Cloudflare Workers AI
Models
Run models at the edge from Workers, with an OpenAI-compatible endpoint and AI Gateway
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.
Models
One OpenAI-compatible endpoint in front of hundreds of hosted models, with automatic fallback and per-key spend limits
Models
Run thousands of open-source models — LLM, image, video, audio — behind one API
Models
Unified model endpoint with failover, spend limits, and observability, wired into the AI SDK
Models
Dedicated deployments and autoscaling inference for open and custom models
Models
Models tuned for enterprise RAG, reranking, search, and classification
Models
Open and commercial models with fast inference, function calling, and OCR endpoints
Models
Search-grounded LLM API returning cited answers over live web content
Models
AI gateway with conditional routing, guardrails, caching, and governance across model providers
Models
Run, fine-tune, and serve open-source models via API
Models
Hosted agentic AI assistant: OpenAI-compatible API, BYOK 50+ providers, free ache/* + paid catalog.
Models
Resold OpenAI-compatible model API. Prepaid tokens; whole-cent rounding up per successful request, US$0.01 minimum.
Same query as JSON: /api/v1/services?category=think&has_llms_txt=true