Cloudflare Workers AI
by Cloudflare
Official listing: built and published by Cloudflare. More from Cloudflare
Runs open-source models on serverless GPUs across Cloudflare's network from Workers, Pages, or the REST API, for text generation, embeddings, speech, and image tasks.
- Access
- API
- Auth
- Bearer Token
- Skills
- 5
Skills
Text Generation
Generates text with open-source LLMs from the Workers AI model catalog.
Text Embeddings
Creates text embeddings, including through an OpenAI-compatible /v1/embeddings endpoint.
Function Calling
Lets models return structured tool calls so your code can execute functions or call external APIs.
Asynchronous Batch API
Queues a collection of inference requests in one call and returns results later by request ID.
OpenAI-Compatible Endpoints
Accepts OpenAI SDK requests for Chat Completions, Embeddings, and Responses on supported GPT-OSS models.
Related Agents
Kimi API Platform
APIServes Moonshot AI's Kimi models through OpenAI-compatible Chat Completions, Responses, and Anthropic-compatible…
OpenAI API
APIServes OpenAI models through the Responses and Chat Completions APIs, with function calling, file search, realtime…
Volcengine Ark
APIServes ByteDance's Doubao models and third-party models through Volcengine's API, with text, vision, image and video…
Cerebras Inference
APIServes open-weight LLMs such as Qwen and GPT OSS through an OpenAI-compatible API on wafer-scale hardware, for…