Cloudflare Workers AI

Cloudflare Workers AI

active

Cloudflare's edge inference platform — 10,000 free neurons/day across 50+ models (LLMs, vision, embeddings, image generation) running on the global Workers network.

https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/v1

Avg Latency

90-day Uptime

%

Rate Limits

— RPM / — RPD

Sign-up Required

Yes

Info

Base URL https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/v1
Sign-up Required Yes
Credit Card Not required
Context Window 128K
Last Verified 2026-05-20
openai-compatiblemulti-providerllamadeepseekvisionembedding

Models (12)

@cf/openai/gpt-oss-120b

CTX: 128K

active

@cf/openai/gpt-oss-20b

CTX: 128K

active

@cf/meta/llama-3.3-70b-instruct-fp8-fast

CTX: 24K

active

@cf/meta/llama-4-scout-17b-16e-instruct

CTX: 128K

active

@cf/meta/llama-3.1-8b-instruct-fp8-fast

CTX: 128K

active

@cf/meta/llama-3.2-3b-instruct

CTX: 128K

active

@cf/meta/llama-3.2-11b-vision-instruct

CTX: 128K

active

@cf/mistralai/mistral-small-3.1-24b-instruct

CTX: 128K

active

@cf/qwen/qwen2.5-coder-32b-instruct

CTX: 32K

active

@cf/qwen/qwq-32b

CTX: 32K

active

@cf/deepseek-ai/deepseek-r1-distill-qwen-32b

CTX: 80K

active

@cf/google/gemma-3-12b-it

CTX: 128K

active

Quick Start

bash
export API_KEY="your_api_key_here"
curl https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $API_KEY" \
  -d '{
    "model": "@cf/openai/gpt-oss-120b",
    "messages": [
      {"role": "user", "content": "Hello! How are you?"}
    ]
  }'