Cloudflare Workers AI

Cloudflare Workers AI runs machine learning models on Cloudflare's global edge network, providing low-latency inference close to users worldwide. Supports text generation, embeddings, image generation, and speech-to-text with a simple REST API. Pay-per-use pricing with generous free tier.

Official Website Documentation

Endpoints

POST

Text Generation

/v1/chat/completions

Generate text using models running on Cloudflare edge network.

Streaming

Vision

Function Calling

Models

@cf/meta/llama-3.1-8b-instruct@cf/meta/llama-3.3-70b-instruct@cf/mistral/mistral-7b-instruct-v0.2@cf/google/gemma-2-9b-it

Pricing

Model	Input Price	Output Price	Context Window
Llama 3.1 8B (free: 1B tokens/day)	Free	Free	32.0K
Llama 3.3 70B (paid)	Free	Free	128.0K

Capabilities

Streaming

JSON Mode

Embeddings

Image Input

Audio Input

Audio Output

Try it in Playground

Test Cloudflare Workers AI APIs directly in our interactive playground with your own API key.

Try it in Playground

Cloudflare Workers AI

Endpoints

Text Generation

Capabilities

Try it in Playground

Overview

Cloudflare Workers AI

Endpoints

Text Generation

Capabilities

Try it in Playground

Overview