 2, + output: 10, + cacheRead: 0.2, + cacheWrite: 2.5, + }, + }, + }, + { + modelId: 'au.anthropic.claude-haiku-4-5-20251001-v1:0', + name: 'Claude Haiku 4.5 (AU)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 64000, + cost: { + input: 1, + output: 5, + cacheRead: 0.1, + cacheWrite: 1.25, + }, + }, + }, + { + modelId: 'au.anthropic.claude-opus-4-6-v1', + name: 'AU Anthropic Claude Opus 4.6', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 16.5, + output: 82.5, + cacheRead: 1.65, + cacheWrite: 20.625, + }, + }, + }, + { + modelId: 'au.anthropic.claude-opus-4-8', + name: 'Claude Opus 4.8 (AU)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'au.anthropic.claude-sonnet-4-5-20250929-v1:0', + name: 'Claude Sonnet 4.5 (AU)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 64000, + cost: { + input: 3, + output: 15, + cacheRead: 0.3, + cacheWrite: 3.75, + }, + }, + }, + { + modelId: 'au.anthropic.claude-sonnet-4-6', + name: 'AU Anthropic Claude Sonnet 4.6', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 3.3, + output: 16.5, + cacheRead: 0.33, + cacheWrite: 4.125, + }, + }, + }, + { + modelId: 'au.anthropic.claude-sonnet-5', + name: 'Claude Sonnet 5 (AU)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 2, + output: 10, + cacheRead: 0.2, + cacheWrite: 2.5, + }, + }, + }, + { + modelId: 'deepseek.r1-v1:0', + name: 'DeepSeek-R1', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text'], + contextWindow: 128000, + maxTokens: 32768, + cost: { + input: 1.35, + output: 5.4, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'deepseek.v3-v1:0', + name: 'DeepSeek-V3.1', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text'], + contextWindow: 163840, + maxTokens: 81920, + cost: { + input: 0.58, + output: 1.68, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'deepseek.v3.2', + name: 'DeepSeek-V3.2', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text'], + contextWindow: 163840, + maxTokens: 81920, + cost: { + input: 0.62, + output: 1.85, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'eu.anthropic.claude-fable-5', + name: 'Claude Fable 5 (EU)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 11, + output: 55, + cacheRead: 1.1, + cacheWrite: 13.75, + }, + }, + }, + { + modelId: 'eu.anthropic.claude-haiku-4-5-20251001-v1:0', + name: 'Claude Haiku 4.5 (EU)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 64000, + cost: { + input: 1.1, + output: 5.5, + cacheRead: 0.11, + cacheWrite: 1.375, + }, + }, + }, + { + modelId: 'eu.anthropic.claude-opus-4-5-20251101-v1:0', + name: 'Claude Opus 4.5 (EU)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 64000, + cost: { + input: 5.5, + output: 27.5, + cacheRead: 0.55, + cacheWrite: 6.875, + }, + }, + }, + { + modelId: 'eu.anthropic.claude-opus-4-6-v1', + name: 'Claude Opus 4.6 (EU)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 5.5, + output: 27.5, + cacheRead: 0.55, + cacheWrite: 6.875, + }, + }, + }, + { + modelId: 'eu.anthropic.claude-opus-4-7', + name: 'Claude Opus 4.7 (EU)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 5.5, + output: 27.5, + cacheRead: 0.55, + cacheWrite: 6.875, + }, + }, + }, + { + modelId: 'eu.anthropic.claude-opus-4-8', + name: 'Claude Opus 4.8 (EU)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 5.5, + output: 27.5, + cacheRead: 0.55, + cacheWrite: 6.875, + }, + }, + }, + { + modelId: 'eu.anthropic.claude-sonnet-4-5-20250929-v1:0', + name: 'Claude Sonnet 4.5 (EU)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 64000, + cost: { + input: 3.3, + output: 16.5, + cacheRead: 0.33, + cacheWrite: 4.125, + }, + }, + }, + { + modelId: 'eu.anthropic.claude-sonnet-4-6', + name: 'Claude Sonnet 4.6 (EU)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 64000, + cost: { + input: 3.3, + output: 16.5, + cacheRead: 0.33, + cacheWrite: 4.125, + }, + }, + }, + { + modelId: 'eu.anthropic.claude-sonnet-5', + name: 'Claude Sonnet 5 (EU)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 2.2, + output: 11, + cacheRead: 0.22, + cacheWrite: 2.75, + }, + }, + }, + { + modelId: 'global.anthropic.claude-fable-5', + name: 'Claude Fable 5 (Global)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 10, + output: 50, + cacheRead: 1, + cacheWrite: 12.5, + }, + }, + }, + { + modelId: 'global.anthropic.claude-haiku-4-5-20251001-v1:0', + name: 'Claude Haiku 4.5 (Global)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 64000, + cost: { + input: 1, + output: 5, + cacheRead: 0.1, + cacheWrite: 1.25, + }, + }, + }, + { + modelId: 'global.anthropic.claude-opus-4-5-20251101-v1:0', + name: 'Claude Opus 4.5 (Global)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 64000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'global.anthropic.claude-opus-4-6-v1', + name: 'Claude Opus 4.6 (Global)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'global.anthropic.claude-opus-4-7', + name: 'Claude Opus 4.7 (Global)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'global.anthropic.claude-opus-4-8', + name: 'Claude Opus 4.8 (Global)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'global.anthropic.claude-sonnet-4-5-20250929-v1:0', + name: 'Claude Sonnet 4.5 (Global)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 64000, + cost: { + input: 3, + output: 15, + cacheRead: 0.3, + cacheWrite: 3.75, + }, + }, + }, + { + modelId: 'global.anthropic.claude-sonnet-4-6', + name: 'Claude Sonnet 4.6 (Global)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 64000, + cost: { + input: 3, + output: 15, + cacheRead: 0.3, + cacheWrite: 3.75, + }, + }, + }, + { + modelId: 'global.anthropic.claude-sonnet-5', + name: 'Claude Sonnet 5 (Global)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 2, + output: 10, + cacheRead: 0.2, + cacheWrite: 2.5, + }, + }, + }, + { + modelId: 'google.gemma-3-27b-it', + name: 'Google Gemma 3 27B Instruct', + config: { + api: 'bedrock-converse-stream', + reasoning: false, + input: ['text', 'image'], + contextWindow: 202752, + maxTokens: 8192, + cost: { + input: 0.12, + output: 0.2, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'google.gemma-3-4b-it', + name: 'Gemma 3 4B IT', + config: { + api: 'bedrock-converse-stream', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 4096, + cost: { + input: 0.04, + output: 0.08, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'jp.anthropic.claude-haiku-4-5-20251001-v1:0', + name: 'Claude Haiku 4.5 (JP)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 64000, + cost: { + input: 1, + output: 5, + cacheRead: 0.1, + cacheWrite: 1.25, + }, + }, + }, + { + modelId: 'jp.anthropic.claude-opus-4-7', + name: 'Claude Opus 4.7 (JP)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'jp.anthropic.claude-opus-4-8', + name: 'Claude Opus 4.8 (JP)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'jp.anthropic.claude-sonnet-4-5-20250929-v1:0', + name: 'Claude Sonnet 4.5 (JP)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 64000, + cost: { + input: 3, + output: 15, + cacheRead: 0.3, + cacheWrite: 3.75, + }, + }, + }, + { + modelId: 'jp.anthropic.claude-sonnet-4-6', + name: 'Claude Sonnet 4.6 (JP)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 64000, + cost: { + input: 3, + output: 15, + cacheRead: 0.3, + cacheWrite: 3.75, + }, + }, + }, + { + modelId: 'jp.anthropic.claude-sonnet-5', + name: 'Claude Sonnet 5 (JP)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 2, + output: 10, + cacheRead: 0.2, + cacheWrite: 2.5, + }, + }, + }, + { + modelId: 'meta.llama3-1-70b-instruct-v1:0', + name: 'Llama 3.1 70B Instruct', + config: { + api: 'bedrock-converse-stream', + reasoning: false, + input: ['text'], + contextWindow: 128000, + maxTokens: 4096, + cost: { + input: 0.72, + output: 0.72, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'meta.llama3-1-8b-instruct-v1:0', + name: 'Llama 3.1 8B Instruct', + config: { + api: 'bedrock-converse-stream', + reasoning: false, + input: ['text'], + contextWindow: 128000, + maxTokens: 4096, + cost: { + input: 0.22, + output: 0.22, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'meta.llama3-3-70b-instruct-v1:0', + name: 'Llama 3.3 70B Instruct', + config: { + api: 'bedrock-converse-stream', + reasoning: false, + input: ['text'], + contextWindow: 128000, + maxTokens: 4096, + cost: { + input: 0.72, + output: 0.72, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'meta.llama4-maverick-17b-instruct-v1:0', + name: 'Llama 4 Maverick 17B Instruct', + config: { + api: 'bedrock-converse-stream', + reasoning: false, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 16384, + cost: { + input: 0.24, + output: 0.97, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'meta.llama4-scout-17b-instruct-v1:0', + name: 'Llama 4 Scout 17B Instruct', + config: { + api: 'bedrock-converse-stream', + reasoning: false, + input: ['text', 'image'], + contextWindow: 3500000, + maxTokens: 16384, + cost: { + input: 0.17, + output: 0.66, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'minimax.minimax-m2', + name: 'MiniMax M2', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text'], + contextWindow: 204608, + maxTokens: 128000, + cost: { + input: 0.3, + output: 1.2, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'minimax.minimax-m2.1', + name: 'MiniMax M2.1', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text'], + contextWindow: 204800, + maxTokens: 131072, + cost: { + input: 0.3, + output: 1.2, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'minimax.minimax-m2.5', + name: 'MiniMax M2.5', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text'], + contextWindow: 196608, + maxTokens: 98304, + cost: { + input: 0.3, + output: 1.2, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistral.devstral-2-123b', + name: 'Devstral 2 123B', + config: { + api: 'bedrock-converse-stream', + reasoning: false, + input: ['text'], + contextWindow: 256000, + maxTokens: 8192, + cost: { + input: 0.4, + output: 2, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistral.magistral-small-2509', + name: 'Magistral Small 1.2', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 40000, + cost: { + input: 0.5, + output: 1.5, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistral.ministral-3-14b-instruct', + name: 'Ministral 14B 3.0', + config: { + api: 'bedrock-converse-stream', + reasoning: false, + input: ['text'], + contextWindow: 128000, + maxTokens: 4096, + cost: { + input: 0.2, + output: 0.2, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistral.ministral-3-3b-instruct', + name: 'Ministral 3 3B', + config: { + api: 'bedrock-converse-stream', + reasoning: false, + input: ['text', 'image'], + contextWindow: 256000, + maxTokens: 8192, + cost: { + input: 0.1, + output: 0.1, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistral.ministral-3-8b-instruct', + name: 'Ministral 3 8B', + config: { + api: 'bedrock-converse-stream', + reasoning: false, + input: ['text'], + contextWindow: 128000, + maxTokens: 4096, + cost: { + input: 0.15, + output: 0.15, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistral.mistral-large-3-675b-instruct', + name: 'Mistral Large 3', + config: { + api: 'bedrock-converse-stream', + reasoning: false, + input: ['text', 'image'], + contextWindow: 256000, + maxTokens: 8192, + cost: { + input: 0.5, + output: 1.5, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistral.pixtral-large-2502-v1:0', + name: 'Pixtral Large (25.02)', + config: { + api: 'bedrock-converse-stream', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 8192, + cost: { + input: 2, + output: 6, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistral.voxtral-mini-3b-2507', + name: 'Voxtral Mini 3B 2507', + config: { + api: 'bedrock-converse-stream', + reasoning: false, + input: ['text'], + contextWindow: 128000, + maxTokens: 4096, + cost: { + input: 0.04, + output: 0.04, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistral.voxtral-small-24b-2507', + name: 'Voxtral Small 24B 2507', + config: { + api: 'bedrock-converse-stream', + reasoning: false, + input: ['text'], + contextWindow: 32000, + maxTokens: 8192, + cost: { + input: 0.15, + output: 0.35, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'moonshot.kimi-k2-thinking', + name: 'Kimi K2 Thinking', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text'], + contextWindow: 262143, + maxTokens: 16000, + cost: { + input: 0.6, + output: 2.5, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'moonshotai.kimi-k2.5', + name: 'Kimi K2.5', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262143, + maxTokens: 16000, + cost: { + input: 0.6, + output: 3, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'nvidia.nemotron-nano-12b-v2', + name: 'NVIDIA Nemotron Nano 12B v2 VL BF16', + config: { + api: 'bedrock-converse-stream', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 4096, + cost: { + input: 0.2, + output: 0.6, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'nvidia.nemotron-nano-3-30b', + name: 'NVIDIA Nemotron Nano 3 30B', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text'], + contextWindow: 128000, + maxTokens: 4096, + cost: { + input: 0.06, + output: 0.24, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'nvidia.nemotron-nano-9b-v2', + name: 'NVIDIA Nemotron Nano 9B v2', + config: { + api: 'bedrock-converse-stream', + reasoning: false, + input: ['text'], + contextWindow: 128000, + maxTokens: 4096, + cost: { + input: 0.06, + output: 0.23, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'nvidia.nemotron-super-3-120b', + name: 'NVIDIA Nemotron 3 Super 120B A12B', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text'], + contextWindow: 262144, + maxTokens: 131072, + cost: { + input: 0.15, + output: 0.65, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai.gpt-5.4', + name: 'GPT-5.4', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 272000, + maxTokens: 128000, + cost: { + input: 2.75, + output: 16.5, + cacheRead: 0.275, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai.gpt-5.5', + name: 'GPT-5.5', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 272000, + maxTokens: 128000, + cost: { + input: 5.5, + output: 33, + cacheRead: 0.55, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai.gpt-5.6-luna', + name: 'GPT-5.6 Luna', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 272000, + maxTokens: 128000, + cost: { + input: 1, + output: 6, + cacheRead: 0.1, + cacheWrite: 1.25, + }, + }, + }, + { + modelId: 'openai.gpt-5.6-sol', + name: 'GPT-5.6 Sol', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 272000, + maxTokens: 128000, + cost: { + input: 5, + output: 30, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'openai.gpt-5.6-terra', + name: 'GPT-5.6 Terra', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 272000, + maxTokens: 128000, + cost: { + input: 2.5, + output: 15, + cacheRead: 0.25, + cacheWrite: 3.125, + }, + }, + }, + { + modelId: 'openai.gpt-oss-120b', + name: 'gpt-oss-120b', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 0.15, + output: 0.6, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai.gpt-oss-120b-1:0', + name: 'gpt-oss-120b', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 0.15, + output: 0.6, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai.gpt-oss-20b', + name: 'gpt-oss-20b', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 0.07, + output: 0.3, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai.gpt-oss-20b-1:0', + name: 'gpt-oss-20b', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 0.07, + output: 0.3, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai.gpt-oss-safeguard-120b', + name: 'GPT OSS Safeguard 120B', + config: { + api: 'bedrock-converse-stream', + reasoning: false, + input: ['text'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 0.15, + output: 0.6, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai.gpt-oss-safeguard-20b', + name: 'GPT OSS Safeguard 20B', + config: { + api: 'bedrock-converse-stream', + reasoning: false, + input: ['text'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 0.07, + output: 0.2, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen.qwen3-235b-a22b-2507-v1:0', + name: 'Qwen3 235B A22B 2507', + config: { + api: 'bedrock-converse-stream', + reasoning: false, + input: ['text'], + contextWindow: 262144, + maxTokens: 131072, + cost: { + input: 0.22, + output: 0.88, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen.qwen3-32b-v1:0', + name: 'Qwen3 32B (dense)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text'], + contextWindow: 16384, + maxTokens: 16384, + cost: { + input: 0.15, + output: 0.6, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen.qwen3-coder-30b-a3b-v1:0', + name: 'Qwen3 Coder 30B A3B Instruct', + config: { + api: 'bedrock-converse-stream', + reasoning: false, + input: ['text'], + contextWindow: 262144, + maxTokens: 131072, + cost: { + input: 0.15, + output: 0.6, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen.qwen3-coder-480b-a35b-v1:0', + name: 'Qwen3 Coder 480B A35B Instruct', + config: { + api: 'bedrock-converse-stream', + reasoning: false, + input: ['text'], + contextWindow: 131072, + maxTokens: 65536, + cost: { + input: 0.22, + output: 1.8, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen.qwen3-coder-next', + name: 'Qwen3 Coder Next', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 65536, + cost: { + input: 0.22, + output: 1.8, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen.qwen3-next-80b-a3b', + name: 'Qwen/Qwen3-Next-80B-A3B-Instruct', + config: { + api: 'bedrock-converse-stream', + reasoning: false, + input: ['text'], + contextWindow: 262000, + maxTokens: 262000, + cost: { + input: 0.14, + output: 1.4, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen.qwen3-vl-235b-a22b', + name: 'Qwen/Qwen3-VL-235B-A22B-Instruct', + config: { + api: 'bedrock-converse-stream', + reasoning: false, + input: ['text', 'image'], + contextWindow: 262000, + maxTokens: 262000, + cost: { + input: 0.3, + output: 1.5, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'us.anthropic.claude-fable-5', + name: 'Claude Fable 5 (US)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 10, + output: 50, + cacheRead: 1, + cacheWrite: 12.5, + }, + }, + }, + { + modelId: 'us.anthropic.claude-haiku-4-5-20251001-v1:0', + name: 'Claude Haiku 4.5 (US)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 64000, + cost: { + input: 1, + output: 5, + cacheRead: 0.1, + cacheWrite: 1.25, + }, + }, + }, + { + modelId: 'us.anthropic.claude-opus-4-1-20250805-v1:0', + name: 'Claude Opus 4.1 (US)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 32000, + cost: { + input: 15, + output: 75, + cacheRead: 1.5, + cacheWrite: 18.75, + }, + }, + }, + { + modelId: 'us.anthropic.claude-opus-4-5-20251101-v1:0', + name: 'Claude Opus 4.5 (US)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 64000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'us.anthropic.claude-opus-4-6-v1', + name: 'Claude Opus 4.6 (US)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'us.anthropic.claude-opus-4-7', + name: 'Claude Opus 4.7 (US)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'us.anthropic.claude-opus-4-8', + name: 'Claude Opus 4.8 (US)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'us.anthropic.claude-sonnet-4-5-20250929-v1:0', + name: 'Claude Sonnet 4.5 (US)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 64000, + cost: { + input: 3, + output: 15, + cacheRead: 0.3, + cacheWrite: 3.75, + }, + }, + }, + { + modelId: 'us.anthropic.claude-sonnet-4-6', + name: 'Claude Sonnet 4.6 (US)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 64000, + cost: { + input: 3, + output: 15, + cacheRead: 0.3, + cacheWrite: 3.75, + }, + }, + }, + { + modelId: 'us.anthropic.claude-sonnet-5', + name: 'Claude Sonnet 5 (US)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 2, + output: 10, + cacheRead: 0.2, + cacheWrite: 2.5, + }, + }, + }, + { + modelId: 'us.deepseek.r1-v1:0', + name: 'DeepSeek-R1 (US)', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text'], + contextWindow: 128000, + maxTokens: 32768, + cost: { + input: 1.35, + output: 5.4, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'us.meta.llama4-maverick-17b-instruct-v1:0', + name: 'Llama 4 Maverick 17B Instruct (US)', + config: { + api: 'bedrock-converse-stream', + reasoning: false, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 16384, + cost: { + input: 0.24, + output: 0.97, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'us.meta.llama4-scout-17b-instruct-v1:0', + name: 'Llama 4 Scout 17B Instruct (US)', + config: { + api: 'bedrock-converse-stream', + reasoning: false, + input: ['text', 'image'], + contextWindow: 3500000, + maxTokens: 16384, + cost: { + input: 0.17, + output: 0.66, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'writer.palmyra-x4-v1:0', + name: 'Palmyra X4', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text'], + contextWindow: 122880, + maxTokens: 8192, + cost: { + input: 2.5, + output: 10, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'writer.palmyra-x5-v1:0', + name: 'Palmyra X5', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text'], + contextWindow: 1040000, + maxTokens: 8192, + cost: { + input: 0.6, + output: 6, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'xai.grok-4.3', + name: 'Grok 4.3', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 131072, + cost: { + input: 1.25, + output: 2.5, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'zai.glm-4.7', + name: 'GLM-4.7', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text'], + contextWindow: 204800, + maxTokens: 131072, + cost: { + input: 0.6, + output: 2.2, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'zai.glm-4.7-flash', + name: 'GLM-4.7-Flash', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text'], + contextWindow: 200000, + maxTokens: 131072, + cost: { + input: 0.07, + output: 0.4, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'zai.glm-5', + name: 'GLM-5', + config: { + api: 'bedrock-converse-stream', + reasoning: true, + input: ['text'], + contextWindow: 202752, + maxTokens: 101376, + cost: { + input: 1, + output: 3.2, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + ], +} as const diff --git a/packages/core/src/generated/providers/ant-ling.ts b/packages/core/src/generated/providers/ant-ling.ts new file mode 100644 index 00000000..29591ed8 --- /dev/null +++ b/packages/core/src/generated/providers/ant-ling.ts @@ -0,0 +1,65 @@ +// This file is auto-generated by scripts/generate-builtin-providers.ts +// Do not edit manually - run 'bun run generate-providers' to update + +export const providerName = 'ant-ling' +export const providerConfig = { + name: 'ant-ling', + config: { + api: 'openai-completions', + baseUrl: 'https://api.ant-ling.com/v1', + apiKey: '', + }, + models: [ + { + modelId: 'Ling-2.6-1T', + name: 'Ling 2.6 1T', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 262144, + maxTokens: 65536, + cost: { + input: 0.06, + output: 0.25, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'Ling-2.6-flash', + name: 'Ling 2.6 Flash', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 262144, + maxTokens: 65536, + cost: { + input: 0.01, + output: 0.02, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'Ring-2.6-1T', + name: 'Ring 2.6 1T', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 262144, + maxTokens: 65536, + cost: { + input: 0.06, + output: 0.25, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + ], +} as const diff --git a/packages/core/src/generated/providers/anthropic.ts b/packages/core/src/generated/providers/anthropic.ts new file mode 100644 index 00000000..ad1353b6 --- /dev/null +++ b/packages/core/src/generated/providers/anthropic.ts @@ -0,0 +1,252 @@ +// This file is auto-generated by scripts/generate-builtin-providers.ts +// Do not edit manually - run 'bun run generate-providers' to update + +export const providerName = 'anthropic' +export const providerConfig = { + name: 'anthropic', + config: { + api: 'anthropic-messages', + baseUrl: 'https://api.anthropic.com', + apiKey: 'ANTHROPIC_API_KEY', + }, + models: [ + { + modelId: 'claude-fable-5', + name: 'Claude Fable 5', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 10, + output: 50, + cacheRead: 1, + cacheWrite: 12.5, + }, + }, + }, + { + modelId: 'claude-haiku-4-5', + name: 'Claude Haiku 4.5 (latest)', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 64000, + cost: { + input: 1, + output: 5, + cacheRead: 0.1, + cacheWrite: 1.25, + }, + }, + }, + { + modelId: 'claude-haiku-4-5-20251001', + name: 'Claude Haiku 4.5', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 64000, + cost: { + input: 1, + output: 5, + cacheRead: 0.1, + cacheWrite: 1.25, + }, + }, + }, + { + modelId: 'claude-opus-4-1', + name: 'Claude Opus 4.1 (latest)', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 32000, + cost: { + input: 15, + output: 75, + cacheRead: 1.5, + cacheWrite: 18.75, + }, + }, + }, + { + modelId: 'claude-opus-4-1-20250805', + name: 'Claude Opus 4.1', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 32000, + cost: { + input: 15, + output: 75, + cacheRead: 1.5, + cacheWrite: 18.75, + }, + }, + }, + { + modelId: 'claude-opus-4-5', + name: 'Claude Opus 4.5 (latest)', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 64000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'claude-opus-4-5-20251101', + name: 'Claude Opus 4.5', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 64000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'claude-opus-4-6', + name: 'Claude Opus 4.6', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'claude-opus-4-7', + name: 'Claude Opus 4.7', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'claude-opus-4-8', + name: 'Claude Opus 4.8', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'claude-sonnet-4-5', + name: 'Claude Sonnet 4.5 (latest)', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 64000, + cost: { + input: 3, + output: 15, + cacheRead: 0.3, + cacheWrite: 3.75, + }, + }, + }, + { + modelId: 'claude-sonnet-4-5-20250929', + name: 'Claude Sonnet 4.5', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 64000, + cost: { + input: 3, + output: 15, + cacheRead: 0.3, + cacheWrite: 3.75, + }, + }, + }, + { + modelId: 'claude-sonnet-4-6', + name: 'Claude Sonnet 4.6', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 3, + output: 15, + cacheRead: 0.3, + cacheWrite: 3.75, + }, + }, + }, + { + modelId: 'claude-sonnet-5', + name: 'Claude Sonnet 5', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 2, + output: 10, + cacheRead: 0.2, + cacheWrite: 2.5, + }, + }, + }, + ], +} as const diff --git a/packages/core/src/generated/providers/azure-openai-responses.ts b/packages/core/src/generated/providers/azure-openai-responses.ts new file mode 100644 index 00000000..a824b304 --- /dev/null +++ b/packages/core/src/generated/providers/azure-openai-responses.ts @@ -0,0 +1,796 @@ +// This file is auto-generated by scripts/generate-builtin-providers.ts +// Do not edit manually - run 'bun run generate-providers' to update + +export const providerName = 'azure-openai-responses' +export const providerConfig = { + name: 'azure-openai-responses', + config: { + api: 'azure-openai-responses', + baseUrl: '', + apiKey: 'AZURE_OPENAI_API_KEY', + }, + models: [ + { + modelId: 'gpt-4', + name: 'GPT-4', + config: { + api: 'azure-openai-responses', + reasoning: false, + input: ['text'], + contextWindow: 8192, + maxTokens: 8192, + cost: { + input: 30, + output: 60, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-4-turbo', + name: 'GPT-4 Turbo', + config: { + api: 'azure-openai-responses', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 4096, + cost: { + input: 10, + output: 30, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-4.1', + name: 'GPT-4.1', + config: { + api: 'azure-openai-responses', + reasoning: false, + input: ['text', 'image'], + contextWindow: 1047576, + maxTokens: 32768, + cost: { + input: 2, + output: 8, + cacheRead: 0.5, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-4.1-mini', + name: 'GPT-4.1 mini', + config: { + api: 'azure-openai-responses', + reasoning: false, + input: ['text', 'image'], + contextWindow: 1047576, + maxTokens: 32768, + cost: { + input: 0.4, + output: 1.6, + cacheRead: 0.1, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-4.1-nano', + name: 'GPT-4.1 nano', + config: { + api: 'azure-openai-responses', + reasoning: false, + input: ['text', 'image'], + contextWindow: 1047576, + maxTokens: 32768, + cost: { + input: 0.1, + output: 0.4, + cacheRead: 0.025, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-4o', + name: 'GPT-4o', + config: { + api: 'azure-openai-responses', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 2.5, + output: 10, + cacheRead: 1.25, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-4o-2024-05-13', + name: 'GPT-4o (2024-05-13)', + config: { + api: 'azure-openai-responses', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 4096, + cost: { + input: 5, + output: 15, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-4o-2024-08-06', + name: 'GPT-4o (2024-08-06)', + config: { + api: 'azure-openai-responses', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 2.5, + output: 10, + cacheRead: 1.25, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-4o-2024-11-20', + name: 'GPT-4o (2024-11-20)', + config: { + api: 'azure-openai-responses', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 2.5, + output: 10, + cacheRead: 1.25, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-4o-mini', + name: 'GPT-4o mini', + config: { + api: 'azure-openai-responses', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 0.15, + output: 0.6, + cacheRead: 0.075, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5', + name: 'GPT-5', + config: { + api: 'azure-openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.25, + output: 10, + cacheRead: 0.125, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5-chat-latest', + name: 'GPT-5 Chat Latest', + config: { + api: 'azure-openai-responses', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 1.25, + output: 10, + cacheRead: 0.125, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5-codex', + name: 'GPT-5-Codex', + config: { + api: 'azure-openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.25, + output: 10, + cacheRead: 0.125, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5-mini', + name: 'GPT-5 Mini', + config: { + api: 'azure-openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 0.25, + output: 2, + cacheRead: 0.025, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5-nano', + name: 'GPT-5 Nano', + config: { + api: 'azure-openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 0.05, + output: 0.4, + cacheRead: 0.005, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5-pro', + name: 'GPT-5 Pro', + config: { + api: 'azure-openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 15, + output: 120, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.1', + name: 'GPT-5.1', + config: { + api: 'azure-openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.25, + output: 10, + cacheRead: 0.125, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.1-chat-latest', + name: 'GPT-5.1 Chat', + config: { + api: 'azure-openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 1.25, + output: 10, + cacheRead: 0.125, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.1-codex', + name: 'GPT-5.1 Codex', + config: { + api: 'azure-openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.25, + output: 10, + cacheRead: 0.125, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.1-codex-max', + name: 'GPT-5.1 Codex Max', + config: { + api: 'azure-openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.25, + output: 10, + cacheRead: 0.125, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.1-codex-mini', + name: 'GPT-5.1 Codex mini', + config: { + api: 'azure-openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 0.25, + output: 2, + cacheRead: 0.025, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.2', + name: 'GPT-5.2', + config: { + api: 'azure-openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.75, + output: 14, + cacheRead: 0.175, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.2-chat-latest', + name: 'GPT-5.2 Chat', + config: { + api: 'azure-openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 1.75, + output: 14, + cacheRead: 0.175, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.2-codex', + name: 'GPT-5.2 Codex', + config: { + api: 'azure-openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.75, + output: 14, + cacheRead: 0.175, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.2-pro', + name: 'GPT-5.2 Pro', + config: { + api: 'azure-openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 21, + output: 168, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.3-chat-latest', + name: 'GPT-5.3 Chat (latest)', + config: { + api: 'azure-openai-responses', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 1.75, + output: 14, + cacheRead: 0.175, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.3-codex', + name: 'GPT-5.3 Codex', + config: { + api: 'azure-openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.75, + output: 14, + cacheRead: 0.175, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.3-codex-spark', + name: 'GPT-5.3 Codex Spark', + config: { + api: 'azure-openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 32000, + cost: { + input: 1.75, + output: 14, + cacheRead: 0.175, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.4', + name: 'GPT-5.4', + config: { + api: 'azure-openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 128000, + cost: { + input: 2.5, + output: 15, + cacheRead: 0.25, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.4-mini', + name: 'GPT-5.4 mini', + config: { + api: 'azure-openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 0.75, + output: 4.5, + cacheRead: 0.075, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.4-nano', + name: 'GPT-5.4 nano', + config: { + api: 'azure-openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 0.2, + output: 1.25, + cacheRead: 0.02, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.4-pro', + name: 'GPT-5.4 Pro', + config: { + api: 'azure-openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 128000, + cost: { + input: 30, + output: 180, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.5', + name: 'GPT-5.5', + config: { + api: 'azure-openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 128000, + cost: { + input: 5, + output: 30, + cacheRead: 0.5, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.5-pro', + name: 'GPT-5.5 Pro', + config: { + api: 'azure-openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 128000, + cost: { + input: 30, + output: 180, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.6-luna', + name: 'GPT-5.6 Luna', + config: { + api: 'azure-openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 128000, + cost: { + input: 1, + output: 6, + cacheRead: 0.1, + cacheWrite: 1.25, + }, + }, + }, + { + modelId: 'gpt-5.6-sol', + name: 'GPT-5.6 Sol', + config: { + api: 'azure-openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 128000, + cost: { + input: 5, + output: 30, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'gpt-5.6-terra', + name: 'GPT-5.6 Terra', + config: { + api: 'azure-openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 128000, + cost: { + input: 2.5, + output: 15, + cacheRead: 0.25, + cacheWrite: 3.125, + }, + }, + }, + { + modelId: 'gpt-realtime-2.1', + name: 'GPT-Realtime-2.1', + config: { + api: 'azure-openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 32000, + cost: { + input: 4, + output: 24, + cacheRead: 0.4, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'o1', + name: 'o1', + config: { + api: 'azure-openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 100000, + cost: { + input: 15, + output: 60, + cacheRead: 7.5, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'o1-pro', + name: 'o1-pro', + config: { + api: 'azure-openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 100000, + cost: { + input: 150, + output: 600, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'o3', + name: 'o3', + config: { + api: 'azure-openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 100000, + cost: { + input: 2, + output: 8, + cacheRead: 0.5, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'o3-deep-research', + name: 'o3-deep-research', + config: { + api: 'azure-openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 100000, + cost: { + input: 10, + output: 40, + cacheRead: 2.5, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'o3-mini', + name: 'o3-mini', + config: { + api: 'azure-openai-responses', + reasoning: true, + input: ['text'], + contextWindow: 200000, + maxTokens: 100000, + cost: { + input: 1.1, + output: 4.4, + cacheRead: 0.55, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'o3-pro', + name: 'o3-pro', + config: { + api: 'azure-openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 100000, + cost: { + input: 20, + output: 80, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'o4-mini', + name: 'o4-mini', + config: { + api: 'azure-openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 100000, + cost: { + input: 1.1, + output: 4.4, + cacheRead: 0.275, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'o4-mini-deep-research', + name: 'o4-mini-deep-research', + config: { + api: 'azure-openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 100000, + cost: { + input: 2, + output: 8, + cacheRead: 0.5, + cacheWrite: 0, + }, + }, + }, + ], +} as const diff --git a/packages/core/src/generated/providers/cerebras.ts b/packages/core/src/generated/providers/cerebras.ts new file mode 100644 index 00000000..3615bfa7 --- /dev/null +++ b/packages/core/src/generated/providers/cerebras.ts @@ -0,0 +1,65 @@ +// This file is auto-generated by scripts/generate-builtin-providers.ts +// Do not edit manually - run 'bun run generate-providers' to update + +export const providerName = 'cerebras' +export const providerConfig = { + name: 'cerebras', + config: { + api: 'openai-completions', + baseUrl: 'https://api.cerebras.ai/v1', + apiKey: 'CEREBRAS_API_KEY', + }, + models: [ + { + modelId: 'gemma-4-31b', + name: 'Gemma 4 31B IT', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 131072, + maxTokens: 40960, + cost: { + input: 0.99, + output: 1.49, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-oss-120b', + name: 'GPT OSS 120B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 40960, + cost: { + input: 0.35, + output: 0.75, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'zai-glm-4.7', + name: 'Z.AI GLM-4.7', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 40960, + cost: { + input: 2.25, + output: 2.75, + cacheRead: 2.25, + cacheWrite: 0, + }, + }, + }, + ], +} as const diff --git a/packages/core/src/generated/providers/cloudflare-ai-gateway.ts b/packages/core/src/generated/providers/cloudflare-ai-gateway.ts new file mode 100644 index 00000000..b1498fc7 --- /dev/null +++ b/packages/core/src/generated/providers/cloudflare-ai-gateway.ts @@ -0,0 +1,729 @@ +// This file is auto-generated by scripts/generate-builtin-providers.ts +// Do not edit manually - run 'bun run generate-providers' to update + +export const providerName = 'cloudflare-ai-gateway' +export const providerConfig = { + name: 'cloudflare-ai-gateway', + config: { + api: 'anthropic-messages', + baseUrl: + 'https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic', + apiKey: 'CLOUDFLARE_API_KEY', + }, + models: [ + { + modelId: 'claude-3-5-haiku', + name: 'Claude Haiku 3.5 (latest)', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 8192, + cost: { + input: 0.8, + output: 4, + cacheRead: 0.08, + cacheWrite: 1, + }, + }, + }, + { + modelId: 'claude-3-haiku', + name: 'Claude Haiku 3', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 4096, + cost: { + input: 0.25, + output: 1.25, + cacheRead: 0.03, + cacheWrite: 0.3, + }, + }, + }, + { + modelId: 'claude-3-opus', + name: 'Claude Opus 3', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 4096, + cost: { + input: 15, + output: 75, + cacheRead: 1.5, + cacheWrite: 18.75, + }, + }, + }, + { + modelId: 'claude-3-sonnet', + name: 'Claude Sonnet 3', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 4096, + cost: { + input: 3, + output: 15, + cacheRead: 0.3, + cacheWrite: 0.3, + }, + }, + }, + { + modelId: 'claude-3.5-haiku', + name: 'Claude Haiku 3.5 (latest)', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 8192, + cost: { + input: 0.8, + output: 4, + cacheRead: 0.08, + cacheWrite: 1, + }, + }, + }, + { + modelId: 'claude-3.5-sonnet', + name: 'Claude Sonnet 3.5 v2', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 8192, + cost: { + input: 3, + output: 15, + cacheRead: 0.3, + cacheWrite: 3.75, + }, + }, + }, + { + modelId: 'claude-fable-5', + name: 'Claude Fable 5', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 10, + output: 50, + cacheRead: 1, + cacheWrite: 12.5, + }, + }, + }, + { + modelId: 'claude-haiku-4-5', + name: 'Claude Haiku 4.5 (latest)', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 64000, + cost: { + input: 1, + output: 5, + cacheRead: 0.1, + cacheWrite: 1.25, + }, + }, + }, + { + modelId: 'claude-opus-4', + name: 'Claude Opus 4 (latest)', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 32000, + cost: { + input: 15, + output: 75, + cacheRead: 1.5, + cacheWrite: 18.75, + }, + }, + }, + { + modelId: 'claude-opus-4-1', + name: 'Claude Opus 4.1 (latest)', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 32000, + cost: { + input: 15, + output: 75, + cacheRead: 1.5, + cacheWrite: 18.75, + }, + }, + }, + { + modelId: 'claude-opus-4-5', + name: 'Claude Opus 4.5 (latest)', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 64000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'claude-opus-4-6', + name: 'Claude Opus 4.6 (latest)', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'claude-opus-4-7', + name: 'Claude Opus 4.7', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'claude-opus-4-8', + name: 'Claude Opus 4.8', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'claude-sonnet-4', + name: 'Claude Sonnet 4 (latest)', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 64000, + cost: { + input: 3, + output: 15, + cacheRead: 0.3, + cacheWrite: 3.75, + }, + }, + }, + { + modelId: 'claude-sonnet-4-5', + name: 'Claude Sonnet 4.5 (latest)', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 64000, + cost: { + input: 3, + output: 15, + cacheRead: 0.3, + cacheWrite: 3.75, + }, + }, + }, + { + modelId: 'claude-sonnet-4-6', + name: 'Claude Sonnet 4.6', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 64000, + cost: { + input: 3, + output: 15, + cacheRead: 0.3, + cacheWrite: 3.75, + }, + }, + }, + { + modelId: 'claude-sonnet-5', + name: 'Claude Sonnet 5', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 2, + output: 10, + cacheRead: 0.2, + cacheWrite: 2.5, + }, + }, + }, + { + modelId: 'gpt-4', + name: 'GPT-4', + config: { + api: 'openai-responses', + reasoning: false, + input: ['text'], + contextWindow: 8192, + maxTokens: 8192, + cost: { + input: 30, + output: 60, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-4-turbo', + name: 'GPT-4 Turbo', + config: { + api: 'openai-responses', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 4096, + cost: { + input: 10, + output: 30, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-4o', + name: 'GPT-4o', + config: { + api: 'openai-responses', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 2.5, + output: 10, + cacheRead: 1.25, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-4o-mini', + name: 'GPT-4o mini', + config: { + api: 'openai-responses', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 0.15, + output: 0.6, + cacheRead: 0.08, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.1', + name: 'GPT-5.1', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.25, + output: 10, + cacheRead: 0.13, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.1-codex', + name: 'GPT-5.1 Codex', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.25, + output: 10, + cacheRead: 0.125, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.2', + name: 'GPT-5.2', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.75, + output: 14, + cacheRead: 0.175, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.2-codex', + name: 'GPT-5.2 Codex', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.75, + output: 14, + cacheRead: 0.175, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.3-codex', + name: 'GPT-5.3 Codex', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.75, + output: 14, + cacheRead: 0.175, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.4', + name: 'GPT-5.4', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 128000, + cost: { + input: 2.5, + output: 15, + cacheRead: 0.25, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.5', + name: 'GPT-5.5', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 128000, + cost: { + input: 5, + output: 30, + cacheRead: 0.5, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.6-luna', + name: 'GPT-5.6 Luna', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 128000, + cost: { + input: 1, + output: 6, + cacheRead: 0.1, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.6-sol', + name: 'GPT-5.6 Sol', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 128000, + cost: { + input: 5, + output: 30, + cacheRead: 0.5, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.6-terra', + name: 'GPT-5.6 Terra', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 128000, + cost: { + input: 2.5, + output: 15, + cacheRead: 0.25, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'o1', + name: 'o1', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 100000, + cost: { + input: 15, + output: 60, + cacheRead: 7.5, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'o3', + name: 'o3', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 100000, + cost: { + input: 2, + output: 8, + cacheRead: 0.5, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'o3-mini', + name: 'o3-mini', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text'], + contextWindow: 200000, + maxTokens: 100000, + cost: { + input: 1.1, + output: 4.4, + cacheRead: 0.55, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'o3-pro', + name: 'o3-pro', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 100000, + cost: { + input: 20, + output: 80, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'o4-mini', + name: 'o4-mini', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 100000, + cost: { + input: 1.1, + output: 4.4, + cacheRead: 0.28, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'workers-ai/@cf/moonshotai/kimi-k2.5', + name: 'Kimi K2.5', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 256000, + maxTokens: 256000, + cost: { + input: 0.6, + output: 3, + cacheRead: 0.1, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'workers-ai/@cf/moonshotai/kimi-k2.6', + name: 'Kimi K2.6', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 256000, + maxTokens: 256000, + cost: { + input: 0.95, + output: 4, + cacheRead: 0.16, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'workers-ai/@cf/nvidia/nemotron-3-120b-a12b', + name: 'Nemotron 3 Super 120B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 256000, + maxTokens: 256000, + cost: { + input: 0.5, + output: 1.5, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'workers-ai/@cf/zai-org/glm-4.7-flash', + name: 'GLM-4.7-Flash', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 131072, + cost: { + input: 0.06, + output: 0.4, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'workers-ai/@cf/zai-org/glm-5.2', + name: 'Glm 5.2', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 1.4, + output: 4.4, + cacheRead: 0.26, + cacheWrite: 0, + }, + }, + }, + ], +} as const diff --git a/packages/core/src/generated/providers/cloudflare-workers-ai.ts b/packages/core/src/generated/providers/cloudflare-workers-ai.ts new file mode 100644 index 00000000..6741bf3a --- /dev/null +++ b/packages/core/src/generated/providers/cloudflare-workers-ai.ts @@ -0,0 +1,235 @@ +// This file is auto-generated by scripts/generate-builtin-providers.ts +// Do not edit manually - run 'bun run generate-providers' to update + +export const providerName = 'cloudflare-workers-ai' +export const providerConfig = { + name: 'cloudflare-workers-ai', + config: { + api: 'openai-completions', + baseUrl: 'https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1', + apiKey: 'CLOUDFLARE_API_KEY', + }, + models: [ + { + modelId: '@cf/google/gemma-4-26b-a4b-it', + name: 'Gemma 4 26B A4B IT', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 256000, + maxTokens: 16384, + cost: { + input: 0.1, + output: 0.3, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: '@cf/ibm-granite/granite-4.0-h-micro', + name: 'Granite 4.0 H Micro', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 131000, + maxTokens: 131000, + cost: { + input: 0.017, + output: 0.112, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: '@cf/meta/llama-3.3-70b-instruct-fp8-fast', + name: 'Llama 3.3 70B Instruct fp8 Fast', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 24000, + maxTokens: 24000, + cost: { + input: 0.293, + output: 2.253, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: '@cf/meta/llama-4-scout-17b-16e-instruct', + name: 'Llama 4 Scout 17B 16E Instruct', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 131000, + maxTokens: 16384, + cost: { + input: 0.27, + output: 0.85, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: '@cf/mistralai/mistral-small-3.1-24b-instruct', + name: 'Mistral Small 3.1 24B Instruct', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 128000, + maxTokens: 128000, + cost: { + input: 0.351, + output: 0.555, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: '@cf/moonshotai/kimi-k2.6', + name: 'Kimi K2.6', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 256000, + cost: { + input: 0.95, + output: 4, + cacheRead: 0.16, + cacheWrite: 0, + }, + }, + }, + { + modelId: '@cf/moonshotai/kimi-k2.7-code', + name: 'Kimi K2.7 Code', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0.95, + output: 4, + cacheRead: 0.19, + cacheWrite: 0, + }, + }, + }, + { + modelId: '@cf/nvidia/nemotron-3-120b-a12b', + name: 'Nemotron 3 Super 120B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 256000, + maxTokens: 256000, + cost: { + input: 0.5, + output: 1.5, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: '@cf/openai/gpt-oss-120b', + name: 'GPT OSS 120B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 0.35, + output: 0.75, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: '@cf/openai/gpt-oss-20b', + name: 'GPT OSS 20B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 0.2, + output: 0.3, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: '@cf/qwen/qwen3-30b-a3b-fp8', + name: 'Qwen3 30B A3b fp8', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 32768, + maxTokens: 32768, + cost: { + input: 0.0509, + output: 0.335, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: '@cf/zai-org/glm-4.7-flash', + name: 'GLM-4.7-Flash', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 131072, + cost: { + input: 0.0605, + output: 0.4, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: '@cf/zai-org/glm-5.2', + name: 'Glm 5.2', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 1.4, + output: 4.4, + cacheRead: 0.26, + cacheWrite: 0, + }, + }, + }, + ], +} as const diff --git a/packages/core/src/generated/providers/deepseek.ts b/packages/core/src/generated/providers/deepseek.ts new file mode 100644 index 00000000..faaaee01 --- /dev/null +++ b/packages/core/src/generated/providers/deepseek.ts @@ -0,0 +1,48 @@ +// This file is auto-generated by scripts/generate-builtin-providers.ts +// Do not edit manually - run 'bun run generate-providers' to update + +export const providerName = 'deepseek' +export const providerConfig = { + name: 'deepseek', + config: { + api: 'openai-completions', + baseUrl: 'https://api.deepseek.com', + apiKey: 'DEEPSEEK_API_KEY', + }, + models: [ + { + modelId: 'deepseek-v4-flash', + name: 'DeepSeek V4 Flash', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1000000, + maxTokens: 384000, + cost: { + input: 0.14, + output: 0.28, + cacheRead: 0.0028, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'deepseek-v4-pro', + name: 'DeepSeek V4 Pro', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1000000, + maxTokens: 384000, + cost: { + input: 0.435, + output: 0.87, + cacheRead: 0.003625, + cacheWrite: 0, + }, + }, + }, + ], +} as const diff --git a/packages/core/src/generated/providers/fireworks.ts b/packages/core/src/generated/providers/fireworks.ts new file mode 100644 index 00000000..fcff4138 --- /dev/null +++ b/packages/core/src/generated/providers/fireworks.ts @@ -0,0 +1,286 @@ +// This file is auto-generated by scripts/generate-builtin-providers.ts +// Do not edit manually - run 'bun run generate-providers' to update + +export const providerName = 'fireworks' +export const providerConfig = { + name: 'fireworks', + config: { + api: 'anthropic-messages', + baseUrl: 'https://api.fireworks.ai/inference', + apiKey: 'FIREWORKS_API_KEY', + }, + models: [ + { + modelId: 'accounts/fireworks/models/deepseek-v4-flash', + name: 'DeepSeek V4 Flash', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 1000000, + maxTokens: 384000, + cost: { + input: 0.14, + output: 0.28, + cacheRead: 0.028, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'accounts/fireworks/models/deepseek-v4-pro', + name: 'DeepSeek V4 Pro', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 1000000, + maxTokens: 384000, + cost: { + input: 1.74, + output: 3.48, + cacheRead: 0.145, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'accounts/fireworks/models/glm-5p1', + name: 'GLM 5.1', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 202800, + maxTokens: 131072, + cost: { + input: 1.4, + output: 4.4, + cacheRead: 0.26, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'accounts/fireworks/models/glm-5p2', + name: 'GLM 5.2', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1048575, + maxTokens: 131072, + cost: { + input: 1.4, + output: 4.4, + cacheRead: 0.14, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'accounts/fireworks/models/gpt-oss-120b', + name: 'GPT OSS 120B', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 32768, + cost: { + input: 0.15, + output: 0.6, + cacheRead: 0.015, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'accounts/fireworks/models/gpt-oss-20b', + name: 'GPT OSS 20B', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 32768, + cost: { + input: 0.07, + output: 0.3, + cacheRead: 0.035, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'accounts/fireworks/models/kimi-k2p6', + name: 'Kimi K2.6', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262000, + maxTokens: 262000, + cost: { + input: 0.95, + output: 4, + cacheRead: 0.16, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'accounts/fireworks/models/kimi-k2p7-code', + name: 'Kimi K2.7 Code', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262000, + maxTokens: 262000, + cost: { + input: 0.95, + output: 4, + cacheRead: 0.19, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'accounts/fireworks/models/minimax-m2p7', + name: 'MiniMax-M2.7', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 196608, + maxTokens: 196608, + cost: { + input: 0.3, + output: 1.2, + cacheRead: 0.06, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'accounts/fireworks/models/minimax-m3', + name: 'MiniMax-M3', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 512000, + maxTokens: 512000, + cost: { + input: 0.3, + output: 1.2, + cacheRead: 0.06, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'accounts/fireworks/models/qwen3p7-plus', + name: 'Qwen 3.7 Plus', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 65536, + cost: { + input: 0.4, + output: 1.6, + cacheRead: 0.08, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'accounts/fireworks/routers/glm-5p1-fast', + name: 'GLM 5.1 Fast', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 202800, + maxTokens: 131072, + cost: { + input: 2.8, + output: 8.8, + cacheRead: 0.52, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'accounts/fireworks/routers/glm-5p2-fast', + name: 'GLM 5.2 Fast', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1048575, + maxTokens: 131072, + cost: { + input: 2.1, + output: 6.6, + cacheRead: 0.21, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'accounts/fireworks/routers/kimi-k2p6-fast', + name: 'Kimi K2.6 Fast', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262000, + maxTokens: 262000, + cost: { + input: 2, + output: 8, + cacheRead: 0.3, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'accounts/fireworks/routers/kimi-k2p6-turbo', + name: 'Kimi K2.6 Turbo', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262000, + maxTokens: 262000, + cost: { + input: 2, + output: 8, + cacheRead: 0.3, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'accounts/fireworks/routers/kimi-k2p7-code-fast', + name: 'Kimi K2.7 Code Fast', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262000, + maxTokens: 262000, + cost: { + input: 1.9, + output: 8, + cacheRead: 0.38, + cacheWrite: 0, + }, + }, + }, + ], +} as const diff --git a/packages/core/src/generated/providers/github-copilot.ts b/packages/core/src/generated/providers/github-copilot.ts new file mode 100644 index 00000000..21c4e2ff --- /dev/null +++ b/packages/core/src/generated/providers/github-copilot.ts @@ -0,0 +1,544 @@ +// This file is auto-generated by scripts/generate-builtin-providers.ts +// Do not edit manually - run 'bun run generate-providers' to update + +export const providerName = 'github-copilot' +export const providerConfig = { + name: 'github-copilot', + config: { + api: 'openai-completions', + baseUrl: 'https://api.individual.githubcopilot.com', + apiKey: 'COPILOT_GITHUB_TOKEN', + }, + models: [ + { + modelId: 'claude-fable-5', + name: 'Claude Fable 5', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 10, + output: 50, + cacheRead: 1, + cacheWrite: 12.5, + }, + }, + }, + { + modelId: 'claude-haiku-4.5', + name: 'Claude Haiku 4.5 (latest)', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 64000, + cost: { + input: 1, + output: 5, + cacheRead: 0.1, + cacheWrite: 1.25, + }, + }, + }, + { + modelId: 'claude-opus-4.5', + name: 'Claude Opus 4.5 (latest)', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 32000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'claude-opus-4.6', + name: 'Claude Opus 4.6', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 32000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'claude-opus-4.7', + name: 'Claude Opus 4.7', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 32000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'claude-opus-4.8', + name: 'Claude Opus 4.8', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 64000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'claude-sonnet-4', + name: 'Claude Sonnet 4 (latest)', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 216000, + maxTokens: 16000, + cost: { + input: 3, + output: 15, + cacheRead: 0.3, + cacheWrite: 3.75, + }, + }, + }, + { + modelId: 'claude-sonnet-4.5', + name: 'Claude Sonnet 4.5 (latest)', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 32000, + cost: { + input: 3, + output: 15, + cacheRead: 0.3, + cacheWrite: 3.75, + }, + }, + }, + { + modelId: 'claude-sonnet-4.6', + name: 'Claude Sonnet 4.6', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 32000, + cost: { + input: 3, + output: 15, + cacheRead: 0.3, + cacheWrite: 3.75, + }, + }, + }, + { + modelId: 'claude-sonnet-5', + name: 'Claude Sonnet 5', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 2, + output: 10, + cacheRead: 0.2, + cacheWrite: 2.5, + }, + }, + }, + { + modelId: 'gemini-2.5-pro', + name: 'Gemini 2.5 Pro', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 64000, + cost: { + input: 1.25, + output: 10, + cacheRead: 0.125, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gemini-3-flash-preview', + name: 'Gemini 3 Flash Preview', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 64000, + cost: { + input: 0.5, + output: 3, + cacheRead: 0.05, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gemini-3.1-pro-preview', + name: 'Gemini 3.1 Pro Preview', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 64000, + cost: { + input: 2, + output: 12, + cacheRead: 0.2, + cacheWrite: 0, + tiers: [ + { + inputTokensAbove: 200000, + input: 4, + output: 18, + cacheRead: 0.4, + cacheWrite: 0, + }, + ], + }, + }, + }, + { + modelId: 'gemini-3.5-flash', + name: 'Gemini 3.5 Flash', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 64000, + cost: { + input: 1.5, + output: 9, + cacheRead: 0.15, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-4.1', + name: 'GPT-4.1', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 2, + output: 8, + cacheRead: 0.5, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5-mini', + name: 'GPT-5 Mini', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 264000, + maxTokens: 64000, + cost: { + input: 0.25, + output: 2, + cacheRead: 0.025, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.2', + name: 'GPT-5.2', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.75, + output: 14, + cacheRead: 0.175, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.2-codex', + name: 'GPT-5.2 Codex', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.75, + output: 14, + cacheRead: 0.175, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.3-codex', + name: 'GPT-5.3 Codex', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 1.75, + output: 14, + cacheRead: 0.175, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.4', + name: 'GPT-5.4', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 2.5, + output: 15, + cacheRead: 0.25, + cacheWrite: 0, + tiers: [ + { + inputTokensAbove: 272000, + input: 5, + output: 22.5, + cacheRead: 0.5, + cacheWrite: 0, + }, + ], + }, + }, + }, + { + modelId: 'gpt-5.4-mini', + name: 'GPT-5.4 mini', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 0.75, + output: 4.5, + cacheRead: 0.075, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.4-nano', + name: 'GPT-5.4 nano', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 0.2, + output: 1.25, + cacheRead: 0.02, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.5', + name: 'GPT-5.5', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 5, + output: 30, + cacheRead: 0.5, + cacheWrite: 0, + tiers: [ + { + inputTokensAbove: 272000, + input: 10, + output: 45, + cacheRead: 1, + cacheWrite: 0, + }, + ], + }, + }, + }, + { + modelId: 'gpt-5.6-luna', + name: 'GPT-5.6 Luna', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 128000, + cost: { + input: 1, + output: 6, + cacheRead: 0.1, + cacheWrite: 1.25, + tiers: [ + { + inputTokensAbove: 200000, + input: 2, + output: 9, + cacheRead: 0.2, + cacheWrite: 2.5, + }, + ], + }, + }, + }, + { + modelId: 'gpt-5.6-sol', + name: 'GPT-5.6 Sol', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 128000, + cost: { + input: 5, + output: 30, + cacheRead: 0.5, + cacheWrite: 6.25, + tiers: [ + { + inputTokensAbove: 272000, + input: 10, + output: 45, + cacheRead: 1, + cacheWrite: 12.5, + }, + ], + }, + }, + }, + { + modelId: 'gpt-5.6-terra', + name: 'GPT-5.6 Terra', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 128000, + cost: { + input: 2.5, + output: 15, + cacheRead: 0.25, + cacheWrite: 3.125, + tiers: [ + { + inputTokensAbove: 272000, + input: 5, + output: 22.5, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + ], + }, + }, + }, + { + modelId: 'kimi-k2.7-code', + name: 'Kimi K2.7 Code', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 256000, + maxTokens: 32000, + cost: { + input: 0.95, + output: 4, + cacheRead: 0.19, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mai-code-1-flash-picker', + name: 'MAI-Code-1-Flash', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text'], + contextWindow: 256000, + maxTokens: 128000, + cost: { + input: 0.75, + output: 4.5, + cacheRead: 0.075, + cacheWrite: 0, + }, + }, + }, + ], +} as const diff --git a/packages/core/src/generated/providers/google-vertex.ts b/packages/core/src/generated/providers/google-vertex.ts new file mode 100644 index 00000000..7535a415 --- /dev/null +++ b/packages/core/src/generated/providers/google-vertex.ts @@ -0,0 +1,184 @@ +// This file is auto-generated by scripts/generate-builtin-providers.ts +// Do not edit manually - run 'bun run generate-providers' to update + +export const providerName = 'google-vertex' +export const providerConfig = { + name: 'google-vertex', + config: { + api: 'google-vertex', + baseUrl: 'https://{location}-aiplatform.googleapis.com', + apiKey: 'GOOGLE_CLOUD_API_KEY', + }, + models: [ + { + modelId: 'gemini-2.5-flash', + name: 'Gemini 2.5 Flash', + config: { + api: 'google-vertex', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 0.3, + output: 2.5, + cacheRead: 0.03, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gemini-2.5-flash-lite', + name: 'Gemini 2.5 Flash-Lite', + config: { + api: 'google-vertex', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 0.1, + output: 0.4, + cacheRead: 0.01, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gemini-2.5-pro', + name: 'Gemini 2.5 Pro', + config: { + api: 'google-vertex', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 1.25, + output: 10, + cacheRead: 0.125, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gemini-3-flash-preview', + name: 'Gemini 3 Flash Preview', + config: { + api: 'google-vertex', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 0.5, + output: 3, + cacheRead: 0.05, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gemini-3.1-flash-lite', + name: 'Gemini 3.1 Flash Lite', + config: { + api: 'google-vertex', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 0.25, + output: 1.5, + cacheRead: 0.025, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gemini-3.1-pro-preview', + name: 'Gemini 3.1 Pro Preview', + config: { + api: 'google-vertex', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 2, + output: 12, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gemini-3.1-pro-preview-customtools', + name: 'Gemini 3.1 Pro Preview Custom Tools', + config: { + api: 'google-vertex', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 2, + output: 12, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gemini-3.5-flash', + name: 'Gemini 3.5 Flash', + config: { + api: 'google-vertex', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 1.5, + output: 9, + cacheRead: 0.15, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gemini-flash-latest', + name: 'Gemini Flash Latest', + config: { + api: 'google-vertex', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 1.5, + output: 9, + cacheRead: 0.15, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gemini-flash-lite-latest', + name: 'Gemini Flash-Lite Latest', + config: { + api: 'google-vertex', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 0.25, + output: 1.5, + cacheRead: 0.025, + cacheWrite: 0, + }, + }, + }, + ], +} as const diff --git a/packages/core/src/generated/providers/google.ts b/packages/core/src/generated/providers/google.ts new file mode 100644 index 00000000..fd11ae8a --- /dev/null +++ b/packages/core/src/generated/providers/google.ts @@ -0,0 +1,320 @@ +// This file is auto-generated by scripts/generate-builtin-providers.ts +// Do not edit manually - run 'bun run generate-providers' to update + +export const providerName = 'google' +export const providerConfig = { + name: 'google', + config: { + api: 'google-generative-ai', + baseUrl: 'https://generativelanguage.googleapis.com/v1beta', + apiKey: 'GEMINI_API_KEY', + }, + models: [ + { + modelId: 'gemini-2.0-flash', + name: 'Gemini 2.0 Flash', + config: { + api: 'google-generative-ai', + reasoning: false, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 8192, + cost: { + input: 0.1, + output: 0.4, + cacheRead: 0.025, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gemini-2.0-flash-lite', + name: 'Gemini 2.0 Flash-Lite', + config: { + api: 'google-generative-ai', + reasoning: false, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 8192, + cost: { + input: 0.075, + output: 0.3, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gemini-2.5-flash', + name: 'Gemini 2.5 Flash', + config: { + api: 'google-generative-ai', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 0.3, + output: 2.5, + cacheRead: 0.03, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gemini-2.5-flash-lite', + name: 'Gemini 2.5 Flash-Lite', + config: { + api: 'google-generative-ai', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 0.1, + output: 0.4, + cacheRead: 0.01, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gemini-2.5-pro', + name: 'Gemini 2.5 Pro', + config: { + api: 'google-generative-ai', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 1.25, + output: 10, + cacheRead: 0.125, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gemini-3-flash-preview', + name: 'Gemini 3 Flash Preview', + config: { + api: 'google-generative-ai', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 0.5, + output: 3, + cacheRead: 0.05, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gemini-3-pro-preview', + name: 'Gemini 3 Pro Preview', + config: { + api: 'google-generative-ai', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 2, + output: 12, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gemini-3.1-flash-lite', + name: 'Gemini 3.1 Flash Lite', + config: { + api: 'google-generative-ai', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 0.25, + output: 1.5, + cacheRead: 0.025, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gemini-3.1-flash-lite-preview', + name: 'Gemini 3.1 Flash Lite Preview', + config: { + api: 'google-generative-ai', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 0.25, + output: 1.5, + cacheRead: 0.025, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gemini-3.1-pro-preview', + name: 'Gemini 3.1 Pro Preview', + config: { + api: 'google-generative-ai', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 2, + output: 12, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gemini-3.1-pro-preview-customtools', + name: 'Gemini 3.1 Pro Preview Custom Tools', + config: { + api: 'google-generative-ai', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 2, + output: 12, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gemini-3.5-flash', + name: 'Gemini 3.5 Flash', + config: { + api: 'google-generative-ai', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 1.5, + output: 9, + cacheRead: 0.15, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gemini-3.5-flash-lite', + name: 'Gemini 3.5 Flash Lite', + config: { + api: 'google-generative-ai', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 0.3, + output: 2.5, + cacheRead: 0.03, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gemini-3.6-flash', + name: 'Gemini 3.6 Flash', + config: { + api: 'google-generative-ai', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 1.5, + output: 7.5, + cacheRead: 0.15, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gemini-flash-latest', + name: 'Gemini Flash Latest', + config: { + api: 'google-generative-ai', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 1.5, + output: 9, + cacheRead: 0.15, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gemini-flash-lite-latest', + name: 'Gemini Flash-Lite Latest', + config: { + api: 'google-generative-ai', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 0.25, + output: 1.5, + cacheRead: 0.025, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gemma-4-26b-a4b-it', + name: 'Gemma 4 26B A4B IT', + config: { + api: 'google-generative-ai', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 32768, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gemma-4-31b-it', + name: 'Gemma 4 31B IT', + config: { + api: 'google-generative-ai', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 32768, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + ], +} as const diff --git a/packages/core/src/generated/providers/groq.ts b/packages/core/src/generated/providers/groq.ts new file mode 100644 index 00000000..2188badc --- /dev/null +++ b/packages/core/src/generated/providers/groq.ts @@ -0,0 +1,133 @@ +// This file is auto-generated by scripts/generate-builtin-providers.ts +// Do not edit manually - run 'bun run generate-providers' to update + +export const providerName = 'groq' +export const providerConfig = { + name: 'groq', + config: { + api: 'openai-completions', + baseUrl: 'https://api.groq.com/openai/v1', + apiKey: 'GROQ_API_KEY', + }, + models: [ + { + modelId: 'llama-3.1-8b-instant', + name: 'Llama 3.1 8B', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 131072, + maxTokens: 131072, + cost: { + input: 0.05, + output: 0.08, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'llama-3.3-70b-versatile', + name: 'Llama 3.3 70B', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 131072, + maxTokens: 32768, + cost: { + input: 0.59, + output: 0.79, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'meta-llama/llama-4-scout-17b-16e-instruct', + name: 'Llama 4 Scout 17B 16E', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 131072, + maxTokens: 8192, + cost: { + input: 0.11, + output: 0.34, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-oss-120b', + name: 'GPT OSS 120B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 65536, + cost: { + input: 0.15, + output: 0.6, + cacheRead: 0.075, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-oss-20b', + name: 'GPT OSS 20B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 65536, + cost: { + input: 0.075, + output: 0.3, + cacheRead: 0.0375, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-oss-safeguard-20b', + name: 'Safety GPT OSS 20B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 65536, + cost: { + input: 0.075, + output: 0.3, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen/qwen3-32b', + name: 'Qwen3-32B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 40960, + cost: { + input: 0.29, + output: 0.59, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + ], +} as const diff --git a/packages/core/src/generated/providers/huggingface.ts b/packages/core/src/generated/providers/huggingface.ts new file mode 100644 index 00000000..4f39a49d --- /dev/null +++ b/packages/core/src/generated/providers/huggingface.ts @@ -0,0 +1,847 @@ +// This file is auto-generated by scripts/generate-builtin-providers.ts +// Do not edit manually - run 'bun run generate-providers' to update + +export const providerName = 'huggingface' +export const providerConfig = { + name: 'huggingface', + config: { + api: 'openai-completions', + baseUrl: 'https://router.huggingface.co/v1', + apiKey: 'HF_TOKEN', + }, + models: [ + { + modelId: 'MiniMaxAI/MiniMax-M2', + name: 'MiniMax-M2', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 204800, + maxTokens: 128000, + cost: { + input: 0.3, + output: 1.2, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'MiniMaxAI/MiniMax-M2.1', + name: 'MiniMax-M2.1', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 204800, + maxTokens: 131072, + cost: { + input: 0.3, + output: 1.2, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'MiniMaxAI/MiniMax-M2.5', + name: 'MiniMax-M2.5', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 204800, + maxTokens: 131072, + cost: { + input: 0.3, + output: 1.2, + cacheRead: 0.03, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'MiniMaxAI/MiniMax-M2.7', + name: 'MiniMax-M2.7', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 204800, + maxTokens: 131072, + cost: { + input: 0.3, + output: 1.2, + cacheRead: 0.06, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'MiniMaxAI/MiniMax-M3', + name: 'MiniMax-M3', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 524288, + maxTokens: 128000, + cost: { + input: 0.3, + output: 1.2, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'Qwen/Qwen3-235B-A22B', + name: 'Qwen3 235B-A22B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 40960, + maxTokens: 16384, + cost: { + input: 0.2, + output: 0.8, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'Qwen/Qwen3-235B-A22B-Thinking-2507', + name: 'Qwen3-235B-A22B-Thinking-2507', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 262144, + maxTokens: 131072, + cost: { + input: 0.3, + output: 3, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'Qwen/Qwen3-32B', + name: 'Qwen3 32B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 16384, + cost: { + input: 0.29, + output: 0.59, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'Qwen/Qwen3-Coder-30B-A3B-Instruct', + name: 'Qwen3-Coder 30B-A3B Instruct', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 262144, + maxTokens: 65536, + cost: { + input: 0.07, + output: 0.26, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'Qwen/Qwen3-Coder-480B-A35B-Instruct', + name: 'Qwen3-Coder-480B-A35B-Instruct', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 262144, + maxTokens: 66536, + cost: { + input: 2, + output: 2, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'Qwen/Qwen3-Coder-Next', + name: 'Qwen3-Coder-Next', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 262144, + maxTokens: 65536, + cost: { + input: 0.2, + output: 1.5, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'Qwen/Qwen3-Next-80B-A3B-Instruct', + name: 'Qwen3-Next-80B-A3B-Instruct', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 262144, + maxTokens: 66536, + cost: { + input: 0.25, + output: 1, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'Qwen/Qwen3-Next-80B-A3B-Thinking', + name: 'Qwen3-Next-80B-A3B-Thinking', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 262144, + maxTokens: 131072, + cost: { + input: 0.3, + output: 2, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'Qwen/Qwen3.5-122B-A10B', + name: 'Qwen3.5 122B-A10B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 65536, + cost: { + input: 0.4, + output: 3.2, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'Qwen/Qwen3.5-27B', + name: 'Qwen3.5 27B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 65536, + cost: { + input: 0.3, + output: 2.4, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'Qwen/Qwen3.5-35B-A3B', + name: 'Qwen3.5 35B-A3B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 65536, + cost: { + input: 0.25, + output: 2, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'Qwen/Qwen3.5-397B-A17B', + name: 'Qwen3.5-397B-A17B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 32768, + cost: { + input: 0.6, + output: 3.6, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'Qwen/Qwen3.5-9B', + name: 'Qwen3.5 9B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 65536, + cost: { + input: 0.17, + output: 0.25, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'Qwen/Qwen3.6-27B', + name: 'Qwen3.6 27B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 65536, + cost: { + input: 0.47, + output: 3.19, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'Qwen/Qwen3.6-35B-A3B', + name: 'Qwen3.6 35B-A3B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 65536, + cost: { + input: 0.15, + output: 0.95, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'XiaomiMiMo/MiMo-V2-Flash', + name: 'MiMo-V2-Flash', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 262144, + maxTokens: 4096, + cost: { + input: 0.1, + output: 0.3, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'XiaomiMiMo/MiMo-V2.5-Pro', + name: 'MiMo-V2.5-Pro', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1048576, + maxTokens: 131072, + cost: { + input: 1, + output: 3, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'deepseek-ai/DeepSeek-R1', + name: 'DeepSeek-R1', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 64000, + maxTokens: 32768, + cost: { + input: 0.7, + output: 2.5, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'deepseek-ai/DeepSeek-R1-0528', + name: 'DeepSeek-R1-0528', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 163840, + maxTokens: 163840, + cost: { + input: 3, + output: 5, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'deepseek-ai/DeepSeek-V3.2', + name: 'DeepSeek-V3.2', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 163840, + maxTokens: 65536, + cost: { + input: 0.28, + output: 0.4, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'deepseek-ai/DeepSeek-V4-Flash', + name: 'DeepSeek V4 Flash', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1048576, + maxTokens: 384000, + cost: { + input: 0.14, + output: 0.28, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'deepseek-ai/DeepSeek-V4-Pro', + name: 'DeepSeek V4 Pro', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1048576, + maxTokens: 393216, + cost: { + input: 0.435, + output: 0.87, + cacheRead: 0.003625, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'google/gemma-4-26B-A4B-it', + name: 'Gemma 4 26B A4B IT', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 32768, + cost: { + input: 0.13, + output: 0.4, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'google/gemma-4-31B-it', + name: 'Gemma 4 31B IT', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 32768, + cost: { + input: 0.14, + output: 0.4, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'meta-llama/Llama-3.3-70B-Instruct', + name: 'Llama-3.3-70B-Instruct', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 131072, + maxTokens: 4096, + cost: { + input: 0.59, + output: 0.79, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'moonshotai/Kimi-K2-Instruct', + name: 'Kimi-K2-Instruct', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 131072, + maxTokens: 16384, + cost: { + input: 1, + output: 3, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'moonshotai/Kimi-K2-Instruct-0905', + name: 'Kimi-K2-Instruct-0905', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 262144, + maxTokens: 16384, + cost: { + input: 1, + output: 3, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'moonshotai/Kimi-K2-Thinking', + name: 'Kimi-K2-Thinking', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0.6, + output: 2.5, + cacheRead: 0.15, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'moonshotai/Kimi-K2.5', + name: 'Kimi-K2.5', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0.6, + output: 3, + cacheRead: 0.1, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'moonshotai/Kimi-K2.6', + name: 'Kimi-K2.6', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0.95, + output: 4, + cacheRead: 0.16, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'moonshotai/Kimi-K2.7-Code', + name: 'Kimi K2.7 Code', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0.95, + output: 4, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-oss-120b', + name: 'GPT OSS 120B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 32768, + cost: { + input: 0.25, + output: 0.69, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-oss-20b', + name: 'GPT OSS 20B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 32768, + cost: { + input: 0.1, + output: 0.5, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'stepfun-ai/Step-3.5-Flash', + name: 'Step 3.5 Flash', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 262144, + maxTokens: 256000, + cost: { + input: 0.1, + output: 0.3, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'stepfun-ai/Step-3.7-Flash', + name: 'Step 3.7 Flash', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 256000, + cost: { + input: 0.2, + output: 1.15, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'zai-org/GLM-4.5', + name: 'GLM-4.5', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 98304, + cost: { + input: 0.6, + output: 2.2, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'zai-org/GLM-4.5-Air', + name: 'GLM-4.5-Air', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 98304, + cost: { + input: 0.13, + output: 0.85, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'zai-org/GLM-4.5V', + name: 'GLM-4.5V', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 65536, + maxTokens: 16384, + cost: { + input: 0.6, + output: 1.8, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'zai-org/GLM-4.6', + name: 'GLM-4.6', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 204800, + maxTokens: 131072, + cost: { + input: 0.55, + output: 2.2, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'zai-org/GLM-4.7', + name: 'GLM-4.7', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 204800, + maxTokens: 131072, + cost: { + input: 0.6, + output: 2.2, + cacheRead: 0.11, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'zai-org/GLM-4.7-Flash', + name: 'GLM-4.7-Flash', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 200000, + maxTokens: 128000, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'zai-org/GLM-5', + name: 'GLM-5', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 202752, + maxTokens: 131072, + cost: { + input: 1, + output: 3.2, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'zai-org/GLM-5.1', + name: 'GLM-5.1', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 202752, + maxTokens: 131072, + cost: { + input: 1, + output: 3.2, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'zai-org/GLM-5.2', + name: 'GLM-5.2', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 262144, + maxTokens: 131072, + cost: { + input: 1.4, + output: 4.4, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + ], +} as const diff --git a/packages/core/src/generated/providers/kimi-coding.ts b/packages/core/src/generated/providers/kimi-coding.ts new file mode 100644 index 00000000..1039dfae --- /dev/null +++ b/packages/core/src/generated/providers/kimi-coding.ts @@ -0,0 +1,65 @@ +// This file is auto-generated by scripts/generate-builtin-providers.ts +// Do not edit manually - run 'bun run generate-providers' to update + +export const providerName = 'kimi-coding' +export const providerConfig = { + name: 'kimi-coding', + config: { + api: 'anthropic-messages', + baseUrl: 'https://api.kimi.com/coding', + apiKey: 'KIMI_API_KEY', + }, + models: [ + { + modelId: 'k3', + name: 'Kimi K3', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 131072, + cost: { + input: 3, + output: 15, + cacheRead: 0.3, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'kimi-for-coding', + name: 'Kimi K2.7 Code', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 32768, + cost: { + input: 0.95, + output: 4, + cacheRead: 0.19, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'kimi-for-coding-highspeed', + name: 'Kimi For Coding HighSpeed', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 32768, + cost: { + input: 1.9, + output: 8, + cacheRead: 0.38, + cacheWrite: 0, + }, + }, + }, + ], +} as const diff --git a/packages/core/src/generated/providers/minimax-cn.ts b/packages/core/src/generated/providers/minimax-cn.ts new file mode 100644 index 00000000..2b5e5c37 --- /dev/null +++ b/packages/core/src/generated/providers/minimax-cn.ts @@ -0,0 +1,65 @@ +// This file is auto-generated by scripts/generate-builtin-providers.ts +// Do not edit manually - run 'bun run generate-providers' to update + +export const providerName = 'minimax-cn' +export const providerConfig = { + name: 'minimax-cn', + config: { + api: 'anthropic-messages', + baseUrl: 'https://api.minimaxi.com/anthropic', + apiKey: 'MINIMAX_CN_API_KEY', + }, + models: [ + { + modelId: 'MiniMax-M2.7', + name: 'MiniMax-M2.7', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 204800, + maxTokens: 131072, + cost: { + input: 0.3, + output: 1.2, + cacheRead: 0.06, + cacheWrite: 0.375, + }, + }, + }, + { + modelId: 'MiniMax-M2.7-highspeed', + name: 'MiniMax-M2.7-highspeed', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 204800, + maxTokens: 131072, + cost: { + input: 0.6, + output: 2.4, + cacheRead: 0.06, + cacheWrite: 0.375, + }, + }, + }, + { + modelId: 'MiniMax-M3', + name: 'MiniMax-M3', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 0.3, + output: 1.2, + cacheRead: 0.06, + cacheWrite: 0, + }, + }, + }, + ], +} as const diff --git a/packages/core/src/generated/providers/minimax.ts b/packages/core/src/generated/providers/minimax.ts new file mode 100644 index 00000000..e3d05e32 --- /dev/null +++ b/packages/core/src/generated/providers/minimax.ts @@ -0,0 +1,65 @@ +// This file is auto-generated by scripts/generate-builtin-providers.ts +// Do not edit manually - run 'bun run generate-providers' to update + +export const providerName = 'minimax' +export const providerConfig = { + name: 'minimax', + config: { + api: 'anthropic-messages', + baseUrl: 'https://api.minimax.io/anthropic', + apiKey: 'MINIMAX_API_KEY', + }, + models: [ + { + modelId: 'MiniMax-M2.7', + name: 'MiniMax-M2.7', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 204800, + maxTokens: 131072, + cost: { + input: 0.3, + output: 1.2, + cacheRead: 0.06, + cacheWrite: 0.375, + }, + }, + }, + { + modelId: 'MiniMax-M2.7-highspeed', + name: 'MiniMax-M2.7-highspeed', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 204800, + maxTokens: 131072, + cost: { + input: 0.6, + output: 2.4, + cacheRead: 0.06, + cacheWrite: 0.375, + }, + }, + }, + { + modelId: 'MiniMax-M3', + name: 'MiniMax-M3', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 0.3, + output: 1.2, + cacheRead: 0.06, + cacheWrite: 0, + }, + }, + }, + ], +} as const diff --git a/packages/core/src/generated/providers/mistral.ts b/packages/core/src/generated/providers/mistral.ts new file mode 100644 index 00000000..91c7e60f --- /dev/null +++ b/packages/core/src/generated/providers/mistral.ts @@ -0,0 +1,524 @@ +// This file is auto-generated by scripts/generate-builtin-providers.ts +// Do not edit manually - run 'bun run generate-providers' to update + +export const providerName = 'mistral' +export const providerConfig = { + name: 'mistral', + config: { + api: 'mistral-conversations', + baseUrl: 'https://api.mistral.ai', + apiKey: 'MISTRAL_API_KEY', + }, + models: [ + { + modelId: 'codestral-latest', + name: 'Codestral (latest)', + config: { + api: 'mistral-conversations', + reasoning: false, + input: ['text'], + contextWindow: 256000, + maxTokens: 4096, + cost: { + input: 0.3, + output: 0.9, + cacheRead: 0.03, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'devstral-2512', + name: 'Devstral 2', + config: { + api: 'mistral-conversations', + reasoning: false, + input: ['text'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0.4, + output: 2, + cacheRead: 0.04, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'devstral-latest', + name: 'Devstral 2', + config: { + api: 'mistral-conversations', + reasoning: false, + input: ['text'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0.4, + output: 2, + cacheRead: 0.04, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'devstral-medium-2507', + name: 'Devstral Medium', + config: { + api: 'mistral-conversations', + reasoning: false, + input: ['text'], + contextWindow: 128000, + maxTokens: 128000, + cost: { + input: 0.4, + output: 2, + cacheRead: 0.04, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'devstral-medium-latest', + name: 'Devstral 2 (latest)', + config: { + api: 'mistral-conversations', + reasoning: false, + input: ['text'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0.4, + output: 2, + cacheRead: 0.04, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'devstral-small-2505', + name: 'Devstral Small 2505', + config: { + api: 'mistral-conversations', + reasoning: false, + input: ['text'], + contextWindow: 128000, + maxTokens: 128000, + cost: { + input: 0.1, + output: 0.3, + cacheRead: 0.01, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'devstral-small-2507', + name: 'Devstral Small', + config: { + api: 'mistral-conversations', + reasoning: false, + input: ['text'], + contextWindow: 128000, + maxTokens: 128000, + cost: { + input: 0.1, + output: 0.3, + cacheRead: 0.01, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'labs-devstral-small-2512', + name: 'Devstral Small 2', + config: { + api: 'mistral-conversations', + reasoning: false, + input: ['text', 'image'], + contextWindow: 256000, + maxTokens: 256000, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'magistral-medium-latest', + name: 'Magistral Medium (latest)', + config: { + api: 'mistral-conversations', + reasoning: true, + input: ['text'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 2, + output: 5, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'magistral-small', + name: 'Magistral Small', + config: { + api: 'mistral-conversations', + reasoning: true, + input: ['text'], + contextWindow: 128000, + maxTokens: 128000, + cost: { + input: 0.5, + output: 1.5, + cacheRead: 0.05, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'ministral-3b-latest', + name: 'Ministral 3B (latest)', + config: { + api: 'mistral-conversations', + reasoning: false, + input: ['text'], + contextWindow: 128000, + maxTokens: 128000, + cost: { + input: 0.04, + output: 0.04, + cacheRead: 0.004, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'ministral-8b-latest', + name: 'Ministral 8B (latest)', + config: { + api: 'mistral-conversations', + reasoning: false, + input: ['text'], + contextWindow: 128000, + maxTokens: 128000, + cost: { + input: 0.1, + output: 0.1, + cacheRead: 0.01, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistral-large-2411', + name: 'Mistral Large 2.1', + config: { + api: 'mistral-conversations', + reasoning: false, + input: ['text'], + contextWindow: 131072, + maxTokens: 16384, + cost: { + input: 2, + output: 6, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistral-large-2512', + name: 'Mistral Large 3', + config: { + api: 'mistral-conversations', + reasoning: false, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0.5, + output: 1.5, + cacheRead: 0.05, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistral-large-latest', + name: 'Mistral Large (latest)', + config: { + api: 'mistral-conversations', + reasoning: false, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0.5, + output: 1.5, + cacheRead: 0.05, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistral-medium-2505', + name: 'Mistral Medium 3', + config: { + api: 'mistral-conversations', + reasoning: false, + input: ['text', 'image'], + contextWindow: 131072, + maxTokens: 131072, + cost: { + input: 0.4, + output: 2, + cacheRead: 0.04, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistral-medium-2508', + name: 'Mistral Medium 3.1', + config: { + api: 'mistral-conversations', + reasoning: false, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0.4, + output: 2, + cacheRead: 0.04, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistral-medium-2604', + name: 'Mistral Medium 3.5', + config: { + api: 'mistral-conversations', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 1.5, + output: 7.5, + cacheRead: 0.15, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistral-medium-3.5', + name: 'Mistral Medium 3.5', + config: { + api: 'mistral-conversations', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 1.5, + output: 7.5, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistral-medium-latest', + name: 'Mistral Medium (latest)', + config: { + api: 'mistral-conversations', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 1.5, + output: 7.5, + cacheRead: 0.15, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistral-nemo', + name: 'Mistral Nemo', + config: { + api: 'mistral-conversations', + reasoning: false, + input: ['text'], + contextWindow: 128000, + maxTokens: 128000, + cost: { + input: 0.15, + output: 0.15, + cacheRead: 0.015, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistral-small-2506', + name: 'Mistral Small 3.2', + config: { + api: 'mistral-conversations', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 0.1, + output: 0.3, + cacheRead: 0.01, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistral-small-2603', + name: 'Mistral Small 4', + config: { + api: 'mistral-conversations', + reasoning: true, + input: ['text', 'image'], + contextWindow: 256000, + maxTokens: 256000, + cost: { + input: 0.15, + output: 0.6, + cacheRead: 0.015, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistral-small-latest', + name: 'Mistral Small (latest)', + config: { + api: 'mistral-conversations', + reasoning: true, + input: ['text', 'image'], + contextWindow: 256000, + maxTokens: 256000, + cost: { + input: 0.15, + output: 0.6, + cacheRead: 0.015, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'open-mistral-7b', + name: 'Mistral 7B', + config: { + api: 'mistral-conversations', + reasoning: false, + input: ['text'], + contextWindow: 8000, + maxTokens: 8000, + cost: { + input: 0.25, + output: 0.25, + cacheRead: 0.025, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'open-mistral-nemo', + name: 'Open Mistral Nemo', + config: { + api: 'mistral-conversations', + reasoning: false, + input: ['text'], + contextWindow: 128000, + maxTokens: 128000, + cost: { + input: 0.15, + output: 0.15, + cacheRead: 0.015, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'open-mixtral-8x22b', + name: 'Mixtral 8x22B', + config: { + api: 'mistral-conversations', + reasoning: false, + input: ['text'], + contextWindow: 64000, + maxTokens: 64000, + cost: { + input: 2, + output: 6, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'open-mixtral-8x7b', + name: 'Mixtral 8x7B', + config: { + api: 'mistral-conversations', + reasoning: false, + input: ['text'], + contextWindow: 32000, + maxTokens: 32000, + cost: { + input: 0.7, + output: 0.7, + cacheRead: 0.07, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'pixtral-12b', + name: 'Pixtral 12B', + config: { + api: 'mistral-conversations', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 128000, + cost: { + input: 0.15, + output: 0.15, + cacheRead: 0.015, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'pixtral-large-latest', + name: 'Pixtral Large (latest)', + config: { + api: 'mistral-conversations', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 128000, + cost: { + input: 2, + output: 6, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + ], +} as const diff --git a/packages/core/src/generated/providers/moonshotai-cn.ts b/packages/core/src/generated/providers/moonshotai-cn.ts new file mode 100644 index 00000000..b364b739 --- /dev/null +++ b/packages/core/src/generated/providers/moonshotai-cn.ts @@ -0,0 +1,184 @@ +// This file is auto-generated by scripts/generate-builtin-providers.ts +// Do not edit manually - run 'bun run generate-providers' to update + +export const providerName = 'moonshotai-cn' +export const providerConfig = { + name: 'moonshotai-cn', + config: { + api: 'openai-completions', + baseUrl: 'https://api.moonshot.cn/v1', + apiKey: 'MOONSHOT_API_KEY', + }, + models: [ + { + modelId: 'kimi-k2-0711-preview', + name: 'Kimi K2 0711', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 131072, + maxTokens: 16384, + cost: { + input: 0.6, + output: 2.5, + cacheRead: 0.15, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'kimi-k2-0905-preview', + name: 'Kimi K2 0905', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0.6, + output: 2.5, + cacheRead: 0.15, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'kimi-k2-thinking', + name: 'Kimi K2 Thinking', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0.6, + output: 2.5, + cacheRead: 0.15, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'kimi-k2-thinking-turbo', + name: 'Kimi K2 Thinking Turbo', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 1.15, + output: 8, + cacheRead: 0.15, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'kimi-k2-turbo-preview', + name: 'Kimi K2 Turbo', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 2.4, + output: 10, + cacheRead: 0.6, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'kimi-k2.5', + name: 'Kimi K2.5', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0.6, + output: 3, + cacheRead: 0.1, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'kimi-k2.6', + name: 'Kimi K2.6', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0.95, + output: 4, + cacheRead: 0.16, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'kimi-k2.7-code', + name: 'Kimi K2.7 Code', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0.95, + output: 4, + cacheRead: 0.19, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'kimi-k2.7-code-highspeed', + name: 'Kimi K2.7 Code HighSpeed', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 1.9, + output: 8, + cacheRead: 0.38, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'kimi-k3', + name: 'Kimi K3', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 131072, + cost: { + input: 3, + output: 15, + cacheRead: 0.3, + cacheWrite: 0, + }, + }, + }, + ], +} as const diff --git a/packages/core/src/generated/providers/moonshotai.ts b/packages/core/src/generated/providers/moonshotai.ts new file mode 100644 index 00000000..7d63962b --- /dev/null +++ b/packages/core/src/generated/providers/moonshotai.ts @@ -0,0 +1,184 @@ +// This file is auto-generated by scripts/generate-builtin-providers.ts +// Do not edit manually - run 'bun run generate-providers' to update + +export const providerName = 'moonshotai' +export const providerConfig = { + name: 'moonshotai', + config: { + api: 'openai-completions', + baseUrl: 'https://api.moonshot.ai/v1', + apiKey: 'MOONSHOT_API_KEY', + }, + models: [ + { + modelId: 'kimi-k2-0711-preview', + name: 'Kimi K2 0711', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 131072, + maxTokens: 16384, + cost: { + input: 0.6, + output: 2.5, + cacheRead: 0.15, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'kimi-k2-0905-preview', + name: 'Kimi K2 0905', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0.6, + output: 2.5, + cacheRead: 0.15, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'kimi-k2-thinking', + name: 'Kimi K2 Thinking', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0.6, + output: 2.5, + cacheRead: 0.15, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'kimi-k2-thinking-turbo', + name: 'Kimi K2 Thinking Turbo', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 1.15, + output: 8, + cacheRead: 0.15, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'kimi-k2-turbo-preview', + name: 'Kimi K2 Turbo', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 2.4, + output: 10, + cacheRead: 0.6, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'kimi-k2.5', + name: 'Kimi K2.5', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0.6, + output: 3, + cacheRead: 0.1, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'kimi-k2.6', + name: 'Kimi K2.6', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0.95, + output: 4, + cacheRead: 0.16, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'kimi-k2.7-code', + name: 'Kimi K2.7 Code', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0.95, + output: 4, + cacheRead: 0.19, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'kimi-k2.7-code-highspeed', + name: 'Kimi K2.7 Code HighSpeed', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 1.9, + output: 8, + cacheRead: 0.38, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'kimi-k3', + name: 'Kimi K3', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 131072, + cost: { + input: 3, + output: 15, + cacheRead: 0.3, + cacheWrite: 0, + }, + }, + }, + ], +} as const diff --git a/packages/core/src/generated/providers/nvidia.ts b/packages/core/src/generated/providers/nvidia.ts new file mode 100644 index 00000000..3dce77e8 --- /dev/null +++ b/packages/core/src/generated/providers/nvidia.ts @@ -0,0 +1,337 @@ +// This file is auto-generated by scripts/generate-builtin-providers.ts +// Do not edit manually - run 'bun run generate-providers' to update + +export const providerName = 'nvidia' +export const providerConfig = { + name: 'nvidia', + config: { + api: 'openai-completions', + baseUrl: 'https://integrate.api.nvidia.com/v1', + apiKey: '', + }, + models: [ + { + modelId: 'meta/llama-3.1-70b-instruct', + name: 'Llama 3.1 70b Instruct', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 128000, + maxTokens: 4096, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'meta/llama-3.1-8b-instruct', + name: 'Llama 3.1 8B Instruct', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 16000, + maxTokens: 4096, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'meta/llama-3.2-11b-vision-instruct', + name: 'Llama 3.2 11b Vision Instruct', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 4096, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'meta/llama-3.2-90b-vision-instruct', + name: 'Llama-3.2-90B-Vision-Instruct', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 8192, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'meta/llama-3.3-70b-instruct', + name: 'Llama 3.3 70b Instruct', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 128000, + maxTokens: 4096, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'minimaxai/minimax-m3', + name: 'MiniMax-M3', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 16384, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistralai/mistral-large-3-675b-instruct-2512', + name: 'Mistral Large 3 675B Instruct 2512', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistralai/mistral-small-4-119b-2603', + name: 'mistral-small-4-119b-2603', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 8192, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'moonshotai/kimi-k2.6', + name: 'Kimi K2.6', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'nvidia/nemotron-3-nano-30b-a3b', + name: 'nemotron-3-nano-30b-a3b', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 131072, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'nvidia/nemotron-3-nano-omni-30b-a3b-reasoning', + name: 'Nemotron 3 Nano Omni', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 256000, + maxTokens: 65536, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'nvidia/nemotron-3-super-120b-a12b', + name: 'Nemotron 3 Super', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0.2, + output: 0.8, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'nvidia/nemotron-3-ultra-550b-a55b', + name: 'Nemotron 3 Ultra 550B A55B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1000000, + maxTokens: 65536, + cost: { + input: 0.5, + output: 2.5, + cacheRead: 0.15, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'nvidia/nvidia-nemotron-nano-9b-v2', + name: 'nvidia-nemotron-nano-9b-v2', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 131072, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-oss-120b', + name: 'GPT-OSS-120B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 128000, + maxTokens: 8192, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-oss-20b', + name: 'GPT OSS 20B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 32768, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'stepfun-ai/step-3.5-flash', + name: 'Step 3.5 Flash', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 256000, + maxTokens: 16384, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'stepfun-ai/step-3.7-flash', + name: 'Step 3.7 Flash', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 256000, + maxTokens: 16384, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'z-ai/glm-5.2', + name: 'GLM-5.2', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1000000, + maxTokens: 131072, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + ], +} as const diff --git a/packages/core/src/generated/providers/openai-codex.ts b/packages/core/src/generated/providers/openai-codex.ts new file mode 100644 index 00000000..efe7689e --- /dev/null +++ b/packages/core/src/generated/providers/openai-codex.ts @@ -0,0 +1,178 @@ +// This file is auto-generated by scripts/generate-builtin-providers.ts +// Do not edit manually - run 'bun run generate-providers' to update + +export const providerName = 'openai-codex' +export const providerConfig = { + name: 'openai-codex', + config: { + api: 'openai-codex-responses', + baseUrl: 'https://chatgpt.com/backend-api', + apiKey: '', + }, + models: [ + { + modelId: 'gpt-5.3-codex-spark', + name: 'GPT-5.3 Codex Spark', + config: { + api: 'openai-codex-responses', + reasoning: true, + input: ['text'], + contextWindow: 128000, + maxTokens: 128000, + cost: { + input: 1.75, + output: 14, + cacheRead: 0.175, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.4', + name: 'GPT-5.4', + config: { + api: 'openai-codex-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 272000, + maxTokens: 128000, + cost: { + input: 2.5, + output: 15, + cacheRead: 0.25, + cacheWrite: 0, + tiers: [ + { + inputTokensAbove: 272000, + input: 5, + output: 22.5, + cacheRead: 0.5, + cacheWrite: 0, + }, + ], + }, + }, + }, + { + modelId: 'gpt-5.4-mini', + name: 'GPT-5.4 mini', + config: { + api: 'openai-codex-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 272000, + maxTokens: 128000, + cost: { + input: 0.75, + output: 4.5, + cacheRead: 0.075, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.5', + name: 'GPT-5.5', + config: { + api: 'openai-codex-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 272000, + maxTokens: 128000, + cost: { + input: 5, + output: 30, + cacheRead: 0.5, + cacheWrite: 0, + tiers: [ + { + inputTokensAbove: 272000, + input: 10, + output: 45, + cacheRead: 1, + cacheWrite: 0, + }, + ], + }, + }, + }, + { + modelId: 'gpt-5.6-luna', + name: 'GPT-5.6 Luna', + config: { + api: 'openai-codex-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 272000, + maxTokens: 128000, + cost: { + input: 1, + output: 6, + cacheRead: 0.1, + cacheWrite: 1.25, + tiers: [ + { + inputTokensAbove: 272000, + input: 2, + output: 9, + cacheRead: 0.2, + cacheWrite: 2.5, + }, + ], + }, + }, + }, + { + modelId: 'gpt-5.6-sol', + name: 'GPT-5.6 Sol', + config: { + api: 'openai-codex-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 272000, + maxTokens: 128000, + cost: { + input: 5, + output: 30, + cacheRead: 0.5, + cacheWrite: 6.25, + tiers: [ + { + inputTokensAbove: 272000, + input: 10, + output: 45, + cacheRead: 1, + cacheWrite: 12.5, + }, + ], + }, + }, + }, + { + modelId: 'gpt-5.6-terra', + name: 'GPT-5.6 Terra', + config: { + api: 'openai-codex-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 272000, + maxTokens: 128000, + cost: { + input: 2.5, + output: 15, + cacheRead: 0.25, + cacheWrite: 3.125, + tiers: [ + { + inputTokensAbove: 272000, + input: 5, + output: 22.5, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + ], + }, + }, + }, + ], +} as const diff --git a/packages/core/src/generated/providers/openai.ts b/packages/core/src/generated/providers/openai.ts new file mode 100644 index 00000000..acb11513 --- /dev/null +++ b/packages/core/src/generated/providers/openai.ts @@ -0,0 +1,859 @@ +// This file is auto-generated by scripts/generate-builtin-providers.ts +// Do not edit manually - run 'bun run generate-providers' to update + +export const providerName = 'openai' +export const providerConfig = { + name: 'openai', + config: { + api: 'openai-responses', + baseUrl: 'https://api.openai.com/v1', + apiKey: 'OPENAI_API_KEY', + }, + models: [ + { + modelId: 'gpt-4', + name: 'GPT-4', + config: { + api: 'openai-responses', + reasoning: false, + input: ['text'], + contextWindow: 8192, + maxTokens: 8192, + cost: { + input: 30, + output: 60, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-4-turbo', + name: 'GPT-4 Turbo', + config: { + api: 'openai-responses', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 4096, + cost: { + input: 10, + output: 30, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-4.1', + name: 'GPT-4.1', + config: { + api: 'openai-responses', + reasoning: false, + input: ['text', 'image'], + contextWindow: 1047576, + maxTokens: 32768, + cost: { + input: 2, + output: 8, + cacheRead: 0.5, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-4.1-mini', + name: 'GPT-4.1 mini', + config: { + api: 'openai-responses', + reasoning: false, + input: ['text', 'image'], + contextWindow: 1047576, + maxTokens: 32768, + cost: { + input: 0.4, + output: 1.6, + cacheRead: 0.1, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-4.1-nano', + name: 'GPT-4.1 nano', + config: { + api: 'openai-responses', + reasoning: false, + input: ['text', 'image'], + contextWindow: 1047576, + maxTokens: 32768, + cost: { + input: 0.1, + output: 0.4, + cacheRead: 0.025, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-4o', + name: 'GPT-4o', + config: { + api: 'openai-responses', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 2.5, + output: 10, + cacheRead: 1.25, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-4o-2024-05-13', + name: 'GPT-4o (2024-05-13)', + config: { + api: 'openai-responses', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 4096, + cost: { + input: 5, + output: 15, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-4o-2024-08-06', + name: 'GPT-4o (2024-08-06)', + config: { + api: 'openai-responses', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 2.5, + output: 10, + cacheRead: 1.25, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-4o-2024-11-20', + name: 'GPT-4o (2024-11-20)', + config: { + api: 'openai-responses', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 2.5, + output: 10, + cacheRead: 1.25, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-4o-mini', + name: 'GPT-4o mini', + config: { + api: 'openai-responses', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 0.15, + output: 0.6, + cacheRead: 0.075, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5', + name: 'GPT-5', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.25, + output: 10, + cacheRead: 0.125, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5-chat-latest', + name: 'GPT-5 Chat Latest', + config: { + api: 'openai-responses', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 1.25, + output: 10, + cacheRead: 0.125, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5-codex', + name: 'GPT-5-Codex', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.25, + output: 10, + cacheRead: 0.125, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5-mini', + name: 'GPT-5 Mini', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 0.25, + output: 2, + cacheRead: 0.025, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5-nano', + name: 'GPT-5 Nano', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 0.05, + output: 0.4, + cacheRead: 0.005, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5-pro', + name: 'GPT-5 Pro', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 15, + output: 120, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.1', + name: 'GPT-5.1', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.25, + output: 10, + cacheRead: 0.125, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.1-chat-latest', + name: 'GPT-5.1 Chat', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 1.25, + output: 10, + cacheRead: 0.125, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.1-codex', + name: 'GPT-5.1 Codex', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.25, + output: 10, + cacheRead: 0.125, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.1-codex-max', + name: 'GPT-5.1 Codex Max', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.25, + output: 10, + cacheRead: 0.125, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.1-codex-mini', + name: 'GPT-5.1 Codex mini', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 0.25, + output: 2, + cacheRead: 0.025, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.2', + name: 'GPT-5.2', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.75, + output: 14, + cacheRead: 0.175, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.2-chat-latest', + name: 'GPT-5.2 Chat', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 1.75, + output: 14, + cacheRead: 0.175, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.2-codex', + name: 'GPT-5.2 Codex', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.75, + output: 14, + cacheRead: 0.175, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.2-pro', + name: 'GPT-5.2 Pro', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 21, + output: 168, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.3-chat-latest', + name: 'GPT-5.3 Chat (latest)', + config: { + api: 'openai-responses', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 1.75, + output: 14, + cacheRead: 0.175, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.3-codex', + name: 'GPT-5.3 Codex', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.75, + output: 14, + cacheRead: 0.175, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.3-codex-spark', + name: 'GPT-5.3 Codex Spark', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 32000, + cost: { + input: 1.75, + output: 14, + cacheRead: 0.175, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.4', + name: 'GPT-5.4', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 272000, + maxTokens: 128000, + cost: { + input: 2.5, + output: 15, + cacheRead: 0.25, + cacheWrite: 0, + tiers: [ + { + inputTokensAbove: 272000, + input: 5, + output: 22.5, + cacheRead: 0.5, + cacheWrite: 0, + }, + ], + }, + }, + }, + { + modelId: 'gpt-5.4-mini', + name: 'GPT-5.4 mini', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 0.75, + output: 4.5, + cacheRead: 0.075, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.4-nano', + name: 'GPT-5.4 nano', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 0.2, + output: 1.25, + cacheRead: 0.02, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.4-pro', + name: 'GPT-5.4 Pro', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 128000, + cost: { + input: 30, + output: 180, + cacheRead: 0, + cacheWrite: 0, + tiers: [ + { + inputTokensAbove: 272000, + input: 60, + output: 270, + cacheRead: 0, + cacheWrite: 0, + }, + ], + }, + }, + }, + { + modelId: 'gpt-5.5', + name: 'GPT-5.5', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 272000, + maxTokens: 128000, + cost: { + input: 5, + output: 30, + cacheRead: 0.5, + cacheWrite: 0, + tiers: [ + { + inputTokensAbove: 272000, + input: 10, + output: 45, + cacheRead: 1, + cacheWrite: 0, + }, + ], + }, + }, + }, + { + modelId: 'gpt-5.5-pro', + name: 'GPT-5.5 Pro', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 128000, + cost: { + input: 30, + output: 180, + cacheRead: 0, + cacheWrite: 0, + tiers: [ + { + inputTokensAbove: 272000, + input: 60, + output: 270, + cacheRead: 0, + cacheWrite: 0, + }, + ], + }, + }, + }, + { + modelId: 'gpt-5.6-luna', + name: 'GPT-5.6 Luna', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 272000, + maxTokens: 128000, + cost: { + input: 1, + output: 6, + cacheRead: 0.1, + cacheWrite: 1.25, + tiers: [ + { + inputTokensAbove: 272000, + input: 2, + output: 9, + cacheRead: 0.2, + cacheWrite: 2.5, + }, + ], + }, + }, + }, + { + modelId: 'gpt-5.6-sol', + name: 'GPT-5.6 Sol', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 272000, + maxTokens: 128000, + cost: { + input: 5, + output: 30, + cacheRead: 0.5, + cacheWrite: 6.25, + tiers: [ + { + inputTokensAbove: 272000, + input: 10, + output: 45, + cacheRead: 1, + cacheWrite: 12.5, + }, + ], + }, + }, + }, + { + modelId: 'gpt-5.6-terra', + name: 'GPT-5.6 Terra', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 272000, + maxTokens: 128000, + cost: { + input: 2.5, + output: 15, + cacheRead: 0.25, + cacheWrite: 3.125, + tiers: [ + { + inputTokensAbove: 272000, + input: 5, + output: 22.5, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + ], + }, + }, + }, + { + modelId: 'gpt-realtime-2.1', + name: 'GPT-Realtime-2.1', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 32000, + cost: { + input: 4, + output: 24, + cacheRead: 0.4, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'o1', + name: 'o1', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 100000, + cost: { + input: 15, + output: 60, + cacheRead: 7.5, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'o1-pro', + name: 'o1-pro', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 100000, + cost: { + input: 150, + output: 600, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'o3', + name: 'o3', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 100000, + cost: { + input: 2, + output: 8, + cacheRead: 0.5, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'o3-deep-research', + name: 'o3-deep-research', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 100000, + cost: { + input: 10, + output: 40, + cacheRead: 2.5, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'o3-mini', + name: 'o3-mini', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text'], + contextWindow: 200000, + maxTokens: 100000, + cost: { + input: 1.1, + output: 4.4, + cacheRead: 0.55, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'o3-pro', + name: 'o3-pro', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 100000, + cost: { + input: 20, + output: 80, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'o4-mini', + name: 'o4-mini', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 100000, + cost: { + input: 1.1, + output: 4.4, + cacheRead: 0.275, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'o4-mini-deep-research', + name: 'o4-mini-deep-research', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 100000, + cost: { + input: 2, + output: 8, + cacheRead: 0.5, + cacheWrite: 0, + }, + }, + }, + ], +} as const diff --git a/packages/core/src/generated/providers/opencode-go.ts b/packages/core/src/generated/providers/opencode-go.ts new file mode 100644 index 00000000..3bf040fb --- /dev/null +++ b/packages/core/src/generated/providers/opencode-go.ts @@ -0,0 +1,269 @@ +// This file is auto-generated by scripts/generate-builtin-providers.ts +// Do not edit manually - run 'bun run generate-providers' to update + +export const providerName = 'opencode-go' +export const providerConfig = { + name: 'opencode-go', + config: { + api: 'openai-completions', + baseUrl: 'https://opencode.ai/zen/go/v1', + apiKey: 'OPENCODE_API_KEY', + }, + models: [ + { + modelId: 'deepseek-v4-flash', + name: 'DeepSeek V4 Flash', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1000000, + maxTokens: 384000, + cost: { + input: 0.14, + output: 0.28, + cacheRead: 0.0028, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'deepseek-v4-pro', + name: 'DeepSeek V4 Pro', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1000000, + maxTokens: 384000, + cost: { + input: 0.435, + output: 0.87, + cacheRead: 0.003625, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'glm-5.1', + name: 'GLM-5.1', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 202752, + maxTokens: 32768, + cost: { + input: 1.4, + output: 4.4, + cacheRead: 0.26, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'glm-5.2', + name: 'GLM-5.2', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1000000, + maxTokens: 131072, + cost: { + input: 1.4, + output: 4.4, + cacheRead: 0.26, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'grok-4.5', + name: 'Grok 4.5', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 500000, + maxTokens: 500000, + cost: { + input: 2, + output: 6, + cacheRead: 0.5, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'kimi-k2.6', + name: 'Kimi K2.6', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 65536, + cost: { + input: 0.95, + output: 4, + cacheRead: 0.16, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'kimi-k2.7-code', + name: 'Kimi K2.7 Code', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0.95, + output: 4, + cacheRead: 0.19, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'kimi-k3', + name: 'Kimi K3 (2x usage)', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 131072, + cost: { + input: 3, + output: 15, + cacheRead: 0.3, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mimo-v2.5', + name: 'MiMo V2.5', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 0.14, + output: 0.28, + cacheRead: 0.0028, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mimo-v2.5-pro', + name: 'MiMo V2.5 Pro', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1048576, + maxTokens: 128000, + cost: { + input: 0.435, + output: 0.87, + cacheRead: 0.003625, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'minimax-m2.7', + name: 'MiniMax-M2.7', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 204800, + maxTokens: 131072, + cost: { + input: 0.3, + output: 1.2, + cacheRead: 0.06, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'minimax-m3', + name: 'MiniMax-M3', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 131072, + cost: { + input: 0.3, + output: 1.2, + cacheRead: 0.06, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen3.6-plus', + name: 'Qwen3.6 Plus', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 65536, + cost: { + input: 0.5, + output: 3, + cacheRead: 0.05, + cacheWrite: 0.625, + }, + }, + }, + { + modelId: 'qwen3.7-max', + name: 'Qwen3.7 Max', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 1000000, + maxTokens: 65536, + cost: { + input: 2.5, + output: 7.5, + cacheRead: 0.5, + cacheWrite: 3.125, + }, + }, + }, + { + modelId: 'qwen3.7-plus', + name: 'Qwen3.7 Plus', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 65536, + cost: { + input: 0.4, + output: 1.6, + cacheRead: 0.04, + cacheWrite: 0.5, + }, + }, + }, + ], +} as const diff --git a/packages/core/src/generated/providers/opencode.ts b/packages/core/src/generated/providers/opencode.ts new file mode 100644 index 00000000..05a5afa7 --- /dev/null +++ b/packages/core/src/generated/providers/opencode.ts @@ -0,0 +1,966 @@ +// This file is auto-generated by scripts/generate-builtin-providers.ts +// Do not edit manually - run 'bun run generate-providers' to update + +export const providerName = 'opencode' +export const providerConfig = { + name: 'opencode', + config: { + api: 'openai-completions', + baseUrl: 'https://opencode.ai/zen/v1', + apiKey: 'OPENCODE_API_KEY', + }, + models: [ + { + modelId: 'big-pickle', + name: 'Big Pickle', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 200000, + maxTokens: 32000, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'claude-fable-5', + name: 'Claude Fable 5', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 10, + output: 50, + cacheRead: 1, + cacheWrite: 12.5, + }, + }, + }, + { + modelId: 'claude-haiku-4-5', + name: 'Claude Haiku 4.5', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 64000, + cost: { + input: 1, + output: 5, + cacheRead: 0.1, + cacheWrite: 1.25, + }, + }, + }, + { + modelId: 'claude-opus-4-1', + name: 'Claude Opus 4.1', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 32000, + cost: { + input: 15, + output: 75, + cacheRead: 1.5, + cacheWrite: 18.75, + }, + }, + }, + { + modelId: 'claude-opus-4-5', + name: 'Claude Opus 4.5', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 64000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'claude-opus-4-6', + name: 'Claude Opus 4.6', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'claude-opus-4-7', + name: 'Claude Opus 4.7', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'claude-opus-4-8', + name: 'Claude Opus 4.8', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'claude-sonnet-4', + name: 'Claude Sonnet 4', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 64000, + cost: { + input: 3, + output: 15, + cacheRead: 0.3, + cacheWrite: 3.75, + }, + }, + }, + { + modelId: 'claude-sonnet-4-5', + name: 'Claude Sonnet 4.5', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 64000, + cost: { + input: 3, + output: 15, + cacheRead: 0.3, + cacheWrite: 3.75, + }, + }, + }, + { + modelId: 'claude-sonnet-4-6', + name: 'Claude Sonnet 4.6', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 64000, + cost: { + input: 3, + output: 15, + cacheRead: 0.3, + cacheWrite: 3.75, + }, + }, + }, + { + modelId: 'claude-sonnet-5', + name: 'Claude Sonnet 5', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 2, + output: 10, + cacheRead: 0.2, + cacheWrite: 2.5, + }, + }, + }, + { + modelId: 'deepseek-v4-flash', + name: 'DeepSeek V4 Flash', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1000000, + maxTokens: 384000, + cost: { + input: 0.14, + output: 0.28, + cacheRead: 0.028, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'deepseek-v4-flash-free', + name: 'DeepSeek V4 Flash Free', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 200000, + maxTokens: 128000, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'deepseek-v4-pro', + name: 'DeepSeek V4 Pro', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1000000, + maxTokens: 384000, + cost: { + input: 1.74, + output: 3.84, + cacheRead: 0.145, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gemini-3-flash', + name: 'Gemini 3 Flash', + config: { + api: 'google-generative-ai', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 0.5, + output: 3, + cacheRead: 0.05, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gemini-3.1-pro', + name: 'Gemini 3.1 Pro Preview', + config: { + api: 'google-generative-ai', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 2, + output: 12, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gemini-3.5-flash', + name: 'Gemini 3.5 Flash', + config: { + api: 'google-generative-ai', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 1.5, + output: 9, + cacheRead: 0.15, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gemini-3.5-flash-lite', + name: 'Gemini 3.5 Flash Lite', + config: { + api: 'google-generative-ai', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 0.3, + output: 2.5, + cacheRead: 0.03, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gemini-3.6-flash', + name: 'Gemini 3.6 Flash', + config: { + api: 'google-generative-ai', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 1.5, + output: 7.5, + cacheRead: 0.15, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'glm-5', + name: 'GLM-5', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 204800, + maxTokens: 131072, + cost: { + input: 1, + output: 3.2, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'glm-5.1', + name: 'GLM-5.1', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 204800, + maxTokens: 131072, + cost: { + input: 1.4, + output: 4.4, + cacheRead: 0.26, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'glm-5.2', + name: 'GLM-5.2', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1000000, + maxTokens: 131072, + cost: { + input: 1.4, + output: 4.4, + cacheRead: 0.26, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5', + name: 'GPT-5', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.07, + output: 8.5, + cacheRead: 0.107, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5-codex', + name: 'GPT-5 Codex', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.07, + output: 8.5, + cacheRead: 0.107, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5-nano', + name: 'GPT-5 Nano', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 0.05, + output: 0.4, + cacheRead: 0.005, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.1', + name: 'GPT-5.1', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.07, + output: 8.5, + cacheRead: 0.107, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.1-codex', + name: 'GPT-5.1 Codex', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.07, + output: 8.5, + cacheRead: 0.107, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.1-codex-max', + name: 'GPT-5.1 Codex Max', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.25, + output: 10, + cacheRead: 0.125, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.1-codex-mini', + name: 'GPT-5.1 Codex Mini', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 0.25, + output: 2, + cacheRead: 0.025, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.2', + name: 'GPT-5.2', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.75, + output: 14, + cacheRead: 0.175, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.2-codex', + name: 'GPT-5.2 Codex', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.75, + output: 14, + cacheRead: 0.175, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.3-codex', + name: 'GPT-5.3 Codex', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.75, + output: 14, + cacheRead: 0.175, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.4', + name: 'GPT-5.4', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 272000, + maxTokens: 128000, + cost: { + input: 2.5, + output: 15, + cacheRead: 0.25, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.4-mini', + name: 'GPT-5.4 Mini', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 0.75, + output: 4.5, + cacheRead: 0.075, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.4-nano', + name: 'GPT-5.4 Nano', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 0.2, + output: 1.25, + cacheRead: 0.02, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.4-pro', + name: 'GPT-5.4 Pro', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 128000, + cost: { + input: 30, + output: 180, + cacheRead: 30, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.5', + name: 'GPT-5.5', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 128000, + cost: { + input: 5, + output: 30, + cacheRead: 0.5, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.5-pro', + name: 'GPT-5.5 Pro', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 128000, + cost: { + input: 30, + output: 180, + cacheRead: 30, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'gpt-5.6-luna', + name: 'GPT-5.6 Luna', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 128000, + cost: { + input: 1, + output: 6, + cacheRead: 0.1, + cacheWrite: 1.25, + }, + }, + }, + { + modelId: 'gpt-5.6-sol', + name: 'GPT-5.6 Sol', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 128000, + cost: { + input: 5, + output: 30, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'gpt-5.6-terra', + name: 'GPT-5.6 Terra', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 128000, + cost: { + input: 2.5, + output: 15, + cacheRead: 0.25, + cacheWrite: 3.125, + }, + }, + }, + { + modelId: 'grok-4.5', + name: 'Grok 4.5', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 500000, + maxTokens: 500000, + cost: { + input: 2, + output: 6, + cacheRead: 0.5, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'grok-build-0.1', + name: 'Grok Build 0.1', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 256000, + maxTokens: 256000, + cost: { + input: 1, + output: 2, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'kimi-k2.5', + name: 'Kimi K2.5', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 65536, + cost: { + input: 0.6, + output: 3, + cacheRead: 0.08, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'kimi-k2.6', + name: 'Kimi K2.6', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 65536, + cost: { + input: 0.95, + output: 4, + cacheRead: 0.16, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'kimi-k2.7-code', + name: 'Kimi K2.7 Code', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0.95, + output: 4, + cacheRead: 0.19, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'laguna-s-2.1-free', + name: 'Laguna S 2.1 Free', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 256000, + maxTokens: 32000, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mimo-v2.5-free', + name: 'MiMo V2.5 Free', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 32000, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'minimax-m2.5', + name: 'MiniMax-M2.5', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 204800, + maxTokens: 131072, + cost: { + input: 0.3, + output: 1.2, + cacheRead: 0.06, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'minimax-m2.7', + name: 'MiniMax-M2.7', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 204800, + maxTokens: 131072, + cost: { + input: 0.3, + output: 1.2, + cacheRead: 0.06, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'minimax-m3', + name: 'MiniMax-M3', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 512000, + maxTokens: 128000, + cost: { + input: 0.3, + output: 1.2, + cacheRead: 0.06, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'nemotron-3-ultra-free', + name: 'Nemotron 3 Ultra Free', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'north-mini-code-free', + name: 'North Mini Code Free', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 256000, + maxTokens: 64000, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen3.5-plus', + name: 'Qwen3.5 Plus', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 65536, + cost: { + input: 0.2, + output: 1.2, + cacheRead: 0.02, + cacheWrite: 0.25, + }, + }, + }, + { + modelId: 'qwen3.6-plus', + name: 'Qwen3.6 Plus', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 65536, + cost: { + input: 0.5, + output: 3, + cacheRead: 0.05, + cacheWrite: 0.625, + }, + }, + }, + ], +} as const diff --git a/packages/core/src/generated/providers/openrouter.ts b/packages/core/src/generated/providers/openrouter.ts new file mode 100644 index 00000000..6c60dcf2 --- /dev/null +++ b/packages/core/src/generated/providers/openrouter.ts @@ -0,0 +1,4655 @@ +// This file is auto-generated by scripts/generate-builtin-providers.ts +// Do not edit manually - run 'bun run generate-providers' to update + +export const providerName = 'openrouter' +export const providerConfig = { + name: 'openrouter', + config: { + api: 'openai-completions', + baseUrl: 'https://openrouter.ai/api/v1', + apiKey: 'OPENROUTER_API_KEY', + }, + models: [ + { + modelId: 'ai21/jamba-large-1.7', + name: 'AI21: Jamba Large 1.7', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 256000, + maxTokens: 4096, + cost: { + input: 2, + output: 8, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'aion-labs/aion-2.0', + name: 'AionLabs: Aion-2.0', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 32768, + cost: { + input: 0.8, + output: 1.6, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'aion-labs/aion-3.0', + name: 'AionLabs: Aion-3.0', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 32768, + cost: { + input: 3, + output: 6, + cacheRead: 0.75, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'aion-labs/aion-3.0-mini', + name: 'AionLabs: Aion-3.0-Mini', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 32768, + cost: { + input: 0.7, + output: 1.4, + cacheRead: 0.18, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'amazon/nova-2-lite-v1', + name: 'Amazon: Nova 2 Lite', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 65535, + cost: { + input: 0.3, + output: 2.5, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'amazon/nova-lite-v1', + name: 'Amazon: Nova Lite 1.0', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 300000, + maxTokens: 5120, + cost: { + input: 0.06, + output: 0.24, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'amazon/nova-micro-v1', + name: 'Amazon: Nova Micro 1.0', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 128000, + maxTokens: 5120, + cost: { + input: 0.035, + output: 0.14, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'amazon/nova-premier-v1', + name: 'Amazon: Nova Premier 1.0', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 32000, + cost: { + input: 2.5, + output: 12.5, + cacheRead: 0.625, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'amazon/nova-pro-v1', + name: 'Amazon: Nova Pro 1.0', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 300000, + maxTokens: 5120, + cost: { + input: 0.8, + output: 3.2, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'anthropic/claude-3-haiku', + name: 'Anthropic: Claude 3 Haiku', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 4096, + cost: { + input: 0.25, + output: 1.25, + cacheRead: 0.03, + cacheWrite: 0.3, + }, + }, + }, + { + modelId: 'anthropic/claude-fable-5', + name: 'Anthropic: Claude Fable 5', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 10, + output: 50, + cacheRead: 1, + cacheWrite: 12.5, + }, + }, + }, + { + modelId: 'anthropic/claude-haiku-4.5', + name: 'Anthropic: Claude Haiku 4.5', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 64000, + cost: { + input: 1, + output: 5, + cacheRead: 0.1, + cacheWrite: 1.25, + }, + }, + }, + { + modelId: 'anthropic/claude-opus-4', + name: 'Anthropic: Claude Opus 4', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 32000, + cost: { + input: 15, + output: 75, + cacheRead: 1.5, + cacheWrite: 18.75, + }, + }, + }, + { + modelId: 'anthropic/claude-opus-4.1', + name: 'Anthropic: Claude Opus 4.1', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 32000, + cost: { + input: 15, + output: 75, + cacheRead: 1.5, + cacheWrite: 18.75, + }, + }, + }, + { + modelId: 'anthropic/claude-opus-4.5', + name: 'Anthropic: Claude Opus 4.5', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 64000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'anthropic/claude-opus-4.6', + name: 'Anthropic: Claude Opus 4.6', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'anthropic/claude-opus-4.7', + name: 'Anthropic: Claude Opus 4.7', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'anthropic/claude-opus-4.7-fast', + name: 'Anthropic: Claude Opus 4.7 (Fast)', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 30, + output: 150, + cacheRead: 3, + cacheWrite: 37.5, + }, + }, + }, + { + modelId: 'anthropic/claude-opus-4.8', + name: 'Anthropic: Claude Opus 4.8', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'anthropic/claude-opus-4.8-fast', + name: 'Anthropic: Claude Opus 4.8 (Fast)', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 10, + output: 50, + cacheRead: 1, + cacheWrite: 12.5, + }, + }, + }, + { + modelId: 'anthropic/claude-sonnet-4', + name: 'Anthropic: Claude Sonnet 4', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 64000, + cost: { + input: 3, + output: 15, + cacheRead: 0.3, + cacheWrite: 3.75, + }, + }, + }, + { + modelId: 'anthropic/claude-sonnet-4.5', + name: 'Anthropic: Claude Sonnet 4.5', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 64000, + cost: { + input: 3, + output: 15, + cacheRead: 0.3, + cacheWrite: 3.75, + }, + }, + }, + { + modelId: 'anthropic/claude-sonnet-4.6', + name: 'Anthropic: Claude Sonnet 4.6', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 3, + output: 15, + cacheRead: 0.3, + cacheWrite: 3.75, + }, + }, + }, + { + modelId: 'anthropic/claude-sonnet-5', + name: 'Anthropic: Claude Sonnet 5', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 2, + output: 10, + cacheRead: 0.2, + cacheWrite: 2.5, + }, + }, + }, + { + modelId: 'arcee-ai/trinity-large-thinking', + name: 'Arcee AI: Trinity Large Thinking', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 262144, + maxTokens: 80000, + cost: { + input: 0.25, + output: 0.8, + cacheRead: 0.06, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'arcee-ai/virtuoso-large', + name: 'Arcee AI: Virtuoso Large', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 131072, + maxTokens: 64000, + cost: { + input: 0.75, + output: 1.2, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'auto', + name: 'Auto', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 2000000, + maxTokens: 30000, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'bytedance-seed/seed-1.6', + name: 'ByteDance Seed: Seed 1.6', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 32768, + cost: { + input: 0.25, + output: 2, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'bytedance-seed/seed-1.6-flash', + name: 'ByteDance Seed: Seed 1.6 Flash', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 32768, + cost: { + input: 0.075, + output: 0.3, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'bytedance-seed/seed-2.0-lite', + name: 'ByteDance Seed: Seed-2.0-Lite', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 131072, + cost: { + input: 0.25, + output: 2, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'bytedance-seed/seed-2.0-mini', + name: 'ByteDance Seed: Seed-2.0-Mini', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 131072, + cost: { + input: 0.1, + output: 0.4, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'cohere/command-r-08-2024', + name: 'Cohere: Command R (08-2024)', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 128000, + maxTokens: 4000, + cost: { + input: 0.15, + output: 0.6, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'cohere/command-r-plus-08-2024', + name: 'Cohere: Command R+ (08-2024)', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 128000, + maxTokens: 4000, + cost: { + input: 2.5, + output: 10, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'cohere/north-mini-code:free', + name: 'Cohere: North Mini Code (free)', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 256000, + maxTokens: 64000, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'deepseek/deepseek-chat', + name: 'DeepSeek: DeepSeek V3', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 128000, + maxTokens: 16000, + cost: { + input: 0.2002, + output: 0.8001, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'deepseek/deepseek-chat-v3-0324', + name: 'DeepSeek: DeepSeek V3 0324', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 163840, + maxTokens: 65536, + cost: { + input: 0.27, + output: 1.12, + cacheRead: 0.135, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'deepseek/deepseek-chat-v3.1', + name: 'DeepSeek: DeepSeek V3.1', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 163840, + maxTokens: 32768, + cost: { + input: 0.25, + output: 0.95, + cacheRead: 0.13, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'deepseek/deepseek-r1', + name: 'DeepSeek: R1', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 64000, + maxTokens: 16000, + cost: { + input: 0.7, + output: 2.5, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'deepseek/deepseek-r1-0528', + name: 'DeepSeek: R1 0528', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 163840, + maxTokens: 32768, + cost: { + input: 0.5, + output: 2.15, + cacheRead: 0.35, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'deepseek/deepseek-v3.1-terminus', + name: 'DeepSeek: DeepSeek V3.1 Terminus', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 32768, + cost: { + input: 0.27, + output: 1, + cacheRead: 0.135, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'deepseek/deepseek-v3.2', + name: 'DeepSeek: DeepSeek V3.2', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 163840, + maxTokens: 65536, + cost: { + input: 0.269, + output: 0.4, + cacheRead: 0.1345, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'deepseek/deepseek-v3.2-exp', + name: 'DeepSeek: DeepSeek V3.2 Exp', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 163840, + maxTokens: 65536, + cost: { + input: 0.27, + output: 0.41, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'deepseek/deepseek-v4-flash', + name: 'DeepSeek: DeepSeek V4 Flash', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1048575, + maxTokens: 4096, + cost: { + input: 0.0938, + output: 0.1876, + cacheRead: 0.01876, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'deepseek/deepseek-v4-pro', + name: 'DeepSeek: DeepSeek V4 Pro', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1048576, + maxTokens: 384000, + cost: { + input: 0.435, + output: 0.87, + cacheRead: 0.003625, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'google/gemini-2.5-flash', + name: 'Google: Gemini 2.5 Flash', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65535, + cost: { + input: 0.3, + output: 2.5, + cacheRead: 0.03, + cacheWrite: 0.083333, + }, + }, + }, + { + modelId: 'google/gemini-2.5-flash-lite', + name: 'Google: Gemini 2.5 Flash Lite', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65535, + cost: { + input: 0.1, + output: 0.4, + cacheRead: 0.01, + cacheWrite: 0.083333, + }, + }, + }, + { + modelId: 'google/gemini-2.5-pro', + name: 'Google: Gemini 2.5 Pro', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 1.25, + output: 10, + cacheRead: 0.125, + cacheWrite: 0.375, + }, + }, + }, + { + modelId: 'google/gemini-2.5-pro-preview', + name: 'Google: Gemini 2.5 Pro Preview 06-05', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 1.25, + output: 10, + cacheRead: 0.125, + cacheWrite: 0.375, + }, + }, + }, + { + modelId: 'google/gemini-2.5-pro-preview-05-06', + name: 'Google: Gemini 2.5 Pro Preview 05-06', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65535, + cost: { + input: 1.25, + output: 10, + cacheRead: 0.125, + cacheWrite: 0.375, + }, + }, + }, + { + modelId: 'google/gemini-3-flash-preview', + name: 'Google: Gemini 3 Flash Preview', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65535, + cost: { + input: 0.5, + output: 3, + cacheRead: 0.05, + cacheWrite: 0.083333, + }, + }, + }, + { + modelId: 'google/gemini-3-pro-image', + name: 'Google: Nano Banana Pro (Gemini 3 Pro Image)', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 65536, + maxTokens: 32768, + cost: { + input: 2, + output: 12, + cacheRead: 0.2, + cacheWrite: 0.375, + }, + }, + }, + { + modelId: 'google/gemini-3.1-flash-lite', + name: 'Google: Gemini 3.1 Flash Lite', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 0.25, + output: 1.5, + cacheRead: 0.025, + cacheWrite: 0.083333, + }, + }, + }, + { + modelId: 'google/gemini-3.1-flash-lite-preview', + name: 'Google: Gemini 3.1 Flash Lite Preview', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 0.25, + output: 1.5, + cacheRead: 0.025, + cacheWrite: 0.083333, + }, + }, + }, + { + modelId: 'google/gemini-3.1-pro-preview', + name: 'Google: Gemini 3.1 Pro Preview', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 2, + output: 12, + cacheRead: 0.2, + cacheWrite: 0.375, + }, + }, + }, + { + modelId: 'google/gemini-3.1-pro-preview-customtools', + name: 'Google: Gemini 3.1 Pro Preview Custom Tools', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 2, + output: 12, + cacheRead: 0.2, + cacheWrite: 0.375, + }, + }, + }, + { + modelId: 'google/gemini-3.5-flash', + name: 'Google: Gemini 3.5 Flash', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 1.5, + output: 9, + cacheRead: 0.15, + cacheWrite: 0.083333, + }, + }, + }, + { + modelId: 'google/gemini-3.5-flash-lite', + name: 'Google: Gemini 3.5 Flash-Lite', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 0.3, + output: 2.5, + cacheRead: 0.03, + cacheWrite: 0.083333, + }, + }, + }, + { + modelId: 'google/gemini-3.6-flash', + name: 'Google: Gemini 3.6 Flash', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 1.5, + output: 7.5, + cacheRead: 0.15, + cacheWrite: 0.083333, + }, + }, + }, + { + modelId: 'google/gemma-3-12b-it', + name: 'Google: Gemma 3 12B', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 131072, + maxTokens: 16384, + cost: { + input: 0.05, + output: 0.15, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'google/gemma-3-27b-it', + name: 'Google: Gemma 3 27B', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 110000, + maxTokens: 4096, + cost: { + input: 0.1, + output: 0.3, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'google/gemma-4-26b-a4b-it', + name: 'Google: Gemma 4 26B A4B ', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 16384, + cost: { + input: 0.07, + output: 0.34, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'google/gemma-4-26b-a4b-it:free', + name: 'Google: Gemma 4 26B A4B (free)', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 131072, + maxTokens: 32768, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'google/gemma-4-31b-it', + name: 'Google: Gemma 4 31B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 16384, + cost: { + input: 0.12, + output: 0.37, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'google/gemma-4-31b-it:free', + name: 'Google: Gemma 4 31B (free)', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 32768, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'ibm-granite/granite-4.1-8b', + name: 'IBM: Granite 4.1 8B', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 131072, + maxTokens: 131072, + cost: { + input: 0.05, + output: 0.1, + cacheRead: 0.05, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'inception/mercury-2', + name: 'Inception: Mercury 2', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 128000, + maxTokens: 50000, + cost: { + input: 0.25, + output: 0.75, + cacheRead: 0.025, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'inclusionai/ling-2.6-1t', + name: 'inclusionAI: Ling-2.6-1T', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 262144, + maxTokens: 32768, + cost: { + input: 0.075, + output: 0.625, + cacheRead: 0.015, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'inclusionai/ling-2.6-flash', + name: 'inclusionAI: Ling-2.6-flash', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 262144, + maxTokens: 32768, + cost: { + input: 0.01, + output: 0.03, + cacheRead: 0.002, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'inclusionai/ring-2.6-1t', + name: 'inclusionAI: Ring-2.6-1T', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 262144, + maxTokens: 65536, + cost: { + input: 0.075, + output: 0.625, + cacheRead: 0.015, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'kwaipilot/kat-coder-air-v2.5', + name: 'Kwaipilot: KAT-Coder-Air V2.5', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 256000, + maxTokens: 80000, + cost: { + input: 0.15, + output: 0.6, + cacheRead: 0.03, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'kwaipilot/kat-coder-pro-v2', + name: 'Kwaipilot: KAT-Coder-Pro V2', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 256000, + maxTokens: 80000, + cost: { + input: 0.3, + output: 1.2, + cacheRead: 0.06, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'kwaipilot/kat-coder-pro-v2.5', + name: 'Kwaipilot: KAT-Coder-Pro V2.5', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 256000, + maxTokens: 80000, + cost: { + input: 0.74, + output: 2.96, + cacheRead: 0.15, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'meituan/longcat-2.0', + name: 'Meituan: LongCat 2.0', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1048756, + maxTokens: 262144, + cost: { + input: 0.3, + output: 1.2, + cacheRead: 0.006, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'meta-llama/llama-3.1-70b-instruct', + name: 'Meta: Llama 3.1 70B Instruct', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 131072, + maxTokens: 16384, + cost: { + input: 0.4, + output: 0.4, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'meta-llama/llama-3.1-8b-instruct', + name: 'Meta: Llama 3.1 8B Instruct', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 131072, + maxTokens: 131072, + cost: { + input: 0.05, + output: 0.08, + cacheRead: 0.025, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'meta-llama/llama-3.3-70b-instruct', + name: 'Meta: Llama 3.3 70B Instruct', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 131072, + maxTokens: 128000, + cost: { + input: 0.13, + output: 0.4, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'meta-llama/llama-4-maverick', + name: 'Meta: Llama 4 Maverick', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 16384, + cost: { + input: 0.2, + output: 0.8, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'meta-llama/llama-4-scout', + name: 'Meta: Llama 4 Scout', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 327680, + maxTokens: 16384, + cost: { + input: 0.1, + output: 0.3, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'meta/muse-spark-1.1', + name: 'Meta: Muse Spark 1.1', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 4096, + cost: { + input: 1.25, + output: 4.25, + cacheRead: 0.15, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'minimax/minimax-m1', + name: 'MiniMax: MiniMax M1', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1000000, + maxTokens: 40000, + cost: { + input: 0.55, + output: 2.2, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'minimax/minimax-m2', + name: 'MiniMax: MiniMax M2', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 204800, + maxTokens: 131072, + cost: { + input: 0.3, + output: 1.2, + cacheRead: 0.03, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'minimax/minimax-m2.1', + name: 'MiniMax: MiniMax M2.1', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 204800, + maxTokens: 131072, + cost: { + input: 0.3, + output: 1.2, + cacheRead: 0.03, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'minimax/minimax-m2.5', + name: 'MiniMax: MiniMax M2.5', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 196608, + maxTokens: 196608, + cost: { + input: 0.15, + output: 0.9, + cacheRead: 0.05, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'minimax/minimax-m2.7', + name: 'MiniMax: MiniMax M2.7', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 196608, + maxTokens: 131072, + cost: { + input: 0.25, + output: 1, + cacheRead: 0.05, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'minimax/minimax-m3', + name: 'MiniMax: MiniMax M3', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 524288, + maxTokens: 512000, + cost: { + input: 0.3, + output: 1.2, + cacheRead: 0.06, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistralai/codestral-2508', + name: 'Mistral: Codestral 2508', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 256000, + maxTokens: 4096, + cost: { + input: 0.3, + output: 0.9, + cacheRead: 0.03, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistralai/devstral-2512', + name: 'Mistral: Devstral 2 2512', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 262144, + maxTokens: 4096, + cost: { + input: 0.4, + output: 2, + cacheRead: 0.04, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistralai/ministral-14b-2512', + name: 'Mistral: Ministral 3 14B 2512', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 4096, + cost: { + input: 0.2, + output: 0.2, + cacheRead: 0.02, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistralai/ministral-3b-2512', + name: 'Mistral: Ministral 3 3B 2512', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 131072, + maxTokens: 4096, + cost: { + input: 0.1, + output: 0.1, + cacheRead: 0.01, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistralai/ministral-8b-2512', + name: 'Mistral: Ministral 3 8B 2512', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 4096, + cost: { + input: 0.15, + output: 0.15, + cacheRead: 0.015, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistralai/mistral-large', + name: 'Mistral Large', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 128000, + maxTokens: 4096, + cost: { + input: 2, + output: 6, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistralai/mistral-large-2407', + name: 'Mistral Large 2407', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 131072, + maxTokens: 4096, + cost: { + input: 2, + output: 6, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistralai/mistral-large-2512', + name: 'Mistral: Mistral Large 3 2512', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 4096, + cost: { + input: 0.5, + output: 1.5, + cacheRead: 0.05, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistralai/mistral-medium-3', + name: 'Mistral: Mistral Medium 3', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 131072, + maxTokens: 4096, + cost: { + input: 0.4, + output: 2, + cacheRead: 0.04, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistralai/mistral-medium-3-5', + name: 'Mistral: Mistral Medium 3.5', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 4096, + cost: { + input: 1.5, + output: 7.5, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistralai/mistral-medium-3.1', + name: 'Mistral: Mistral Medium 3.1', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 131072, + maxTokens: 4096, + cost: { + input: 0.4, + output: 2, + cacheRead: 0.04, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistralai/mistral-nemo', + name: 'Mistral: Mistral Nemo', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 131072, + maxTokens: 16384, + cost: { + input: 0.019, + output: 0.03, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistralai/mistral-saba', + name: 'Mistral: Saba', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 32768, + maxTokens: 4096, + cost: { + input: 0.2, + output: 0.6, + cacheRead: 0.02, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistralai/mistral-small-2603', + name: 'Mistral: Mistral Small 4', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 4096, + cost: { + input: 0.15, + output: 0.6, + cacheRead: 0.015, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistralai/mistral-small-3.2-24b-instruct', + name: 'Mistral: Mistral Small 3.2 24B', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 131072, + maxTokens: 4096, + cost: { + input: 0.1, + output: 0.3, + cacheRead: 0.01, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistralai/mixtral-8x22b-instruct', + name: 'Mistral: Mixtral 8x22B Instruct', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 65536, + maxTokens: 4096, + cost: { + input: 2, + output: 6, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistralai/voxtral-small-24b-2507', + name: 'Mistral: Voxtral Small 24B 2507', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 32000, + maxTokens: 4096, + cost: { + input: 0.1, + output: 0.3, + cacheRead: 0.01, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'moonshotai/kimi-k2', + name: 'MoonshotAI: Kimi K2 0711', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 131072, + maxTokens: 100352, + cost: { + input: 0.57, + output: 2.3, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'moonshotai/kimi-k2-0905', + name: 'MoonshotAI: Kimi K2 0905', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 262144, + maxTokens: 100352, + cost: { + input: 0.6, + output: 2.5, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'moonshotai/kimi-k2-thinking', + name: 'MoonshotAI: Kimi K2 Thinking', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 262144, + maxTokens: 100352, + cost: { + input: 0.6, + output: 2.5, + cacheRead: 0.15, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'moonshotai/kimi-k2.5', + name: 'MoonshotAI: Kimi K2.5', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 4096, + cost: { + input: 0.41, + output: 2.06, + cacheRead: 0.07, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'moonshotai/kimi-k2.6', + name: 'MoonshotAI: Kimi K2.6', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0.684, + output: 3.42, + cacheRead: 0.144, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'moonshotai/kimi-k2.7-code', + name: 'MoonshotAI: Kimi K2.7 Code', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0.82, + output: 3.75, + cacheRead: 0.16, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'moonshotai/kimi-k3', + name: 'MoonshotAI: Kimi K3', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 131072, + cost: { + input: 3, + output: 15, + cacheRead: 0.3, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'nex-agi/nex-n2-mini', + name: 'Nex AGI: Nex-N2-Mini', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0.025, + output: 0.1, + cacheRead: 0.0025, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'nex-agi/nex-n2-pro', + name: 'Nex AGI: Nex-N2-Pro', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0.25, + output: 1, + cacheRead: 0.025, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'nvidia/nemotron-3-nano-30b-a3b', + name: 'NVIDIA: Nemotron 3 Nano 30B A3B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 262144, + maxTokens: 228000, + cost: { + input: 0.05, + output: 0.2, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'nvidia/nemotron-3-nano-30b-a3b:free', + name: 'NVIDIA: Nemotron 3 Nano 30B A3B (free)', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 256000, + maxTokens: 4096, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free', + name: 'NVIDIA: Nemotron 3 Nano Omni (free)', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 256000, + maxTokens: 65536, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'nvidia/nemotron-3-super-120b-a12b', + name: 'NVIDIA: Nemotron 3 Super', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 262144, + maxTokens: 4096, + cost: { + input: 0.08, + output: 0.45, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'nvidia/nemotron-3-super-120b-a12b:free', + name: 'NVIDIA: Nemotron 3 Super (free)', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'nvidia/nemotron-3-ultra-550b-a55b', + name: 'NVIDIA: Nemotron 3 Ultra', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 512288, + maxTokens: 4096, + cost: { + input: 0.6, + output: 3.6, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'nvidia/nemotron-3-ultra-550b-a55b:free', + name: 'NVIDIA: Nemotron 3 Ultra (free)', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1000000, + maxTokens: 65536, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'nvidia/nemotron-nano-12b-v2-vl:free', + name: 'NVIDIA: Nemotron Nano 12B 2 VL (free)', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 128000, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'nvidia/nemotron-nano-9b-v2:free', + name: 'NVIDIA: Nemotron Nano 9B V2 (free)', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 128000, + maxTokens: 4096, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-3.5-turbo', + name: 'OpenAI: GPT-3.5 Turbo', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 16385, + maxTokens: 4096, + cost: { + input: 0.5, + output: 1.5, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-3.5-turbo-0613', + name: 'OpenAI: GPT-3.5 Turbo (older v0613)', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 4095, + maxTokens: 4096, + cost: { + input: 1, + output: 2, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-3.5-turbo-16k', + name: 'OpenAI: GPT-3.5 Turbo 16k', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 16385, + maxTokens: 4096, + cost: { + input: 3, + output: 4, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-4', + name: 'OpenAI: GPT-4', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 8191, + maxTokens: 4096, + cost: { + input: 30, + output: 60, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-4-turbo', + name: 'OpenAI: GPT-4 Turbo', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 4096, + cost: { + input: 10, + output: 30, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-4-turbo-preview', + name: 'OpenAI: GPT-4 Turbo Preview', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 128000, + maxTokens: 4096, + cost: { + input: 10, + output: 30, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-4.1', + name: 'OpenAI: GPT-4.1', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 1047576, + maxTokens: 32768, + cost: { + input: 2, + output: 8, + cacheRead: 0.5, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-4.1-mini', + name: 'OpenAI: GPT-4.1 Mini', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 1047576, + maxTokens: 32768, + cost: { + input: 0.4, + output: 1.6, + cacheRead: 0.1, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-4.1-nano', + name: 'OpenAI: GPT-4.1 Nano', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 1047576, + maxTokens: 32768, + cost: { + input: 0.1, + output: 0.4, + cacheRead: 0.025, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-4o', + name: 'OpenAI: GPT-4o', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 2.5, + output: 10, + cacheRead: 1.25, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-4o-2024-05-13', + name: 'OpenAI: GPT-4o (2024-05-13)', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 4096, + cost: { + input: 5, + output: 15, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-4o-2024-08-06', + name: 'OpenAI: GPT-4o (2024-08-06)', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 2.5, + output: 10, + cacheRead: 1.25, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-4o-2024-11-20', + name: 'OpenAI: GPT-4o (2024-11-20)', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 2.5, + output: 10, + cacheRead: 1.25, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-4o-mini', + name: 'OpenAI: GPT-4o-mini', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 0.15, + output: 0.6, + cacheRead: 0.075, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-4o-mini-2024-07-18', + name: 'OpenAI: GPT-4o-mini (2024-07-18)', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 0.15, + output: 0.6, + cacheRead: 0.075, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5', + name: 'OpenAI: GPT-5', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.25, + output: 10, + cacheRead: 0.125, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5-codex', + name: 'OpenAI: GPT-5 Codex', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.25, + output: 10, + cacheRead: 0.125, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5-mini', + name: 'OpenAI: GPT-5 Mini', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 0.25, + output: 2, + cacheRead: 0.025, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5-nano', + name: 'OpenAI: GPT-5 Nano', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 0.05, + output: 0.4, + cacheRead: 0.005, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5-pro', + name: 'OpenAI: GPT-5 Pro', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 15, + output: 120, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5.1', + name: 'OpenAI: GPT-5.1', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.25, + output: 10, + cacheRead: 0.125, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5.1-chat', + name: 'OpenAI: GPT-5.1 Chat', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 1.25, + output: 10, + cacheRead: 0.125, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5.1-codex', + name: 'OpenAI: GPT-5.1-Codex', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.25, + output: 10, + cacheRead: 0.125, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5.1-codex-max', + name: 'OpenAI: GPT-5.1-Codex-Max', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.25, + output: 10, + cacheRead: 0.125, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5.1-codex-mini', + name: 'OpenAI: GPT-5.1-Codex-Mini', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 100000, + cost: { + input: 0.25, + output: 2, + cacheRead: 0.025, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5.2', + name: 'OpenAI: GPT-5.2', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.75, + output: 14, + cacheRead: 0.175, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5.2-chat', + name: 'OpenAI: GPT-5.2 Chat', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 1.75, + output: 14, + cacheRead: 0.175, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5.2-codex', + name: 'OpenAI: GPT-5.2-Codex', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.75, + output: 14, + cacheRead: 0.175, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5.2-pro', + name: 'OpenAI: GPT-5.2 Pro', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 21, + output: 168, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5.3-chat', + name: 'OpenAI: GPT-5.3 Chat', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 1.75, + output: 14, + cacheRead: 0.175, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5.3-codex', + name: 'OpenAI: GPT-5.3-Codex', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.75, + output: 14, + cacheRead: 0.175, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5.4', + name: 'OpenAI: GPT-5.4', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 128000, + cost: { + input: 2.5, + output: 15, + cacheRead: 0.25, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5.4-mini', + name: 'OpenAI: GPT-5.4 Mini', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 0.75, + output: 4.5, + cacheRead: 0.075, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5.4-nano', + name: 'OpenAI: GPT-5.4 Nano', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 0.2, + output: 1.25, + cacheRead: 0.02, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5.4-pro', + name: 'OpenAI: GPT-5.4 Pro', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 128000, + cost: { + input: 30, + output: 180, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5.5', + name: 'OpenAI: GPT-5.5', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 128000, + cost: { + input: 5, + output: 30, + cacheRead: 0.5, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5.5-pro', + name: 'OpenAI: GPT-5.5 Pro', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 128000, + cost: { + input: 30, + output: 180, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5.6-luna', + name: 'OpenAI: GPT-5.6 Luna', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 128000, + cost: { + input: 1, + output: 6, + cacheRead: 0.1, + cacheWrite: 1.25, + }, + }, + }, + { + modelId: 'openai/gpt-5.6-luna-pro', + name: 'OpenAI: GPT-5.6 Luna Pro', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 128000, + cost: { + input: 1, + output: 6, + cacheRead: 0.1, + cacheWrite: 1.25, + }, + }, + }, + { + modelId: 'openai/gpt-5.6-sol', + name: 'OpenAI: GPT-5.6 Sol', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 128000, + cost: { + input: 5, + output: 30, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'openai/gpt-5.6-sol-pro', + name: 'OpenAI: GPT-5.6 Sol Pro', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 128000, + cost: { + input: 5, + output: 30, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'openai/gpt-5.6-terra', + name: 'OpenAI: GPT-5.6 Terra', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 128000, + cost: { + input: 2.5, + output: 15, + cacheRead: 0.25, + cacheWrite: 3.125, + }, + }, + }, + { + modelId: 'openai/gpt-5.6-terra-pro', + name: 'OpenAI: GPT-5.6 Terra Pro', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 128000, + cost: { + input: 2.5, + output: 15, + cacheRead: 0.25, + cacheWrite: 3.125, + }, + }, + }, + { + modelId: 'openai/gpt-audio', + name: 'OpenAI: GPT Audio', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 2.5, + output: 10, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-audio-mini', + name: 'OpenAI: GPT Audio Mini', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 0.6, + output: 2.4, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-chat-latest', + name: 'OpenAI: GPT Chat Latest', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 5, + output: 30, + cacheRead: 0.5, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-oss-120b', + name: 'OpenAI: gpt-oss-120b', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 131072, + cost: { + input: 0.037, + output: 0.17, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-oss-20b', + name: 'OpenAI: gpt-oss-20b', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 131072, + cost: { + input: 0.03, + output: 0.13, + cacheRead: 0.03, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-oss-20b:free', + name: 'OpenAI: gpt-oss-20b (free)', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 32768, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-oss-safeguard-20b', + name: 'OpenAI: gpt-oss-safeguard-20b', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 65536, + cost: { + input: 0.075, + output: 0.3, + cacheRead: 0.0375, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/o1', + name: 'OpenAI: o1', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 100000, + cost: { + input: 15, + output: 60, + cacheRead: 7.5, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/o3', + name: 'OpenAI: o3', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 100000, + cost: { + input: 2, + output: 8, + cacheRead: 0.5, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/o3-deep-research', + name: 'OpenAI: o3 Deep Research', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 100000, + cost: { + input: 10, + output: 40, + cacheRead: 2.5, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/o3-mini', + name: 'OpenAI: o3 Mini', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 200000, + maxTokens: 100000, + cost: { + input: 1.1, + output: 4.4, + cacheRead: 0.55, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/o3-mini-high', + name: 'OpenAI: o3 Mini High', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 200000, + maxTokens: 100000, + cost: { + input: 1.1, + output: 4.4, + cacheRead: 0.55, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/o3-pro', + name: 'OpenAI: o3 Pro', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 100000, + cost: { + input: 20, + output: 80, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/o4-mini', + name: 'OpenAI: o4 Mini', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 100000, + cost: { + input: 1.1, + output: 4.4, + cacheRead: 0.275, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/o4-mini-deep-research', + name: 'OpenAI: o4 Mini Deep Research', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 100000, + cost: { + input: 2, + output: 8, + cacheRead: 0.5, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/o4-mini-high', + name: 'OpenAI: o4 Mini High', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 100000, + cost: { + input: 1.1, + output: 4.4, + cacheRead: 0.275, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openrouter/auto', + name: 'Auto Router', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 2000000, + maxTokens: 4096, + cost: { + input: -1000000, + output: -1000000, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openrouter/auto-beta', + name: 'Auto Router (Beta)', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 2000000, + maxTokens: 4096, + cost: { + input: -1000000, + output: -1000000, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openrouter/free', + name: 'Free Models Router', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 4096, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openrouter/fusion', + name: 'OpenRouter: Fusion', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1000000, + maxTokens: 30000, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'poolside/laguna-m.1', + name: 'Poolside: Laguna M.1', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 262144, + maxTokens: 32768, + cost: { + input: 0.2, + output: 0.4, + cacheRead: 0.1, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'poolside/laguna-m.1:free', + name: 'Poolside: Laguna M.1 (free)', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 262144, + maxTokens: 32768, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'poolside/laguna-s-2.1', + name: 'Poolside: Laguna S 2.1', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1048576, + maxTokens: 131072, + cost: { + input: 0.1, + output: 0.2, + cacheRead: 0.01, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'poolside/laguna-s-2.1:free', + name: 'Poolside: Laguna S 2.1 (free)', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 262144, + maxTokens: 32768, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'poolside/laguna-xs-2.1', + name: 'Poolside: Laguna XS 2.1', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 262144, + maxTokens: 32768, + cost: { + input: 0.06, + output: 0.12, + cacheRead: 0.03, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'poolside/laguna-xs-2.1:free', + name: 'Poolside: Laguna XS 2.1 (free)', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 262144, + maxTokens: 32768, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen/qwen-2.5-72b-instruct', + name: 'Qwen2.5 72B Instruct', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 32768, + maxTokens: 16384, + cost: { + input: 0.36, + output: 0.4, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen/qwen-2.5-7b-instruct', + name: 'Qwen: Qwen2.5 7B Instruct', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 32768, + maxTokens: 32768, + cost: { + input: 0.04, + output: 0.1, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen/qwen-plus', + name: 'Qwen: Qwen-Plus', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 1000000, + maxTokens: 32768, + cost: { + input: 0.26, + output: 0.78, + cacheRead: 0.052, + cacheWrite: 0.325, + }, + }, + }, + { + modelId: 'qwen/qwen-plus-2025-07-28', + name: 'Qwen: Qwen Plus 0728', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 1000000, + maxTokens: 32768, + cost: { + input: 0.26, + output: 0.78, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen/qwen-plus-2025-07-28:thinking', + name: 'Qwen: Qwen Plus 0728 (thinking)', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1000000, + maxTokens: 32768, + cost: { + input: 0.26, + output: 0.78, + cacheRead: 0, + cacheWrite: 0.325, + }, + }, + }, + { + modelId: 'qwen/qwen3-14b', + name: 'Qwen: Qwen3 14B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 40960, + maxTokens: 16384, + cost: { + input: 0.12, + output: 0.24, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen/qwen3-235b-a22b', + name: 'Qwen: Qwen3 235B A22B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 8192, + cost: { + input: 0.455, + output: 1.82, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen/qwen3-235b-a22b-2507', + name: 'Qwen: Qwen3 235B A22B Instruct 2507', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 262144, + maxTokens: 16384, + cost: { + input: 0.09, + output: 0.55, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen/qwen3-235b-a22b-thinking-2507', + name: 'Qwen: Qwen3 235B A22B Thinking 2507', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 32768, + cost: { + input: 0.3, + output: 3, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen/qwen3-30b-a3b', + name: 'Qwen: Qwen3 30B A3B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 8192, + cost: { + input: 0.13, + output: 0.52, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen/qwen3-30b-a3b-instruct-2507', + name: 'Qwen: Qwen3 30B A3B Instruct 2507', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 262144, + maxTokens: 4096, + cost: { + input: 0.1, + output: 0.3, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen/qwen3-30b-a3b-thinking-2507', + name: 'Qwen: Qwen3 30B A3B Thinking 2507', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 81920, + maxTokens: 32768, + cost: { + input: 0.13, + output: 1.56, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen/qwen3-32b', + name: 'Qwen: Qwen3 32B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 40960, + maxTokens: 16384, + cost: { + input: 0.08, + output: 0.28, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen/qwen3-8b', + name: 'Qwen: Qwen3 8B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 8192, + cost: { + input: 0.117, + output: 0.455, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen/qwen3-coder', + name: 'Qwen: Qwen3 Coder 480B A35B', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 262144, + maxTokens: 65536, + cost: { + input: 0.3, + output: 1, + cacheRead: 0.1, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen/qwen3-coder-30b-a3b-instruct', + name: 'Qwen: Qwen3 Coder 30B A3B Instruct', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 160000, + maxTokens: 32768, + cost: { + input: 0.07, + output: 0.27, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen/qwen3-coder-flash', + name: 'Qwen: Qwen3 Coder Flash', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 1000000, + maxTokens: 65536, + cost: { + input: 0.195, + output: 0.975, + cacheRead: 0.039, + cacheWrite: 0.24375, + }, + }, + }, + { + modelId: 'qwen/qwen3-coder-next', + name: 'Qwen: Qwen3 Coder Next', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0.11, + output: 0.8, + cacheRead: 0.07, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen/qwen3-coder-plus', + name: 'Qwen: Qwen3 Coder Plus', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 1000000, + maxTokens: 65536, + cost: { + input: 0.65, + output: 3.25, + cacheRead: 0.13, + cacheWrite: 0.8125, + }, + }, + }, + { + modelId: 'qwen/qwen3-max', + name: 'Qwen: Qwen3 Max', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 262144, + maxTokens: 32768, + cost: { + input: 0.78, + output: 3.9, + cacheRead: 0.156, + cacheWrite: 0.975, + }, + }, + }, + { + modelId: 'qwen/qwen3-max-thinking', + name: 'Qwen: Qwen3 Max Thinking', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 262144, + maxTokens: 32768, + cost: { + input: 0.78, + output: 3.9, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen/qwen3-next-80b-a3b-instruct', + name: 'Qwen: Qwen3 Next 80B A3B Instruct', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0.1, + output: 1.1, + cacheRead: 0.07, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen/qwen3-next-80b-a3b-thinking', + name: 'Qwen: Qwen3 Next 80B A3B Thinking', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 32768, + cost: { + input: 0.0975, + output: 0.78, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen/qwen3-vl-235b-a22b-instruct', + name: 'Qwen: Qwen3 VL 235B A22B Instruct', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 131072, + maxTokens: 32768, + cost: { + input: 0.21, + output: 1.9, + cacheRead: 0.1, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen/qwen3-vl-235b-a22b-thinking', + name: 'Qwen: Qwen3 VL 235B A22B Thinking', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 131072, + maxTokens: 32768, + cost: { + input: 0.26, + output: 2.6, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen/qwen3-vl-30b-a3b-instruct', + name: 'Qwen: Qwen3 VL 30B A3B Instruct', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 131072, + maxTokens: 32768, + cost: { + input: 0.13, + output: 0.52, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen/qwen3-vl-30b-a3b-thinking', + name: 'Qwen: Qwen3 VL 30B A3B Thinking', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 131072, + maxTokens: 32768, + cost: { + input: 0.13, + output: 1.56, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen/qwen3-vl-32b-instruct', + name: 'Qwen: Qwen3 VL 32B Instruct', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 131072, + maxTokens: 32768, + cost: { + input: 0.104, + output: 0.416, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen/qwen3-vl-8b-instruct', + name: 'Qwen: Qwen3 VL 8B Instruct', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 131072, + maxTokens: 32768, + cost: { + input: 0.117, + output: 0.455, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen/qwen3-vl-8b-thinking', + name: 'Qwen: Qwen3 VL 8B Thinking', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 131072, + maxTokens: 32768, + cost: { + input: 0.117, + output: 1.365, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen/qwen3.5-122b-a10b', + name: 'Qwen: Qwen3.5-122B-A10B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 65536, + cost: { + input: 0.26, + output: 2.08, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen/qwen3.5-27b', + name: 'Qwen: Qwen3.5-27B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 81920, + cost: { + input: 0.26, + output: 2.6, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen/qwen3.5-35b-a3b', + name: 'Qwen: Qwen3.5-35B-A3B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0.14, + output: 1, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen/qwen3.5-397b-a17b', + name: 'Qwen: Qwen3.5 397B A17B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 65536, + cost: { + input: 0.39, + output: 2.34, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen/qwen3.5-9b', + name: 'Qwen: Qwen3.5-9B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0.1, + output: 0.15, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen/qwen3.5-flash-02-23', + name: 'Qwen: Qwen3.5-Flash', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 65536, + cost: { + input: 0.065, + output: 0.26, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen/qwen3.5-plus-02-15', + name: 'Qwen: Qwen3.5 Plus 2026-02-15', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 65536, + cost: { + input: 0.26, + output: 1.56, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen/qwen3.5-plus-20260420', + name: 'Qwen: Qwen3.5 Plus 2026-04-20', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 65536, + cost: { + input: 0.3, + output: 1.8, + cacheRead: 0, + cacheWrite: 0.375, + }, + }, + }, + { + modelId: 'qwen/qwen3.6-27b', + name: 'Qwen: Qwen3.6 27B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 65536, + cost: { + input: 0.45, + output: 2.7, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen/qwen3.6-35b-a3b', + name: 'Qwen: Qwen3.6 35B A3B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0.14, + output: 1, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen/qwen3.6-flash', + name: 'Qwen: Qwen3.6 Flash', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 65536, + cost: { + input: 0.1875, + output: 1.125, + cacheRead: 0, + cacheWrite: 0.234375, + }, + }, + }, + { + modelId: 'qwen/qwen3.6-max-preview', + name: 'Qwen: Qwen3.6 Max Preview', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 262144, + maxTokens: 65536, + cost: { + input: 1.04, + output: 6.24, + cacheRead: 0, + cacheWrite: 1.3, + }, + }, + }, + { + modelId: 'qwen/qwen3.6-plus', + name: 'Qwen: Qwen3.6 Plus', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 65536, + cost: { + input: 0.325, + output: 1.95, + cacheRead: 0, + cacheWrite: 0.40625, + }, + }, + }, + { + modelId: 'qwen/qwen3.7-max', + name: 'Qwen: Qwen3.7 Max', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1000000, + maxTokens: 65536, + cost: { + input: 1.475, + output: 4.425, + cacheRead: 0.295, + cacheWrite: 1.84375, + }, + }, + }, + { + modelId: 'qwen/qwen3.7-plus', + name: 'Qwen: Qwen3.7 Plus', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 65536, + cost: { + input: 0.32, + output: 1.28, + cacheRead: 0.064, + cacheWrite: 0.4, + }, + }, + }, + { + modelId: 'rekaai/reka-edge', + name: 'Reka Edge', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text', 'image'], + contextWindow: 16384, + maxTokens: 16384, + cost: { + input: 0.1, + output: 0.1, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'relace/relace-search', + name: 'Relace: Relace Search', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 256000, + maxTokens: 128000, + cost: { + input: 1, + output: 3, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'sakana/fugu-ultra', + name: 'Sakana: Fugu Ultra', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 5, + output: 30, + cacheRead: 0.5, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'sao10k/l3.1-euryale-70b', + name: 'Sao10K: Llama 3.1 Euryale 70B v2.2', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 131072, + maxTokens: 16384, + cost: { + input: 0.85, + output: 0.85, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'stepfun/step-3.5-flash', + name: 'StepFun: Step 3.5 Flash', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 262144, + maxTokens: 65536, + cost: { + input: 0.1, + output: 0.3, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'stepfun/step-3.7-flash', + name: 'StepFun: Step 3.7 Flash', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 256000, + maxTokens: 256000, + cost: { + input: 0.2, + output: 1.15, + cacheRead: 0.04, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'tencent/hy3', + name: 'Tencent: Hy3', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0.14, + output: 0.58, + cacheRead: 0.035, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'tencent/hy3-preview', + name: 'Tencent: Hy3 preview', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 262144, + maxTokens: 4096, + cost: { + input: 0.063, + output: 0.21, + cacheRead: 0.021, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'thedrummer/unslopnemo-12b', + name: 'TheDrummer: UnslopNemo 12B', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 32768, + maxTokens: 32768, + cost: { + input: 0.4, + output: 0.4, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'thinkingmachines/inkling', + name: 'Thinking Machines: Inkling', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 524288, + maxTokens: 4096, + cost: { + input: 1, + output: 4.05, + cacheRead: 0.17, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'upstage/solar-pro-3', + name: 'Upstage: Solar Pro 3', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 128000, + maxTokens: 4096, + cost: { + input: 0.15, + output: 0.6, + cacheRead: 0.015, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'x-ai/grok-4.20', + name: 'xAI: Grok 4.20', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 2000000, + maxTokens: 4096, + cost: { + input: 1.25, + output: 2.5, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'x-ai/grok-4.3', + name: 'xAI: Grok 4.3', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 4096, + cost: { + input: 1.25, + output: 2.5, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'x-ai/grok-4.5', + name: 'xAI: Grok 4.5', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 500000, + maxTokens: 4096, + cost: { + input: 2, + output: 6, + cacheRead: 0.3, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'x-ai/grok-build-0.1', + name: 'xAI: Grok Build 0.1', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 256000, + maxTokens: 4096, + cost: { + input: 1, + output: 2, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'xiaomi/mimo-v2.5', + name: 'Xiaomi: MiMo-V2.5', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 131072, + cost: { + input: 0.14, + output: 0.28, + cacheRead: 0.0028, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'xiaomi/mimo-v2.5-pro', + name: 'Xiaomi: MiMo-V2.5-Pro', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1048576, + maxTokens: 131072, + cost: { + input: 0.435, + output: 0.87, + cacheRead: 0.0036, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'z-ai/glm-4.5', + name: 'Z.ai: GLM 4.5', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 98304, + cost: { + input: 0.6, + output: 2.2, + cacheRead: 0.11, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'z-ai/glm-4.5-air', + name: 'Z.ai: GLM 4.5 Air', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 98304, + cost: { + input: 0.13, + output: 0.85, + cacheRead: 0.025, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'z-ai/glm-4.5v', + name: 'Z.ai: GLM 4.5V', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 65536, + maxTokens: 16384, + cost: { + input: 0.6, + output: 1.8, + cacheRead: 0.11, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'z-ai/glm-4.6', + name: 'Z.ai: GLM 4.6', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 202752, + maxTokens: 131072, + cost: { + input: 0.5, + output: 2, + cacheRead: 0.1, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'z-ai/glm-4.6v', + name: 'Z.ai: GLM 4.6V', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 131072, + maxTokens: 32768, + cost: { + input: 0.3, + output: 0.9, + cacheRead: 0.055, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'z-ai/glm-4.7', + name: 'Z.ai: GLM 4.7', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 202752, + maxTokens: 131072, + cost: { + input: 0.4, + output: 1.75, + cacheRead: 0.08, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'z-ai/glm-4.7-flash', + name: 'Z.ai: GLM 4.7 Flash', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 131072, + cost: { + input: 0.0605, + output: 0.4, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'z-ai/glm-5', + name: 'Z.ai: GLM 5', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 204800, + maxTokens: 131072, + cost: { + input: 0.6, + output: 1.9, + cacheRead: 0.119, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'z-ai/glm-5-turbo', + name: 'Z.ai: GLM 5 Turbo', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 202752, + maxTokens: 131072, + cost: { + input: 1.2, + output: 4, + cacheRead: 0.24, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'z-ai/glm-5.1', + name: 'Z.ai: GLM 5.1', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 200000, + maxTokens: 128000, + cost: { + input: 0.966, + output: 3.036, + cacheRead: 0.1794, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'z-ai/glm-5.2', + name: 'Z.ai: GLM 5.2', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1048576, + maxTokens: 131072, + cost: { + input: 0.8204, + output: 2.5784, + cacheRead: 0.15236, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'z-ai/glm-5v-turbo', + name: 'Z.ai: GLM 5V Turbo', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 202752, + maxTokens: 131072, + cost: { + input: 1.2, + output: 4, + cacheRead: 0.24, + cacheWrite: 0, + }, + }, + }, + { + modelId: '~anthropic/claude-fable-latest', + name: 'Anthropic: Claude Fable Latest', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 10, + output: 50, + cacheRead: 1, + cacheWrite: 12.5, + }, + }, + }, + { + modelId: '~anthropic/claude-haiku-latest', + name: 'Anthropic Claude Haiku Latest', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 64000, + cost: { + input: 1, + output: 5, + cacheRead: 0.1, + cacheWrite: 1.25, + }, + }, + }, + { + modelId: '~anthropic/claude-opus-latest', + name: 'Anthropic: Claude Opus Latest', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: '~anthropic/claude-sonnet-latest', + name: 'Anthropic Claude Sonnet Latest', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 2, + output: 10, + cacheRead: 0.2, + cacheWrite: 2.5, + }, + }, + }, + { + modelId: '~google/gemini-flash-latest', + name: 'Google Gemini Flash Latest', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 1.5, + output: 7.5, + cacheRead: 0.15, + cacheWrite: 0.083333, + }, + }, + }, + { + modelId: '~google/gemini-pro-latest', + name: 'Google Gemini Pro Latest', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 2, + output: 12, + cacheRead: 0.2, + cacheWrite: 0.375, + }, + }, + }, + { + modelId: '~moonshotai/kimi-latest', + name: 'MoonshotAI Kimi Latest', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 131072, + cost: { + input: 3, + output: 15, + cacheRead: 0.3, + cacheWrite: 0, + }, + }, + }, + { + modelId: '~openai/gpt-latest', + name: 'OpenAI GPT Latest', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 128000, + cost: { + input: 5, + output: 30, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: '~openai/gpt-mini-latest', + name: 'OpenAI GPT Mini Latest', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 0.75, + output: 4.5, + cacheRead: 0.075, + cacheWrite: 0, + }, + }, + }, + { + modelId: '~x-ai/grok-latest', + name: 'xAI: Grok Latest', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 500000, + maxTokens: 4096, + cost: { + input: 2, + output: 6, + cacheRead: 0.3, + cacheWrite: 0, + }, + }, + }, + ], +} as const diff --git a/packages/core/src/generated/providers/qwen-token-plan-cn.ts b/packages/core/src/generated/providers/qwen-token-plan-cn.ts new file mode 100644 index 00000000..fed3fb05 --- /dev/null +++ b/packages/core/src/generated/providers/qwen-token-plan-cn.ts @@ -0,0 +1,269 @@ +// This file is auto-generated by scripts/generate-builtin-providers.ts +// Do not edit manually - run 'bun run generate-providers' to update + +export const providerName = 'qwen-token-plan-cn' +export const providerConfig = { + name: 'qwen-token-plan-cn', + config: { + api: 'openai-completions', + baseUrl: 'https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1', + apiKey: '', + }, + models: [ + { + modelId: 'MiniMax-M2.5', + name: 'MiniMax-M2.5', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 196608, + maxTokens: 24576, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'deepseek-v3.2', + name: 'DeepSeek V3.2', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 65536, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'deepseek-v4-flash', + name: 'DeepSeek V4 Flash', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1000000, + maxTokens: 384000, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'deepseek-v4-pro', + name: 'DeepSeek V4 Pro', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1000000, + maxTokens: 384000, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'glm-5', + name: 'GLM-5', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 202752, + maxTokens: 16384, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'glm-5.1', + name: 'GLM-5.1', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 202752, + maxTokens: 128000, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'glm-5.2', + name: 'GLM-5.2', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1000000, + maxTokens: 131072, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'kimi-k2.5', + name: 'Kimi K2.5', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 32768, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'kimi-k2.6', + name: 'Kimi K2.6', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 16384, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'kimi-k2.7-code', + name: 'Kimi K2.7 Code', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen3.6-flash', + name: 'Qwen3.6 Flash', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 65536, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen3.6-plus', + name: 'Qwen3.6 Plus', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 65536, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen3.7-max', + name: 'Qwen3.7 Max', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1000000, + maxTokens: 65536, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen3.7-plus', + name: 'Qwen3.7 Plus', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 64000, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen3.8-max-preview', + name: 'Qwen3.8 Max Preview', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 131072, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + ], +} as const diff --git a/packages/core/src/generated/providers/qwen-token-plan.ts b/packages/core/src/generated/providers/qwen-token-plan.ts new file mode 100644 index 00000000..f62f3a1c --- /dev/null +++ b/packages/core/src/generated/providers/qwen-token-plan.ts @@ -0,0 +1,269 @@ +// This file is auto-generated by scripts/generate-builtin-providers.ts +// Do not edit manually - run 'bun run generate-providers' to update + +export const providerName = 'qwen-token-plan' +export const providerConfig = { + name: 'qwen-token-plan', + config: { + api: 'openai-completions', + baseUrl: 'https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1', + apiKey: '', + }, + models: [ + { + modelId: 'MiniMax-M2.5', + name: 'MiniMax-M2.5', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 196608, + maxTokens: 24576, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'deepseek-v3.2', + name: 'DeepSeek V3.2', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 65536, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'deepseek-v4-flash', + name: 'DeepSeek V4 Flash', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1000000, + maxTokens: 384000, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'deepseek-v4-pro', + name: 'DeepSeek V4 Pro', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1000000, + maxTokens: 384000, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'glm-5', + name: 'GLM-5', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 202752, + maxTokens: 16384, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'glm-5.1', + name: 'GLM-5.1', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 202752, + maxTokens: 128000, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'glm-5.2', + name: 'GLM-5.2', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1000000, + maxTokens: 131072, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'kimi-k2.5', + name: 'Kimi K2.5', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 32768, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'kimi-k2.6', + name: 'Kimi K2.6', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 16384, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'kimi-k2.7-code', + name: 'Kimi K2.7 Code', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen3.6-flash', + name: 'Qwen3.6 Flash', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 65536, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen3.6-plus', + name: 'Qwen3.6 Plus', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 65536, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen3.7-max', + name: 'Qwen3.7 Max', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1000000, + maxTokens: 65536, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen3.7-plus', + name: 'Qwen3.7 Plus', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 64000, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'qwen3.8-max-preview', + name: 'Qwen3.8 Max Preview', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 131072, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + ], +} as const diff --git a/packages/core/src/generated/providers/together.ts b/packages/core/src/generated/providers/together.ts new file mode 100644 index 00000000..bb3484a6 --- /dev/null +++ b/packages/core/src/generated/providers/together.ts @@ -0,0 +1,286 @@ +// This file is auto-generated by scripts/generate-builtin-providers.ts +// Do not edit manually - run 'bun run generate-providers' to update + +export const providerName = 'together' +export const providerConfig = { + name: 'together', + config: { + api: 'openai-completions', + baseUrl: 'https://api.together.ai/v1', + apiKey: 'TOGETHER_API_KEY', + }, + models: [ + { + modelId: 'MiniMaxAI/MiniMax-M2.7', + name: 'MiniMax-M2.7', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 202752, + maxTokens: 131072, + cost: { + input: 0.3, + output: 1.2, + cacheRead: 0.06, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'MiniMaxAI/MiniMax-M3', + name: 'MiniMax-M3', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 524288, + maxTokens: 250000, + cost: { + input: 0.3, + output: 1.2, + cacheRead: 0.06, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'Qwen/Qwen2.5-7B-Instruct-Turbo', + name: 'Qwen 2.5 7B Instruct Turbo', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 32768, + maxTokens: 32768, + cost: { + input: 0.3, + output: 0.3, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'Qwen/Qwen3.5-9B', + name: 'Qwen3.5 9B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 65536, + cost: { + input: 0.17, + output: 0.25, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'Qwen/Qwen3.6-Plus', + name: 'Qwen3.6 Plus', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1000000, + maxTokens: 500000, + cost: { + input: 0.5, + output: 3, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'Qwen/Qwen3.7-Max', + name: 'Qwen3.7 Max', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 1000000, + maxTokens: 500000, + cost: { + input: 1.25, + output: 3.75, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'deepseek-ai/DeepSeek-V4-Pro', + name: 'DeepSeek V4 Pro', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 512000, + maxTokens: 384000, + cost: { + input: 1.74, + output: 3.48, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'google/gemma-4-31B-it', + name: 'Gemma 4 31B Instruct', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 131072, + cost: { + input: 0.39, + output: 0.97, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'meta-llama/Llama-3.3-70B-Instruct-Turbo', + name: 'Llama 3.3 70B', + config: { + api: 'openai-completions', + reasoning: false, + input: ['text'], + contextWindow: 131072, + maxTokens: 131072, + cost: { + input: 1.04, + output: 1.04, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'moonshotai/Kimi-K2.6', + name: 'Kimi K2.6', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 131000, + cost: { + input: 1.2, + output: 4.5, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'moonshotai/Kimi-K2.7-Code', + name: 'Kimi K2.7 Code', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 262144, + maxTokens: 131072, + cost: { + input: 0.95, + output: 4, + cacheRead: 0.19, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'nvidia/nemotron-3-ultra-550b-a55b', + name: 'Nemotron 3 Ultra 550B A55B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 512300, + maxTokens: 512300, + cost: { + input: 0.6, + output: 3.6, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-oss-120b', + name: 'GPT OSS 120B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 131072, + cost: { + input: 0.15, + output: 0.6, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-oss-20b', + name: 'GPT OSS 20B', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 131072, + cost: { + input: 0.05, + output: 0.2, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'thinkingmachines/Inkling', + name: 'Inkling', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 524288, + maxTokens: 131072, + cost: { + input: 1, + output: 4.05, + cacheRead: 0.17, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'zai-org/GLM-5.2', + name: 'GLM-5.2', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 262144, + maxTokens: 164000, + cost: { + input: 1.4, + output: 4.4, + cacheRead: 0.26, + cacheWrite: 0, + }, + }, + }, + ], +} as const diff --git a/packages/core/src/generated/providers/vercel-ai-gateway.ts b/packages/core/src/generated/providers/vercel-ai-gateway.ts new file mode 100644 index 00000000..7e1afceb --- /dev/null +++ b/packages/core/src/generated/providers/vercel-ai-gateway.ts @@ -0,0 +1,3278 @@ +// This file is auto-generated by scripts/generate-builtin-providers.ts +// Do not edit manually - run 'bun run generate-providers' to update + +export const providerName = 'vercel-ai-gateway' +export const providerConfig = { + name: 'vercel-ai-gateway', + config: { + api: 'anthropic-messages', + baseUrl: 'https://ai-gateway.vercel.sh', + apiKey: 'AI_GATEWAY_API_KEY', + }, + models: [ + { + modelId: 'alibaba/qwen-3-14b', + name: 'Qwen3-14B', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 40960, + maxTokens: 16384, + cost: { + input: 0.12, + output: 0.24, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'alibaba/qwen-3-235b', + name: 'Qwen3 235B A22B', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 262144, + maxTokens: 16384, + cost: { + input: 0.22, + output: 0.88, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'alibaba/qwen-3-30b', + name: 'Qwen3-30B-A3B', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 40960, + maxTokens: 16384, + cost: { + input: 0.12, + output: 0.5, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'alibaba/qwen-3-32b', + name: 'Qwen 3 32B', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 128000, + maxTokens: 8192, + cost: { + input: 0.16, + output: 0.64, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'alibaba/qwen-3.6-max-preview', + name: 'Qwen 3.6 Max Preview', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 240000, + maxTokens: 64000, + cost: { + input: 1.3, + output: 7.8, + cacheRead: 0.26, + cacheWrite: 1.625, + }, + }, + }, + { + modelId: 'alibaba/qwen3-235b-a22b-thinking', + name: 'Qwen3 VL 235B A22B Thinking', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 131072, + maxTokens: 32768, + cost: { + input: 0.4, + output: 4, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'alibaba/qwen3-coder', + name: 'Qwen3 Coder 480B A35B Instruct', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text'], + contextWindow: 262144, + maxTokens: 65536, + cost: { + input: 1.5, + output: 7.5, + cacheRead: 0.3, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'alibaba/qwen3-coder-30b-a3b', + name: 'Qwen 3 Coder 30B A3B Instruct', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text'], + contextWindow: 262144, + maxTokens: 8192, + cost: { + input: 0.15, + output: 0.6, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'alibaba/qwen3-coder-next', + name: 'Qwen3 Coder Next', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text'], + contextWindow: 256000, + maxTokens: 256000, + cost: { + input: 0.5, + output: 1.2, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'alibaba/qwen3-coder-plus', + name: 'Qwen3 Coder Plus', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text'], + contextWindow: 1000000, + maxTokens: 65536, + cost: { + input: 1, + output: 5, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'alibaba/qwen3-max', + name: 'Qwen3 Max', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text'], + contextWindow: 262144, + maxTokens: 32768, + cost: { + input: 1.2, + output: 6, + cacheRead: 0.24, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'alibaba/qwen3-max-preview', + name: 'Qwen3 Max Preview', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text'], + contextWindow: 262144, + maxTokens: 32768, + cost: { + input: 1.2, + output: 6, + cacheRead: 0.24, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'alibaba/qwen3-max-thinking', + name: 'Qwen 3 Max Thinking', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 256000, + maxTokens: 65536, + cost: { + input: 1.2, + output: 6, + cacheRead: 0.24, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'alibaba/qwen3-next-80b-a3b-instruct', + name: 'Qwen3 Next 80B A3B Instruct', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text'], + contextWindow: 131072, + maxTokens: 32768, + cost: { + input: 0.15, + output: 1.2, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'alibaba/qwen3-next-80b-a3b-thinking', + name: 'Qwen3 Next 80B A3B Thinking', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 32768, + cost: { + input: 0.15, + output: 1.2, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'alibaba/qwen3-vl-235b-a22b-instruct', + name: 'Qwen3 VL 235B A22B Instruct', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text', 'image'], + contextWindow: 131072, + maxTokens: 129024, + cost: { + input: 0.4, + output: 1.6, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'alibaba/qwen3-vl-instruct', + name: 'Qwen3 VL 235B A22B Instruct', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text', 'image'], + contextWindow: 131072, + maxTokens: 129024, + cost: { + input: 0.4, + output: 1.6, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'alibaba/qwen3-vl-thinking', + name: 'Qwen3 VL 235B A22B Thinking', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 131072, + maxTokens: 32768, + cost: { + input: 0.4, + output: 4, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'alibaba/qwen3.5-flash', + name: 'Qwen 3.5 Flash', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 64000, + cost: { + input: 0.1, + output: 0.4, + cacheRead: 0.001, + cacheWrite: 0.125, + }, + }, + }, + { + modelId: 'alibaba/qwen3.5-plus', + name: 'Qwen 3.5 Plus', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 64000, + cost: { + input: 0.4, + output: 2.4, + cacheRead: 0.04, + cacheWrite: 0.5, + }, + }, + }, + { + modelId: 'alibaba/qwen3.6-27b', + name: 'Qwen 3.6 27B', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 256000, + maxTokens: 256000, + cost: { + input: 0.6, + output: 3.6, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'alibaba/qwen3.6-plus', + name: 'Qwen 3.6 Plus', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 64000, + cost: { + input: 0.5, + output: 3, + cacheRead: 0.1, + cacheWrite: 0.625, + }, + }, + }, + { + modelId: 'alibaba/qwen3.7-max', + name: 'Qwen 3.7 Max', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 991000, + maxTokens: 64000, + cost: { + input: 1.25, + output: 3.75, + cacheRead: 0.25, + cacheWrite: 1.5625, + }, + }, + }, + { + modelId: 'alibaba/qwen3.7-plus', + name: 'Qwen 3.7 Plus', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 64000, + cost: { + input: 0.4, + output: 1.6, + cacheRead: 0.08, + cacheWrite: 0.5, + }, + }, + }, + { + modelId: 'amazon/nova-2-lite', + name: 'Nova 2 Lite', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 1000000, + cost: { + input: 0.3, + output: 2.5, + cacheRead: 0.075, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'amazon/nova-lite', + name: 'Nova Lite', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text', 'image'], + contextWindow: 300000, + maxTokens: 8192, + cost: { + input: 0.06, + output: 0.24, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'amazon/nova-micro', + name: 'Nova Micro', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text'], + contextWindow: 128000, + maxTokens: 8192, + cost: { + input: 0.035, + output: 0.14, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'amazon/nova-pro', + name: 'Nova Pro', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text', 'image'], + contextWindow: 300000, + maxTokens: 8192, + cost: { + input: 0.8, + output: 3.2, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'anthropic/claude-3-haiku', + name: 'Claude 3 Haiku', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 4096, + cost: { + input: 0.25, + output: 1.25, + cacheRead: 0.03, + cacheWrite: 0.3, + }, + }, + }, + { + modelId: 'anthropic/claude-fable-5', + name: 'Claude Fable 5', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 10, + output: 50, + cacheRead: 1, + cacheWrite: 12.5, + }, + }, + }, + { + modelId: 'anthropic/claude-haiku-4.5', + name: 'Claude Haiku 4.5', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 64000, + cost: { + input: 1, + output: 5, + cacheRead: 0.1, + cacheWrite: 1.25, + }, + }, + }, + { + modelId: 'anthropic/claude-opus-4', + name: 'Claude Opus 4', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 8192, + cost: { + input: 15, + output: 75, + cacheRead: 1.5, + cacheWrite: 18.75, + }, + }, + }, + { + modelId: 'anthropic/claude-opus-4.1', + name: 'Claude Opus 4.1', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 32000, + cost: { + input: 15, + output: 75, + cacheRead: 1.5, + cacheWrite: 18.75, + }, + }, + }, + { + modelId: 'anthropic/claude-opus-4.5', + name: 'Claude Opus 4.5', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 64000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'anthropic/claude-opus-4.6', + name: 'Claude Opus 4.6', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'anthropic/claude-opus-4.7', + name: 'Claude Opus 4.7', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'anthropic/claude-opus-4.7-fast', + name: 'Claude Opus 4.7 (Fast)', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 30, + output: 150, + cacheRead: 3, + cacheWrite: 37.5, + }, + }, + }, + { + modelId: 'anthropic/claude-opus-4.8', + name: 'Claude Opus 4.8', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 5, + output: 25, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'anthropic/claude-opus-4.8-fast', + name: 'Claude Opus 4.8 (Fast)', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 10, + output: 50, + cacheRead: 1, + cacheWrite: 12.5, + }, + }, + }, + { + modelId: 'anthropic/claude-sonnet-4', + name: 'Claude Sonnet 4', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 8192, + cost: { + input: 3, + output: 15, + cacheRead: 0.3, + cacheWrite: 3.75, + }, + }, + }, + { + modelId: 'anthropic/claude-sonnet-4.5', + name: 'Claude Sonnet 4.5', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 64000, + cost: { + input: 3, + output: 15, + cacheRead: 0.3, + cacheWrite: 3.75, + }, + }, + }, + { + modelId: 'anthropic/claude-sonnet-4.6', + name: 'Claude Sonnet 4.6', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 3, + output: 15, + cacheRead: 0.3, + cacheWrite: 3.75, + }, + }, + }, + { + modelId: 'anthropic/claude-sonnet-5', + name: 'Claude Sonnet 5', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 2, + output: 10, + cacheRead: 0.2, + cacheWrite: 2.5, + }, + }, + }, + { + modelId: 'arcee-ai/trinity-large-thinking', + name: 'Trinity Large Thinking', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 262100, + maxTokens: 80000, + cost: { + input: 0.25, + output: 0.9, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'arcee-ai/trinity-mini', + name: 'Trinity Mini', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text'], + contextWindow: 131072, + maxTokens: 131072, + cost: { + input: 0.045, + output: 0.15, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'bytedance/seed-1.6', + name: 'Seed 1.6', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 256000, + maxTokens: 32000, + cost: { + input: 0.25, + output: 2, + cacheRead: 0.05, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'bytedance/seed-1.8', + name: 'Bytedance Seed 1.8', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 256000, + maxTokens: 64000, + cost: { + input: 0.25, + output: 2, + cacheRead: 0.05, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'cohere/command-a', + name: 'Command A', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text'], + contextWindow: 256000, + maxTokens: 8000, + cost: { + input: 2.5, + output: 10, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'deepseek/deepseek-r1', + name: 'DeepSeek-R1', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 128000, + maxTokens: 8192, + cost: { + input: 1.35, + output: 5.4, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'deepseek/deepseek-v3', + name: 'DeepSeek V3 0324', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text'], + contextWindow: 163840, + maxTokens: 163840, + cost: { + input: 0.27, + output: 1.12, + cacheRead: 0.135, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'deepseek/deepseek-v3.1', + name: 'DeepSeek V3.1', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 163840, + maxTokens: 128000, + cost: { + input: 0.25, + output: 0.95, + cacheRead: 0.13, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'deepseek/deepseek-v3.1-terminus', + name: 'DeepSeek V3.1 Terminus', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 65536, + cost: { + input: 0.27, + output: 1, + cacheRead: 0.135, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'deepseek/deepseek-v3.2', + name: 'DeepSeek V3.2', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text'], + contextWindow: 128000, + maxTokens: 8000, + cost: { + input: 0.28, + output: 0.42, + cacheRead: 0.028, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'deepseek/deepseek-v3.2-thinking', + name: 'DeepSeek V3.2 Thinking', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 128000, + maxTokens: 8000, + cost: { + input: 0.62, + output: 1.85, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'deepseek/deepseek-v4-flash', + name: 'DeepSeek V4 Flash', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 1000000, + maxTokens: 384000, + cost: { + input: 0.14, + output: 0.28, + cacheRead: 0.028, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'deepseek/deepseek-v4-pro', + name: 'DeepSeek V4 Pro', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 1000000, + maxTokens: 384000, + cost: { + input: 0.435, + output: 0.87, + cacheRead: 0.0036, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'google/gemini-2.5-flash', + name: 'Gemini 2.5 Flash', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 65536, + cost: { + input: 0.3, + output: 2.5, + cacheRead: 0.03, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'google/gemini-2.5-flash-lite', + name: 'Gemini 2.5 Flash Lite', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 0.1, + output: 0.4, + cacheRead: 0.01, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'google/gemini-2.5-pro', + name: 'Gemini 2.5 Pro', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 65536, + cost: { + input: 1.25, + output: 10, + cacheRead: 0.125, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'google/gemini-3-flash', + name: 'Gemini 3 Flash', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 65000, + cost: { + input: 0.5, + output: 3, + cacheRead: 0.05, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'google/gemini-3-pro-preview', + name: 'Gemini 3 Pro Preview', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 64000, + cost: { + input: 2, + output: 12, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'google/gemini-3.1-flash-lite', + name: 'Gemini 3.1 Flash Lite', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 65000, + cost: { + input: 0.25, + output: 1.5, + cacheRead: 0.03, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'google/gemini-3.1-flash-lite-preview', + name: 'Gemini 3.1 Flash Lite Preview', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 65000, + cost: { + input: 0.25, + output: 1.5, + cacheRead: 0.03, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'google/gemini-3.1-pro-preview', + name: 'Gemini 3.1 Pro Preview', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 64000, + cost: { + input: 2, + output: 12, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'google/gemini-3.5-flash', + name: 'Gemini 3.5 Flash', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 64000, + cost: { + input: 1.5, + output: 9, + cacheRead: 0.15, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'google/gemini-3.5-flash-lite', + name: 'Gemini 3.5 Flash Lite', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 65000, + cost: { + input: 0.3, + output: 2.5, + cacheRead: 0.03, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'google/gemini-3.6-flash', + name: 'Gemini 3.6 Flash', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 64000, + cost: { + input: 1.5, + output: 7.5, + cacheRead: 0.15, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'google/gemma-4-26b-a4b-it', + name: 'Gemma 4 26B A4B IT', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 131072, + cost: { + input: 0.15, + output: 0.6, + cacheRead: 0.015, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'google/gemma-4-31b-it', + name: 'Gemma 4 31B IT', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 131072, + cost: { + input: 0.14, + output: 0.4, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'inception/mercury-2', + name: 'Mercury 2', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 128000, + maxTokens: 128000, + cost: { + input: 0.25, + output: 0.75, + cacheRead: 0.025, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'inception/mercury-coder-small', + name: 'Mercury Coder Small Beta', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text'], + contextWindow: 32000, + maxTokens: 16384, + cost: { + input: 0.25, + output: 1, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'interfaze/interfaze-beta', + name: 'Interfaze Beta', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 32000, + cost: { + input: 1.5, + output: 3.5, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'kwaipilot/kat-coder-air-v2.5', + name: 'Kat Coder Air V2.5', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 256000, + maxTokens: 80000, + cost: { + input: 0.15, + output: 0.6, + cacheRead: 0.03, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'kwaipilot/kat-coder-pro-v1', + name: 'KAT-Coder-Pro V1', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text'], + contextWindow: 256000, + maxTokens: 32000, + cost: { + input: 0.3, + output: 1.2, + cacheRead: 0.06, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'kwaipilot/kat-coder-pro-v2', + name: 'Kat Coder Pro V2', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 256000, + maxTokens: 256000, + cost: { + input: 0.3, + output: 1.2, + cacheRead: 0.06, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'kwaipilot/kat-coder-pro-v2.5', + name: 'Kat Coder Pro V2.5', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 256000, + maxTokens: 80000, + cost: { + input: 0.74, + output: 2.96, + cacheRead: 0.15, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'meta/llama-3.1-70b', + name: 'Llama 3.1 70B Instruct', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text'], + contextWindow: 128000, + maxTokens: 8192, + cost: { + input: 0.72, + output: 0.72, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'meta/llama-3.1-8b', + name: 'Llama 3.1 8B Instruct', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text'], + contextWindow: 128000, + maxTokens: 8192, + cost: { + input: 0.22, + output: 0.22, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'meta/llama-3.3-70b', + name: 'Llama 3.3 70B Instruct', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text'], + contextWindow: 128000, + maxTokens: 8192, + cost: { + input: 0.72, + output: 0.72, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'meta/llama-4-maverick', + name: 'Llama 4 Maverick 17B Instruct', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 8192, + cost: { + input: 0.24, + output: 0.97, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'meta/llama-4-scout', + name: 'Llama 4 Scout 17B Instruct', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 8192, + cost: { + input: 0.17, + output: 0.66, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'meta/muse-spark-1.1', + name: 'Muse Spark 1.1', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 1048576, + cost: { + input: 1.25, + output: 4.25, + cacheRead: 0.15, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'minimax/minimax-m2', + name: 'MiniMax M2', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 205000, + maxTokens: 205000, + cost: { + input: 0.3, + output: 1.2, + cacheRead: 0.03, + cacheWrite: 0.375, + }, + }, + }, + { + modelId: 'minimax/minimax-m2.1', + name: 'MiniMax M2.1', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 204800, + maxTokens: 131072, + cost: { + input: 0.3, + output: 1.2, + cacheRead: 0.03, + cacheWrite: 0.375, + }, + }, + }, + { + modelId: 'minimax/minimax-m2.1-lightning', + name: 'MiniMax M2.1 Lightning', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 204800, + maxTokens: 131072, + cost: { + input: 0.3, + output: 2.4, + cacheRead: 0.03, + cacheWrite: 0.375, + }, + }, + }, + { + modelId: 'minimax/minimax-m2.5', + name: 'MiniMax M2.5', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 204800, + maxTokens: 131000, + cost: { + input: 0.3, + output: 1.2, + cacheRead: 0.03, + cacheWrite: 0.375, + }, + }, + }, + { + modelId: 'minimax/minimax-m2.5-highspeed', + name: 'MiniMax M2.5 High Speed', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 204800, + maxTokens: 131000, + cost: { + input: 0.6, + output: 2.4, + cacheRead: 0.03, + cacheWrite: 0.375, + }, + }, + }, + { + modelId: 'minimax/minimax-m2.7', + name: 'MiniMax M2.7', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 204800, + maxTokens: 131000, + cost: { + input: 0.3, + output: 1.2, + cacheRead: 0.06, + cacheWrite: 0.375, + }, + }, + }, + { + modelId: 'minimax/minimax-m2.7-highspeed', + name: 'MiniMax M2.7 High Speed', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 204800, + maxTokens: 131100, + cost: { + input: 0.6, + output: 2.4, + cacheRead: 0.06, + cacheWrite: 0.375, + }, + }, + }, + { + modelId: 'minimax/minimax-m3', + name: 'MiniMax M3', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 1000000, + cost: { + input: 0.3, + output: 1.2, + cacheRead: 0.06, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistral/codestral', + name: 'Mistral Codestral', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text'], + contextWindow: 128000, + maxTokens: 4000, + cost: { + input: 0.3, + output: 0.9, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistral/devstral-2', + name: 'Devstral 2', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text'], + contextWindow: 256000, + maxTokens: 256000, + cost: { + input: 0.4, + output: 2, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistral/devstral-small-2', + name: 'Devstral Small 2', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text', 'image'], + contextWindow: 256000, + maxTokens: 256000, + cost: { + input: 0.1, + output: 0.3, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistral/magistral-medium', + name: 'Magistral Medium 2509', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 64000, + cost: { + input: 2, + output: 5, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistral/magistral-small', + name: 'Magistral Small 2509', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 64000, + cost: { + input: 0.5, + output: 1.5, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistral/ministral-14b', + name: 'Ministral 14B', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text', 'image'], + contextWindow: 256000, + maxTokens: 256000, + cost: { + input: 0.2, + output: 0.2, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistral/ministral-3b', + name: 'Ministral 3B', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text'], + contextWindow: 128000, + maxTokens: 4000, + cost: { + input: 0.1, + output: 0.1, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistral/ministral-8b', + name: 'Ministral 8B', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text'], + contextWindow: 128000, + maxTokens: 4000, + cost: { + input: 0.15, + output: 0.15, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistral/mistral-large-3', + name: 'Mistral Large 3', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text', 'image'], + contextWindow: 256000, + maxTokens: 256000, + cost: { + input: 0.5, + output: 1.5, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistral/mistral-medium', + name: 'Mistral Medium 3.1', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 64000, + cost: { + input: 0.4, + output: 2, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistral/mistral-medium-3.5', + name: 'Mistral Medium Latest', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 256000, + maxTokens: 256000, + cost: { + input: 1.5, + output: 7.5, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistral/mistral-nemo', + name: 'Mistral Nemo 12B', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text'], + contextWindow: 128000, + maxTokens: 128000, + cost: { + input: 0.15, + output: 0.15, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistral/mistral-small', + name: 'Mistral Small', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text', 'image'], + contextWindow: 32000, + maxTokens: 4000, + cost: { + input: 0.1, + output: 0.3, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mistral/pixtral-12b', + name: 'Pixtral 12B 2409', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 4000, + cost: { + input: 0.15, + output: 0.15, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'moonshotai/kimi-k2', + name: 'Kimi K2 Instruct', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text'], + contextWindow: 131072, + maxTokens: 131072, + cost: { + input: 0.57, + output: 2.3, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'moonshotai/kimi-k2-thinking', + name: 'Kimi K2 Thinking', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 216144, + maxTokens: 216144, + cost: { + input: 0.47, + output: 2, + cacheRead: 0.141, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'moonshotai/kimi-k2.5', + name: 'Kimi K2.5', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262114, + maxTokens: 262114, + cost: { + input: 0.6, + output: 3, + cacheRead: 0.1, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'moonshotai/kimi-k2.6', + name: 'Kimi K2.6', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262000, + maxTokens: 262000, + cost: { + input: 0.95, + output: 4, + cacheRead: 0.16, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'moonshotai/kimi-k2.7-code', + name: 'Kimi K2.7 Code', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 256000, + maxTokens: 32768, + cost: { + input: 0.95, + output: 4, + cacheRead: 0.19, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'moonshotai/kimi-k2.7-code-highspeed', + name: 'Kimi K2.7 Code High Speed', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 32768, + cost: { + input: 1.9, + output: 8, + cacheRead: 0.38, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'moonshotai/kimi-k3', + name: 'Kimi K3', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 131072, + cost: { + input: 3, + output: 15, + cacheRead: 0.3, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'nvidia/nemotron-3-nano-30b-a3b', + name: 'Nemotron 3 Nano 30B A3B', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 262144, + maxTokens: 262144, + cost: { + input: 0.05, + output: 0.24, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'nvidia/nemotron-3-super-120b-a12b', + name: 'NVIDIA Nemotron 3 Super 120B A12B', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 256000, + maxTokens: 32000, + cost: { + input: 0.15, + output: 0.65, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'nvidia/nemotron-3-ultra-550b-a55b', + name: 'Nemotron 3 Ultra', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 1000000, + maxTokens: 65000, + cost: { + input: 0.6, + output: 2.4, + cacheRead: 0.12, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'nvidia/nemotron-nano-12b-v2-vl', + name: 'Nvidia Nemotron Nano 12B V2 VL', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 131072, + maxTokens: 131072, + cost: { + input: 0.2, + output: 0.6, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'nvidia/nemotron-nano-9b-v2', + name: 'Nvidia Nemotron Nano 9B V2', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 131072, + cost: { + input: 0.06, + output: 0.23, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-3.5-turbo', + name: 'GPT-3.5 Turbo', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text'], + contextWindow: 16385, + maxTokens: 4096, + cost: { + input: 0.5, + output: 1.5, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-4-turbo', + name: 'GPT-4 Turbo', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 4096, + cost: { + input: 10, + output: 30, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-4.1', + name: 'GPT-4.1', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text', 'image'], + contextWindow: 1047576, + maxTokens: 32768, + cost: { + input: 2, + output: 8, + cacheRead: 0.5, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-4.1-mini', + name: 'GPT-4.1 mini', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text', 'image'], + contextWindow: 1047576, + maxTokens: 32768, + cost: { + input: 0.4, + output: 1.6, + cacheRead: 0.1, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-4.1-nano', + name: 'GPT-4.1 nano', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text', 'image'], + contextWindow: 1047576, + maxTokens: 32768, + cost: { + input: 0.1, + output: 0.4, + cacheRead: 0.025, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-4o', + name: 'GPT-4o', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 2.5, + output: 10, + cacheRead: 1.25, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-4o-mini', + name: 'GPT-4o mini', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 0.15, + output: 0.6, + cacheRead: 0.075, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5', + name: 'GPT-5', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.25, + output: 10, + cacheRead: 0.125, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5-chat', + name: 'GPT 5 Chat', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 1.25, + output: 10, + cacheRead: 0.125, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5-codex', + name: 'GPT-5-Codex', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.25, + output: 10, + cacheRead: 0.125, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5-mini', + name: 'GPT-5 mini', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 0.25, + output: 2, + cacheRead: 0.025, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5-nano', + name: 'GPT-5 nano', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 0.05, + output: 0.4, + cacheRead: 0.005, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5-pro', + name: 'GPT-5 pro', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 272000, + cost: { + input: 15, + output: 120, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5.1-codex', + name: 'GPT-5.1-Codex', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.25, + output: 10, + cacheRead: 0.125, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5.1-codex-max', + name: 'GPT 5.1 Codex Max', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.25, + output: 10, + cacheRead: 0.125, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5.1-codex-mini', + name: 'GPT 5.1 Codex Mini', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 0.25, + output: 2, + cacheRead: 0.025, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5.1-instant', + name: 'GPT-5.1 Instant', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 1.25, + output: 10, + cacheRead: 0.125, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5.1-thinking', + name: 'GPT 5.1 Thinking', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.25, + output: 10, + cacheRead: 0.125, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5.2', + name: 'GPT 5.2', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.75, + output: 14, + cacheRead: 0.175, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5.2-chat', + name: 'GPT 5.2 Chat', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 1.75, + output: 14, + cacheRead: 0.175, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5.2-codex', + name: 'GPT 5.2 Codex', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.75, + output: 14, + cacheRead: 0.175, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5.2-pro', + name: 'GPT 5.2 ', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 21, + output: 168, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5.3-chat', + name: 'GPT-5.3 Chat', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 16384, + cost: { + input: 1.75, + output: 14, + cacheRead: 0.175, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5.3-codex', + name: 'GPT 5.3 Codex', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 1.75, + output: 14, + cacheRead: 0.175, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5.4', + name: 'GPT 5.4', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 128000, + cost: { + input: 2.5, + output: 15, + cacheRead: 0.25, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5.4-mini', + name: 'GPT 5.4 Mini', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 0.75, + output: 4.5, + cacheRead: 0.075, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5.4-nano', + name: 'GPT 5.4 Nano', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 400000, + maxTokens: 128000, + cost: { + input: 0.2, + output: 1.25, + cacheRead: 0.02, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5.4-pro', + name: 'GPT 5.4 Pro', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 128000, + cost: { + input: 30, + output: 180, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5.5', + name: 'GPT 5.5', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 5, + output: 30, + cacheRead: 0.5, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5.5-pro', + name: 'GPT 5.5 Pro', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 30, + output: 180, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-5.6-luna', + name: 'GPT 5.6 Luna', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 128000, + cost: { + input: 1, + output: 6, + cacheRead: 0.1, + cacheWrite: 1.25, + }, + }, + }, + { + modelId: 'openai/gpt-5.6-sol', + name: 'GPT 5.6 Sol', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 128000, + cost: { + input: 5, + output: 30, + cacheRead: 0.5, + cacheWrite: 6.25, + }, + }, + }, + { + modelId: 'openai/gpt-5.6-terra', + name: 'GPT 5.6 Terra', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 128000, + cost: { + input: 2.5, + output: 15, + cacheRead: 0.25, + cacheWrite: 3.125, + }, + }, + }, + { + modelId: 'openai/gpt-oss-120b', + name: 'GPT OSS 120B', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 131072, + cost: { + input: 0.1, + output: 0.5, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-oss-20b', + name: 'GPT OSS 20B', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 8192, + cost: { + input: 0.05, + output: 0.2, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/gpt-oss-safeguard-20b', + name: 'GPT OSS Safeguard 20B', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 65536, + cost: { + input: 0.075, + output: 0.3, + cacheRead: 0.037, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/o1', + name: 'o1', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 100000, + cost: { + input: 15, + output: 60, + cacheRead: 7.5, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/o3', + name: 'o3', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 100000, + cost: { + input: 2, + output: 8, + cacheRead: 0.5, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/o3-deep-research', + name: 'o3-deep-research', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 100000, + cost: { + input: 10, + output: 40, + cacheRead: 2.5, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/o3-mini', + name: 'o3-mini', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 200000, + maxTokens: 100000, + cost: { + input: 1.1, + output: 4.4, + cacheRead: 0.55, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/o3-pro', + name: 'o3 Pro', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 100000, + cost: { + input: 20, + output: 80, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'openai/o4-mini', + name: 'o4-mini', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 100000, + cost: { + input: 1.1, + output: 4.4, + cacheRead: 0.275, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'poolside/laguna-s-2.1', + name: 'Laguna S 2.1', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 1000000, + maxTokens: 131072, + cost: { + input: 0.1, + output: 0.2, + cacheRead: 0.01, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'poolside/laguna-s-2.1-free', + name: 'Laguna S 2.1 Free', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 256000, + maxTokens: 32768, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'sakana/fugu-ultra', + name: 'Fugu Ultra', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 1000000, + cost: { + input: 5, + output: 30, + cacheRead: 0.5, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'stepfun/step-3.5-flash', + name: 'StepFun 3.5 Flash', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 262114, + maxTokens: 262114, + cost: { + input: 0.09, + output: 0.3, + cacheRead: 0.02, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'stepfun/step-3.7-flash', + name: 'Step 3.7 Flash', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 256000, + maxTokens: 256000, + cost: { + input: 0.2, + output: 1.15, + cacheRead: 0.04, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'thinkingmachines/inkling', + name: 'Inkling', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 256000, + maxTokens: 256000, + cost: { + input: 1, + output: 4.05, + cacheRead: 0.17, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'xai/grok-4.1-fast-non-reasoning', + name: 'Grok 4.1 Fast Non-Reasoning', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 1000000, + cost: { + input: 0.2, + output: 0.5, + cacheRead: 0.05, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'xai/grok-4.1-fast-reasoning', + name: 'Grok 4.1 Fast Reasoning', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 1000000, + cost: { + input: 0.2, + output: 0.5, + cacheRead: 0.05, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'xai/grok-4.20-multi-agent', + name: 'Grok 4.20 Multi-Agent', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 2000000, + maxTokens: 2000000, + cost: { + input: 1.25, + output: 2.5, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'xai/grok-4.20-multi-agent-beta', + name: 'Grok 4.20 Multi Agent Beta', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 2000000, + maxTokens: 2000000, + cost: { + input: 1.25, + output: 2.5, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'xai/grok-4.20-non-reasoning', + name: 'Grok 4.20 Non-Reasoning', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text', 'image'], + contextWindow: 2000000, + maxTokens: 2000000, + cost: { + input: 1.25, + output: 2.5, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'xai/grok-4.20-non-reasoning-beta', + name: 'Grok 4.20 Beta Non-Reasoning', + config: { + api: 'anthropic-messages', + reasoning: false, + input: ['text', 'image'], + contextWindow: 2000000, + maxTokens: 2000000, + cost: { + input: 1.25, + output: 2.5, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'xai/grok-4.20-reasoning', + name: 'Grok 4.20 Reasoning', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 2000000, + maxTokens: 2000000, + cost: { + input: 1.25, + output: 2.5, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'xai/grok-4.20-reasoning-beta', + name: 'Grok 4.20 Beta Reasoning', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 2000000, + maxTokens: 2000000, + cost: { + input: 1.25, + output: 2.5, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'xai/grok-4.3', + name: 'Grok 4.3', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 1000000, + cost: { + input: 1.25, + output: 2.5, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'xai/grok-4.5', + name: 'Grok 4.5', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 500000, + maxTokens: 500000, + cost: { + input: 2, + output: 6, + cacheRead: 0.3, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'xai/grok-build-0.1', + name: 'Grok Build 0.1', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 256000, + maxTokens: 256000, + cost: { + input: 1, + output: 2, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'xiaomi/mimo-v2.5', + name: 'MiMo M2.5', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1050000, + maxTokens: 131100, + cost: { + input: 0.14, + output: 0.28, + cacheRead: 0.0028, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'xiaomi/mimo-v2.5-pro', + name: 'MiMo V2.5 Pro', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 1050000, + maxTokens: 131000, + cost: { + input: 0.435, + output: 0.87, + cacheRead: 0.0036, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'zai/glm-4.5', + name: 'GLM 4.5', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 128000, + maxTokens: 96000, + cost: { + input: 0.6, + output: 2.2, + cacheRead: 0.11, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'zai/glm-4.5-air', + name: 'GLM 4.5 Air', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 128000, + maxTokens: 96000, + cost: { + input: 0.2, + output: 1.1, + cacheRead: 0.03, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'zai/glm-4.5v', + name: 'GLM 4.5V', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 66000, + maxTokens: 16000, + cost: { + input: 0.6, + output: 1.8, + cacheRead: 0.11, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'zai/glm-4.6', + name: 'GLM 4.6', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 200000, + maxTokens: 96000, + cost: { + input: 0.6, + output: 2.2, + cacheRead: 0.11, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'zai/glm-4.6v', + name: 'GLM-4.6V', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 24000, + cost: { + input: 0.3, + output: 0.9, + cacheRead: 0.05, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'zai/glm-4.6v-flash', + name: 'GLM-4.6V-Flash', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 128000, + maxTokens: 24000, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'zai/glm-4.7', + name: 'GLM 4.7', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 200000, + maxTokens: 120000, + cost: { + input: 0.6, + output: 2.2, + cacheRead: 0.12, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'zai/glm-4.7-flash', + name: 'GLM 4.7 Flash', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 200000, + maxTokens: 131000, + cost: { + input: 0.07, + output: 0.4, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'zai/glm-4.7-flashx', + name: 'GLM 4.7 FlashX', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 200000, + maxTokens: 128000, + cost: { + input: 0.06, + output: 0.4, + cacheRead: 0.01, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'zai/glm-5', + name: 'GLM 5', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 202800, + maxTokens: 131100, + cost: { + input: 0.95, + output: 3.15, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'zai/glm-5-turbo', + name: 'GLM 5 Turbo', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 202800, + maxTokens: 131100, + cost: { + input: 1.2, + output: 4, + cacheRead: 0.24, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'zai/glm-5.1', + name: 'GLM 5.1', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 202000, + maxTokens: 202000, + cost: { + input: 1.3, + output: 4.3, + cacheRead: 0.26, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'zai/glm-5.2', + name: 'GLM 5.2', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 1040000, + maxTokens: 128000, + cost: { + input: 1.4, + output: 4.4, + cacheRead: 0.26, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'zai/glm-5.2-fast', + name: 'GLM 5.2 Fast', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text'], + contextWindow: 1000000, + maxTokens: 128000, + cost: { + input: 2.1, + output: 6.6, + cacheRead: 0.21, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'zai/glm-5v-turbo', + name: 'GLM 5V Turbo', + config: { + api: 'anthropic-messages', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 128000, + cost: { + input: 1.2, + output: 4, + cacheRead: 0.24, + cacheWrite: 0, + }, + }, + }, + ], +} as const diff --git a/packages/core/src/generated/providers/xai.ts b/packages/core/src/generated/providers/xai.ts new file mode 100644 index 00000000..6fb034d1 --- /dev/null +++ b/packages/core/src/generated/providers/xai.ts @@ -0,0 +1,65 @@ +// This file is auto-generated by scripts/generate-builtin-providers.ts +// Do not edit manually - run 'bun run generate-providers' to update + +export const providerName = 'xai' +export const providerConfig = { + name: 'xai', + config: { + api: 'openai-completions', + baseUrl: 'https://api.x.ai/v1', + apiKey: 'XAI_API_KEY', + }, + models: [ + { + modelId: 'grok-4.3', + name: 'Grok 4.3', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1000000, + maxTokens: 30000, + cost: { + input: 1.25, + output: 2.5, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'grok-4.5', + name: 'Grok 4.5', + config: { + api: 'openai-responses', + reasoning: true, + input: ['text', 'image'], + contextWindow: 500000, + maxTokens: 500000, + cost: { + input: 2, + output: 6, + cacheRead: 0.3, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'grok-build-0.1', + name: 'Grok Build 0.1', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 256000, + maxTokens: 256000, + cost: { + input: 1, + output: 2, + cacheRead: 0.2, + cacheWrite: 0, + }, + }, + }, + ], +} as const diff --git a/packages/core/src/generated/providers/xiaomi-token-plan-ams.ts b/packages/core/src/generated/providers/xiaomi-token-plan-ams.ts new file mode 100644 index 00000000..4bfbb709 --- /dev/null +++ b/packages/core/src/generated/providers/xiaomi-token-plan-ams.ts @@ -0,0 +1,65 @@ +// This file is auto-generated by scripts/generate-builtin-providers.ts +// Do not edit manually - run 'bun run generate-providers' to update + +export const providerName = 'xiaomi-token-plan-ams' +export const providerConfig = { + name: 'xiaomi-token-plan-ams', + config: { + api: 'openai-completions', + baseUrl: 'https://token-plan-ams.xiaomimimo.com/v1', + apiKey: 'XIAOMI_TOKEN_PLAN_AMS_API_KEY', + }, + models: [ + { + modelId: 'mimo-v2-pro', + name: 'MiMo-V2-Pro', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1048576, + maxTokens: 131072, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mimo-v2.5', + name: 'MiMo-V2.5', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 131072, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mimo-v2.5-pro', + name: 'MiMo-V2.5-Pro', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1048576, + maxTokens: 131072, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + ], +} as const diff --git a/packages/core/src/generated/providers/xiaomi-token-plan-cn.ts b/packages/core/src/generated/providers/xiaomi-token-plan-cn.ts new file mode 100644 index 00000000..e95a0d01 --- /dev/null +++ b/packages/core/src/generated/providers/xiaomi-token-plan-cn.ts @@ -0,0 +1,65 @@ +// This file is auto-generated by scripts/generate-builtin-providers.ts +// Do not edit manually - run 'bun run generate-providers' to update + +export const providerName = 'xiaomi-token-plan-cn' +export const providerConfig = { + name: 'xiaomi-token-plan-cn', + config: { + api: 'openai-completions', + baseUrl: 'https://token-plan-cn.xiaomimimo.com/v1', + apiKey: 'XIAOMI_TOKEN_PLAN_CN_API_KEY', + }, + models: [ + { + modelId: 'mimo-v2-pro', + name: 'MiMo-V2-Pro', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1048576, + maxTokens: 131072, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mimo-v2.5', + name: 'MiMo-V2.5', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 131072, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mimo-v2.5-pro', + name: 'MiMo-V2.5-Pro', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1048576, + maxTokens: 131072, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + ], +} as const diff --git a/packages/core/src/generated/providers/xiaomi-token-plan-sgp.ts b/packages/core/src/generated/providers/xiaomi-token-plan-sgp.ts new file mode 100644 index 00000000..8bac1fbf --- /dev/null +++ b/packages/core/src/generated/providers/xiaomi-token-plan-sgp.ts @@ -0,0 +1,65 @@ +// This file is auto-generated by scripts/generate-builtin-providers.ts +// Do not edit manually - run 'bun run generate-providers' to update + +export const providerName = 'xiaomi-token-plan-sgp' +export const providerConfig = { + name: 'xiaomi-token-plan-sgp', + config: { + api: 'openai-completions', + baseUrl: 'https://token-plan-sgp.xiaomimimo.com/v1', + apiKey: 'XIAOMI_TOKEN_PLAN_SGP_API_KEY', + }, + models: [ + { + modelId: 'mimo-v2-pro', + name: 'MiMo-V2-Pro', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1048576, + maxTokens: 131072, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mimo-v2.5', + name: 'MiMo-V2.5', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 131072, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mimo-v2.5-pro', + name: 'MiMo-V2.5-Pro', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1048576, + maxTokens: 131072, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + ], +} as const diff --git a/packages/core/src/generated/providers/xiaomi.ts b/packages/core/src/generated/providers/xiaomi.ts new file mode 100644 index 00000000..6637ae3e --- /dev/null +++ b/packages/core/src/generated/providers/xiaomi.ts @@ -0,0 +1,116 @@ +// This file is auto-generated by scripts/generate-builtin-providers.ts +// Do not edit manually - run 'bun run generate-providers' to update + +export const providerName = 'xiaomi' +export const providerConfig = { + name: 'xiaomi', + config: { + api: 'openai-completions', + baseUrl: 'https://api.xiaomimimo.com/v1', + apiKey: 'XIAOMI_API_KEY', + }, + models: [ + { + modelId: 'mimo-v2-flash', + name: 'MiMo-V2-Flash', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 262144, + maxTokens: 65536, + cost: { + input: 0.14, + output: 0.28, + cacheRead: 0.0028, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mimo-v2-omni', + name: 'MiMo-V2-Omni', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 262144, + maxTokens: 131072, + cost: { + input: 0.14, + output: 0.28, + cacheRead: 0.0028, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mimo-v2-pro', + name: 'MiMo-V2-Pro', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1048576, + maxTokens: 131072, + cost: { + input: 0.435, + output: 0.87, + cacheRead: 0.0036, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mimo-v2.5', + name: 'MiMo-V2.5', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 1048576, + maxTokens: 131072, + cost: { + input: 0.14, + output: 0.28, + cacheRead: 0.0028, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mimo-v2.5-pro', + name: 'MiMo-V2.5-Pro', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1048576, + maxTokens: 131072, + cost: { + input: 0.435, + output: 0.87, + cacheRead: 0.0036, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'mimo-v2.5-pro-ultraspeed', + name: 'MiMo-V2.5-Pro-UltraSpeed', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1048576, + maxTokens: 131072, + cost: { + input: 1.305, + output: 2.61, + cacheRead: 0.0108, + cacheWrite: 0, + }, + }, + }, + ], +} as const diff --git a/packages/core/src/generated/providers/zai-coding-cn.ts b/packages/core/src/generated/providers/zai-coding-cn.ts new file mode 100644 index 00000000..89232744 --- /dev/null +++ b/packages/core/src/generated/providers/zai-coding-cn.ts @@ -0,0 +1,116 @@ +// This file is auto-generated by scripts/generate-builtin-providers.ts +// Do not edit manually - run 'bun run generate-providers' to update + +export const providerName = 'zai-coding-cn' +export const providerConfig = { + name: 'zai-coding-cn', + config: { + api: 'openai-completions', + baseUrl: 'https://open.bigmodel.cn/api/coding/paas/v4', + apiKey: '', + }, + models: [ + { + modelId: 'glm-4.5-air', + name: 'GLM-4.5-Air', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 98304, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'glm-4.7', + name: 'GLM-4.7', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 204800, + maxTokens: 131072, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'glm-5-turbo', + name: 'GLM-5-Turbo', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 200000, + maxTokens: 131072, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'glm-5.1', + name: 'GLM-5.1', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 200000, + maxTokens: 131072, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'glm-5.2', + name: 'GLM-5.2', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1000000, + maxTokens: 131072, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'glm-5v-turbo', + name: 'GLM-5V-Turbo', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 131072, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + ], +} as const diff --git a/packages/core/src/generated/providers/zai.ts b/packages/core/src/generated/providers/zai.ts new file mode 100644 index 00000000..ef3431fb --- /dev/null +++ b/packages/core/src/generated/providers/zai.ts @@ -0,0 +1,116 @@ +// This file is auto-generated by scripts/generate-builtin-providers.ts +// Do not edit manually - run 'bun run generate-providers' to update + +export const providerName = 'zai' +export const providerConfig = { + name: 'zai', + config: { + api: 'openai-completions', + baseUrl: 'https://api.z.ai/api/coding/paas/v4', + apiKey: 'ZAI_API_KEY', + }, + models: [ + { + modelId: 'glm-4.5-air', + name: 'GLM-4.5-Air', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 131072, + maxTokens: 98304, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'glm-4.7', + name: 'GLM-4.7', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 204800, + maxTokens: 131072, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'glm-5-turbo', + name: 'GLM-5-Turbo', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 200000, + maxTokens: 131072, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'glm-5.1', + name: 'GLM-5.1', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 200000, + maxTokens: 131072, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'glm-5.2', + name: 'GLM-5.2', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text'], + contextWindow: 1000000, + maxTokens: 131072, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + { + modelId: 'glm-5v-turbo', + name: 'GLM-5V-Turbo', + config: { + api: 'openai-completions', + reasoning: true, + input: ['text', 'image'], + contextWindow: 200000, + maxTokens: 131072, + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + }, + }, + ], +} as const diff --git a/scripts/generate-builtin-providers.ts b/scripts/generate-builtin-providers.ts index 8aac7dce..c8586192 100644 --- a/scripts/generate-builtin-providers.ts +++ b/scripts/generate-builtin-providers.ts @@ -57,82 +57,135 @@ export function sortProviders(entries: [string, unknown][]): [string, unknown][] }) } -async function sync() { - console.log('Fetching pi models from GitHub...') - const res = await fetch( - 'https://raw.githubusercontent.com/earendil-works/pi/refs/heads/main/packages/ai/src/models.generated.ts', +function toIdentifier(name: string): string { + const camel = name.replace(/-([a-z0-9])/g, (_, g) => g.toUpperCase()) + return camel.replace(/[^a-zA-Z0-9_$]/g, '_') +} + +async function loadModelData(): Promise> { + // Check local pi-mono data directory first + const piMonoDataDir = path.resolve( + process.cwd(), + '..', + 'pi-mono', + 'packages', + 'ai', + 'src', + 'providers', + 'data', ) - if (!res.ok) { - throw new Error(`Failed to fetch pi models: ${res.statusText}`) + if (fs.existsSync(piMonoDataDir)) { + console.log(`Loading model data from local pi-mono workspace: ${piMonoDataDir}`) + const files = fs + .readdirSync(piMonoDataDir) + .filter((f) => f.endsWith('.json') && !f.startsWith('.')) + const rawProviders: Record = {} + for (const file of files) { + const providerName = path.basename(file, '.json') + const filePath = path.join(piMonoDataDir, file) + const content = JSON.parse(fs.readFileSync(filePath, 'utf8')) + rawProviders[providerName] = content + } + return rawProviders } - let text = await res.text() - console.log('Parsing models...') - // Remove imports - text = text.replace(/import\s+.*?from\s+['"].*?['"];?/g, '') + throw new Error( + `Model data directory not found at ${piMonoDataDir}. Please run 'npm run generate-models' in pi-mono.`, + ) +} - // Remove 'satisfies Model<...>' - text = text.replace(/satisfies\s+Model<[^>]+>/g, '') +async function sync() { + console.log('Loading pi model data...') + const rawModels = await loadModelData() - // Write to a temporary file to import it - const tmpPath = path.join(process.cwd(), 'scripts', 'tmp-models.ts') - fs.writeFileSync(tmpPath, text) - - try { - const { MODELS } = await import(tmpPath) + // eslint-disable-next-line @typescript-eslint/no-explicit-any + const providers: Record = {} + const sortedEntries = sortProviders(Object.entries(rawModels)) + for (const [providerName, models] of sortedEntries) { // eslint-disable-next-line @typescript-eslint/no-explicit-any - const providers: Record = {} + const modelList = Object.values(models as Record) + if (modelList.length === 0) continue - const sortedEntries = sortProviders(Object.entries(MODELS)) - - for (const [providerName, models] of sortedEntries) { + const firstModel = modelList[0] + providers[providerName] = { + name: providerName, + config: { + api: firstModel.api, + baseUrl: firstModel.baseUrl, + apiKey: envMap[providerName] || '', + }, // eslint-disable-next-line @typescript-eslint/no-explicit-any - const modelList = Object.values(models as Record) - if (modelList.length === 0) continue - - const firstModel = modelList[0] - providers[providerName] = { - name: providerName, + models: modelList.map((m: any) => ({ + modelId: m.id, + name: m.name, config: { - api: firstModel.api, - baseUrl: firstModel.baseUrl, - apiKey: envMap[providerName] || '', + api: m.api, + reasoning: m.reasoning, + input: m.input, + contextWindow: m.contextWindow, + maxTokens: m.maxTokens, + cost: m.cost, }, - // eslint-disable-next-line @typescript-eslint/no-explicit-any - models: modelList.map((m: any) => ({ - modelId: m.id, - name: m.name, - config: { - api: m.api, - reasoning: m.reasoning, - input: m.input, - contextWindow: m.contextWindow, - maxTokens: m.maxTokens, - cost: m.cost, - }, - })), - } + })), } + } - const generatedDir = path.join(process.cwd(), 'packages', 'core', 'src', 'generated') - if (!fs.existsSync(generatedDir)) { - fs.mkdirSync(generatedDir, { recursive: true }) + const generatedDir = path.join(process.cwd(), 'packages', 'core', 'src', 'generated') + const providersSubdir = path.join(generatedDir, 'providers') + + if (!fs.existsSync(providersSubdir)) { + fs.mkdirSync(providersSubdir, { recursive: true }) + } + + // Clean existing files in providers directory + const existingSubFiles = fs.readdirSync(providersSubdir) + for (const file of existingSubFiles) { + if (file.endsWith('.ts')) { + fs.unlinkSync(path.join(providersSubdir, file)) } + } - const outPath = path.join(generatedDir, 'providers.generated.ts') - const outContent = `// This file is auto-generated by scripts/generate-builtin-providers.ts + // Write individual provider files + const importStatements: string[] = [] + const providerEntries: string[] = [] + + for (const [providerName, providerData] of Object.entries(providers)) { + const filePath = path.join(providersSubdir, `${providerName}.ts`) + const fileContent = `// This file is auto-generated by scripts/generate-builtin-providers.ts // Do not edit manually - run 'bun run generate-providers' to update -export const builtinProviders: Record = ${JSON.stringify(providers, null, 2)} as unknown as Record +export const providerName = ${JSON.stringify(providerName)} +export const providerConfig = ${JSON.stringify(providerData, null, 2)} as const ` - fs.writeFileSync(outPath, outContent) - console.log(`Successfully generated builtin providers: ${outPath}`) - } finally { - if (fs.existsSync(tmpPath)) { - fs.unlinkSync(tmpPath) + fs.writeFileSync(filePath, fileContent) + + const identifier = toIdentifier(providerName) + importStatements.push( + `import { providerConfig as ${identifier} } from './providers/${providerName}'`, + ) + if (identifier === providerName) { + providerEntries.push(` ${identifier},`) + } else { + providerEntries.push(` ${JSON.stringify(providerName)}: ${identifier},`) } } + + console.log(`Generated ${Object.keys(providers).length} provider files in ${providersSubdir}`) + + // Write main aggregator providers.generated.ts + const outPath = path.join(generatedDir, 'providers.generated.ts') + const outContent = `// This file is auto-generated by scripts/generate-builtin-providers.ts +// Do not edit manually - run 'bun run generate-providers' to update + +${importStatements.join('\n')} + +export const builtinProviders: Record = { +${providerEntries.join('\n')} +} as unknown as Record +` + fs.writeFileSync(outPath, outContent) + console.log(`Successfully generated aggregator: ${outPath}`) } sync().catch((err) => {