Chat, embedding, reasoning, and other model APIs — not only LLMs
Run models at the edge from Workers, with an OpenAI-compatible endpoint and AI Gateway
Serverless and dedicated inference for open models, plus a hosted MCP endpoint over Hub tools
Open-source proxy and SDK exposing 100+ model providers behind one OpenAI-compatible API
Unified model endpoint with failover, spend limits, and observability, wired into the AI SDK
AI analytics notebooks & Threads; hosted Hex MCP for project search, data Q&A, and notebook edits.
Pay-per-run AI runtime with 150+ apps, agents, and skills over remote MCP.
Same query as JSON: /api/v1/services?category=think&has_mcp=trueMCP server:https://mcp.botfriendly.xyz