cat-shark/pi-commandcode-provider
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
960d0d1f2388d039c8e8cd8f610723c2425ca92b
pi-commandcode-provider/models.json
T
Tao Yang 960d0d1f23 feat: extract models from command-code dist, load via models.json 
- Add scripts/extract-models.ts to parse command-code npm dist file
- Generate models.json (21 models, 15 pricing entries) with contextWindow
  and maxOutputTokens pre-filled; no nulls or hardcoded fallbacks in index.ts
- Rewrite index.ts to load model list and costs from models.json
- Cap gateway model maxOutputTokens at 65536 (API limit for Baseten/Vercel)
- Add 'Update models' section to README documenting the generation flow
- Add npm run extract-models script
2026-05-25 16:37:08 +08:00

545 lines
14 KiB
JSON
Raw Blame History

{
"providers": {
"ANTHROPIC": "anthropic",
"OPENAI": "openai",
"BASETEN": "baseten",
"VERCEL_AI_GATEWAY": "vercel-ai-gateway",
"CLOUDFLARE_AI_GATEWAY": "cloudflare-ai-gateway",
"OPENROUTER": "openrouter"
},
"providerGroups": [
{
"id": "command-code",
"label": "Command Code",
"shortLabel": "cmd",
"description": "recommended",
"providers": [
"anthropic",
"openai",
"baseten",
"vercel-ai-gateway"
]
},
{
"id": "anthropic",
"label": "Anthropic",
"shortLabel": "anth",
"description": "Claude Pro/Max",
"providers": [
"anthropic"
]
},
{
"id": "github-copilot",
"label": "GitHub Copilot",
"shortLabel": "copilot",
"description": "Copilot subscription",
"providers": [
"anthropic",
"openai"
]
},
{
"id": "codex",
"label": "ChatGPT (Codex)",
"shortLabel": "codex",
"description": "ChatGPT Pro/Plus subscription",
"providers": [
"openai"
]
}
],
"models": [
{
"key": "SONNET_4_6",
"id": "claude-sonnet-4-6",
"provider": "anthropic",
"spec": "chatComplete",
"label": "Claude Sonnet 4.6",
"name": "Claude Sonnet 4.6",
"description": "best combo of speed & intelligence (recommended)",
"reasoning": true,
"reasoningEfforts": [
"low",
"medium",
"high",
"xhigh",
"max"
],
"contextWindow": 1000000,
"maxOutputTokens": 64000,
"vendorLabel": null
},
{
"key": "OPUS_4_7",
"id": "claude-opus-4-7",
"provider": "anthropic",
"spec": "chatComplete",
"label": "Claude Opus 4.7",
"name": "Claude Opus 4.7",
"description": "most intelligent for agents and coding",
"reasoning": true,
"reasoningEfforts": [
"low",
"medium",
"high",
"xhigh",
"max"
],
"contextWindow": 1000000,
"maxOutputTokens": 64000,
"vendorLabel": null
},
{
"key": "HAIKU_4_5",
"id": "claude-haiku-4-5-20251001",
"provider": "anthropic",
"spec": "chatComplete",
"label": "Claude Haiku 4.5",
"name": "Claude Haiku 4.5",
"description": "fastest & most compact, great for quick tasks",
"reasoning": false,
"reasoningEfforts": null,
"contextWindow": 200000,
"maxOutputTokens": 64000,
"vendorLabel": null
},
{
"key": "GPT_5_5",
"id": "gpt-5.5",
"provider": "openai",
"spec": "responses",
"label": "GPT-5.5",
"name": "GPT-5.5",
"description": "latest frontier model for general complex work",
"reasoning": true,
"reasoningEfforts": [
"low",
"medium",
"high",
"xhigh"
],
"contextWindow": 256000,
"maxOutputTokens": 128000,
"vendorLabel": null
},
{
"key": "GPT_5_4",
"id": "gpt-5.4",
"provider": "openai",
"spec": "responses",
"label": "GPT-5.4",
"name": "GPT-5.4",
"description": "frontier model for general complex work",
"reasoning": true,
"reasoningEfforts": [
"low",
"medium",
"high",
"xhigh"
],
"contextWindow": 400000,
"maxOutputTokens": 128000,
"vendorLabel": null
},
{
"key": "GPT_5_3_CODEX",
"id": "gpt-5.3-codex",
"provider": "openai",
"spec": "responses",
"label": "GPT-5.3 Codex",
"name": "GPT-5.3 Codex",
"description": "frontier coding model",
"reasoning": true,
"reasoningEfforts": [
"low",
"medium",
"high",
"xhigh"
],
"contextWindow": 400000,
"maxOutputTokens": 128000,
"vendorLabel": null
},
{
"key": "GPT_5_4_MINI",
"id": "gpt-5.4-mini",
"provider": "openai",
"spec": "responses",
"label": "GPT-5.4 Mini",
"name": "GPT-5.4 Mini",
"description": "fast, cost-effective model for everyday tasks",
"reasoning": true,
"reasoningEfforts": [
"low",
"medium",
"high"
],
"contextWindow": 400000,
"maxOutputTokens": 128000,
"vendorLabel": null
},
{
"key": "KIMI_K2_6",
"id": "moonshotai/Kimi-K2.6",
"provider": "vercel-ai-gateway",
"spec": "chatComplete",
"label": "Kimi K2.6",
"name": "Kimi K2.6",
"description": "long-horizon coding with vision",
"reasoning": false,
"reasoningEfforts": null,
"contextWindow": 256000,
"maxOutputTokens": 65536,
"vendorLabel": null
},
{
"key": "KIMI_K2_5",
"id": "moonshotai/Kimi-K2.5",
"provider": "vercel-ai-gateway",
"spec": "chatComplete",
"label": "Kimi K2.5",
"name": "Kimi K2.5",
"description": "multimodal frontend coding",
"reasoning": false,
"reasoningEfforts": null,
"contextWindow": 256000,
"maxOutputTokens": 65536,
"vendorLabel": null
},
{
"key": "GLM_5_1",
"id": "zai-org/GLM-5.1",
"provider": "vercel-ai-gateway",
"spec": "chatComplete",
"label": "GLM-5.1",
"name": "GLM-5.1",
"description": "long-horizon autonomous coding agent",
"reasoning": false,
"reasoningEfforts": null,
"contextWindow": 200000,
"maxOutputTokens": 65536,
"vendorLabel": null
},
{
"key": "GLM_5",
"id": "zai-org/GLM-5",
"provider": "vercel-ai-gateway",
"spec": "chatComplete",
"label": "GLM-5",
"name": "GLM-5",
"description": "multi-mode thinking & long-range planning",
"reasoning": false,
"reasoningEfforts": null,
"contextWindow": 200000,
"maxOutputTokens": 65536,
"vendorLabel": null
},
{
"key": "MINIMAX_M2_7",
"id": "MiniMaxAI/MiniMax-M2.7",
"provider": "vercel-ai-gateway",
"spec": "chatComplete",
"label": "MiniMax M2.7",
"name": "MiniMax M2.7",
"description": "end-to-end software engineering agent",
"reasoning": false,
"reasoningEfforts": null,
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"vendorLabel": null
},
{
"key": "MINIMAX_M2_5",
"id": "MiniMaxAI/MiniMax-M2.5",
"provider": "vercel-ai-gateway",
"spec": "chatComplete",
"label": "MiniMax M2.5",
"name": "MiniMax M2.5",
"description": "cross-platform full-stack agentic dev",
"reasoning": false,
"reasoningEfforts": null,
"contextWindow": 200000,
"maxOutputTokens": 65536,
"vendorLabel": null
},
{
"key": "DEEPSEEK_V4_PRO",
"id": "deepseek/deepseek-v4-pro",
"provider": "vercel-ai-gateway",
"spec": "chatComplete",
"label": "DeepSeek V4 Pro",
"name": "DeepSeek V4 Pro",
"description": "hybrid-attention long-context reasoning",
"reasoning": true,
"reasoningEfforts": [
"high",
"max"
],
"contextWindow": 1000000,
"maxOutputTokens": 384000,
"vendorLabel": null
},
{
"key": "DEEPSEEK_V4_FLASH",
"id": "deepseek/deepseek-v4-flash",
"provider": "vercel-ai-gateway",
"spec": "chatComplete",
"label": "DeepSeek V4 Flash",
"name": "DeepSeek V4 Flash",
"description": "fast hybrid-attention reasoning",
"reasoning": true,
"reasoningEfforts": [
"high",
"max"
],
"contextWindow": 1000000,
"maxOutputTokens": 384000,
"vendorLabel": null
},
{
"key": "QWEN_3_6_MAX_PREVIEW",
"id": "Qwen/Qwen3.6-Max-Preview",
"provider": "vercel-ai-gateway",
"spec": "chatComplete",
"label": "Qwen 3.6 Max Preview",
"name": "Qwen 3.6 Max Preview",
"description": "vibe coding & efficient agent execution",
"reasoning": true,
"reasoningEfforts": null,
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"vendorLabel": null
},
{
"key": "QWEN_3_6_PLUS",
"id": "Qwen/Qwen3.6-Plus",
"provider": "vercel-ai-gateway",
"spec": "chatComplete",
"label": "Qwen 3.6 Plus",
"name": "Qwen 3.6 Plus",
"description": "agentic coding & reasoning",
"reasoning": true,
"reasoningEfforts": null,
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"vendorLabel": null
},
{
"key": "QWEN_3_7_MAX",
"id": "Qwen/Qwen3.7-Max",
"provider": "vercel-ai-gateway",
"spec": "chatComplete",
"label": "Qwen 3.7 Max",
"name": "Qwen 3.7 Max",
"description": "frontier coding & long-horizon agent execution",
"reasoning": true,
"reasoningEfforts": null,
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"vendorLabel": null
},
{
"key": "STEP_3_5_FLASH",
"id": "stepfun/Step-3.5-Flash",
"provider": "vercel-ai-gateway",
"spec": "chatComplete",
"label": "Step 3.5 Flash",
"name": "Step 3.5 Flash",
"description": "fast sparse-MoE agentic reasoning",
"reasoning": true,
"reasoningEfforts": null,
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"vendorLabel": null
},
{
"key": "GEMINI_3_5_FLASH",
"id": "google/gemini-3.5-flash",
"provider": "vercel-ai-gateway",
"spec": "chatComplete",
"label": "Gemini 3.5 Flash",
"name": "Gemini 3.5 Flash",
"description": "Pro-level coding proficiency, parallel agentic execution",
"reasoning": true,
"reasoningEfforts": [
"low",
"medium",
"high"
],
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"vendorLabel": "Google"
},
{
"key": "GEMINI_3_1_FLASH_LITE",
"id": "google/gemini-3.1-flash-lite",
"provider": "vercel-ai-gateway",
"spec": "chatComplete",
"label": "Gemini 3.1 Flash Lite",
"name": "Gemini 3.1 Flash Lite",
"description": "high-volume workhorse model with implicit caching",
"reasoning": true,
"reasoningEfforts": [
"low",
"medium",
"high"
],
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"vendorLabel": "Google"
}
],
"pricing": [
{
"provider": "Anthropic",
"id": "anthropic:claude-sonnet-4-20250514",
"category": "premium",
"promptCost": 3,
"completionCost": 15,
"cacheWrite5mCost": 3.75,
"cacheWrite1hCost": 6,
"cacheHitCost": 0.3
},
{
"provider": "Anthropic",
"id": "anthropic:claude-sonnet-4-5-20250929",
"category": "premium",
"promptCost": 3,
"completionCost": 15,
"cacheWrite5mCost": 3.75,
"cacheWrite1hCost": 6,
"cacheHitCost": 0.3
},
{
"provider": "Anthropic",
"id": "anthropic:claude-opus-4-5-20251101",
"category": "premium",
"promptCost": 5,
"completionCost": 25,
"cacheWrite5mCost": 6.25,
"cacheWrite1hCost": 10,
"cacheHitCost": 0.5
},
{
"provider": "Anthropic",
"id": "anthropic:claude-sonnet-4-6",
"category": "premium",
"promptCost": 3,
"completionCost": 15,
"cacheWrite5mCost": 3.75,
"cacheWrite1hCost": 6,
"cacheHitCost": 0.3
},
{
"provider": "Anthropic",
"id": "anthropic:claude-opus-4-7",
"category": "premium",
"promptCost": 5,
"completionCost": 25,
"cacheWrite5mCost": 6.25,
"cacheWrite1hCost": 10,
"cacheHitCost": 0.5
},
{
"provider": "Anthropic",
"id": "anthropic:claude-opus-4-6",
"category": "premium",
"promptCost": 5,
"completionCost": 25,
"cacheWrite5mCost": 6.25,
"cacheWrite1hCost": 10,
"cacheHitCost": 0.5
},
{
"provider": "Anthropic",
"id": "anthropic:claude-haiku-4-5-20251001",
"category": "premium",
"promptCost": 1,
"completionCost": 5,
"cacheWrite5mCost": 1.25,
"cacheWrite1hCost": 2,
"cacheHitCost": 0.1
},
{
"provider": "OpenAI",
"id": "openai:gpt-5.5",
"category": "premium",
"promptCost": 5,
"completionCost": 30,
"cacheWrite5mCost": 0,
"cacheWrite1hCost": 0,
"cacheHitCost": 0.5
},
{
"provider": "OpenAI",
"id": "openai:gpt-5.4",
"category": "premium",
"promptCost": 2.5,
"completionCost": 15,
"cacheWrite5mCost": 0,
"cacheWrite1hCost": 0,
"cacheHitCost": 0.25
},
{
"provider": "OpenAI",
"id": "openai:gpt-5.3-codex",
"category": "premium",
"promptCost": 2,
"completionCost": 8,
"cacheWrite5mCost": 0,
"cacheWrite1hCost": 0,
"cacheHitCost": 0.5
},
{
"provider": "OpenAI",
"id": "openai:gpt-5.4-mini",
"category": "premium",
"promptCost": 0.75,
"completionCost": 4.5,
"cacheWrite5mCost": 0,
"cacheWrite1hCost": 0,
"cacheHitCost": 0.075
},
{
"provider": "Baseten",
"id": "baseten:zai-org/GLM-5",
"category": "opensource",
"promptCost": 0.95,
"completionCost": 3.15,
"cacheWrite5mCost": 0,
"cacheWrite1hCost": 0,
"cacheHitCost": 0
},
{
"provider": "Baseten",
"id": "baseten:moonshotai/Kimi-K2.5",
"category": "opensource",
"promptCost": 0.6,
"completionCost": 3,
"cacheWrite5mCost": 0,
"cacheWrite1hCost": 0,
"cacheHitCost": 0
},
{
"provider": "Baseten",
"id": "baseten:moonshotai/Kimi-K2.6",
"category": "opensource",
"promptCost": 0.95,
"completionCost": 4,
"cacheWrite5mCost": 0,
"cacheWrite1hCost": 0,
"cacheHitCost": 0.16
},
{
"provider": "Baseten",
"id": "baseten:MiniMaxAI/MiniMax-M2.5",
"category": "opensource",
"promptCost": 0.5,
"completionCost": 2,
"cacheWrite5mCost": 0,
"cacheWrite1hCost": 0,
"cacheHitCost": 0
}
]
}
Reference in New Issue View Git Blame Copy Permalink