A directory of services AI agents can actually use — APIs, tools and merchants with machine-readable interfaces and agent payment protocols. Badges are probe-backed, never self-asserted.
| Service | Category | Score |
|---|
 Anthropic Claude APIOpenAPIMPP Claude models with tool use, the MCP connector, Agent Skills, and the Claude Agent SDK | Models | ||
 Cloudflare Workers AIMCPOpenAPIllms.txt Run models at the edge from Workers, with an OpenAI-compatible endpoint and AI Gateway | Models | ||
 Google Gemini APIOpenAPIMPP Gemini multimodal models via Google AI Studio and Vertex AI, with function calling and MCP support | Models | ||
 Hugging Face InferenceMCPOpenAPI Serverless and dedicated inference for open models, plus a hosted MCP endpoint over Hub tools | Models | ||
 LiteLLMMCPOpenAPI Open-source proxy and SDK exposing 100+ model providers behind one OpenAI-compatible API | Models | ||
 OpenAI APIOpenAPIACPMPP GPT-5 series models, embeddings, and the Responses API with native MCP and tool use | Models | ||
 OpenRouterOpenAPIllms.txt One OpenAI-compatible endpoint in front of hundreds of hosted models, with automatic fallback and per-key spend limits | Models | ||
 ReplicateOpenAPIllms.txt Run thousands of open-source models — LLM, image, video, audio — behind one API | Models | ||
 Vercel AI GatewayMCPOpenAPIllms.txt Unified model endpoint with failover, spend limits, and observability, wired into the AI SDK | Models | ||
 BasetenOpenAPIllms.txt Dedicated deployments and autoscaling inference for open and custom models | Models | ||
 Cerebras InferenceOpenAPI Wafer-scale inference API serving open models at very high tokens per second | Models | ||
 CohereOpenAPIllms.txt Models tuned for enterprise RAG, reranking, search, and classification | Models | ||
 DeepL APIOpenAPI High-quality machine translation and document translation over REST | Models | ||
 DeepSeek APIOpenAPI Low-cost reasoning and chat models with an OpenAI-compatible interface | Models | ||
 Fireworks AIOpenAPI Fast, cheap serving for open-source LLMs, vision, and audio models | Models | ||
 GroqOpenAPI Ultra-fast LLM inference on custom LPU hardware, tuned for low time-to-first-token | Models | ||
 Mistral AIOpenAPIllms.txt Open and commercial models with fast inference, function calling, and OCR endpoints | Models | ||
 Perplexity APIOpenAPIllms.txt Search-grounded LLM API returning cited answers over live web content | Models | ||
 PortkeyOpenAPIllms.txt AI gateway with conditional routing, guardrails, caching, and governance across model providers | Models | ||
 Together AIOpenAPIllms.txt Run, fine-tune, and serve open-source models via API | Models |
Same query as JSON: /api/v1/services?category=think&auth_method=api-key