{"server":{"name":"modelpricewatch","title":"Model Price Watch","version":"1.0.0"},"protocol":"Model Context Protocol","transport":"streamable-http","protocolVersion":"2025-06-18","endpoint":"https://modelpricewatch.com/mcp","instructions":"Live LLM API pricing from modelpricewatch.com. Use these tools to look up current input/output token prices, context windows, and capabilities for 150+ AI models across 20+ providers (OpenAI, Anthropic, Google, Mistral, xAI, etc.), compare models, and find the cheapest option for a use case. All prices are USD per 1,000,000 tokens.","tools":[{"name":"search_models","description":"Search the live LLM pricing database by model name, provider, or id. Returns matching models with current input/output prices (USD per 1M tokens), context window, modality, and category. Use this to answer 'how much does <model> cost' or 'what models does <provider> offer'."},{"name":"get_model_pricing","description":"Get full pricing and capability details for one model by its id (from search_models). Returns input/output/cached price per 1M tokens, blended cost, context window, modality, release date, and the modelpricewatch.com page URL."},{"name":"compare_models","description":"Compare 2–5 models side by side on price, context window, and capabilities, with a verdict on which is cheapest for input, output, and a typical blended workload."},{"name":"cheapest_models","description":"Find the cheapest current models, ranked by input price, output price, or a blended cost. The generic ranking covers generative text models (embeddings, OCR and realtime models are excluded — they price different work); pass category to rank a specific pool instead, e.g. 'embedding'. Use to answer 'what is the cheapest model for <use case>'."},{"name":"list_providers","description":"List all tracked AI model providers (OpenAI, Anthropic, Google, etc.) with a short description and their pricing page."}],"allowances":{"unit":"requests per minute","note":"Fair-use guidance to design against, not a hard cap. Enforcement is coarse and happens at the network edge.","tool_calls":{"free":20,"pro":240,"startup":2400,"enterprise":null},"discovery_get":"Rate limited at the edge. Fetch this document once per session and cache it; it only changes when we deploy.","retry_after_seconds":60,"free_alternative":"https://modelpricewatch.com/api/v1/models.json","free_alternative_docs":"https://modelpricewatch.com/api/","request_key_url":"https://modelpricewatch.com/contact/?subject=MCP%20Access","docs_url":"https://modelpricewatch.com/api-pricing/","tiers":[{"tier":"pro","price":"$19/mo","calls_per_minute":240},{"tier":"startup","price":"$99/mo","calls_per_minute":2400},{"tier":"enterprise","price":"$499+/mo","calls_per_minute":null}]},"docs":"https://modelpricewatch.com/api-pricing/"}