Cloudflare Workers AI — Free LLM API
9 free models available — no credit card required. Get API key →
Edge AI inference — 10,000 neurons/day, 50+ models.
Cloudflare Workers AI runs open-weight models directly on Cloudflare's global edge network. The free tier allocates 10,000 Neurons (compute units) per day, supporting 50+ models including Llama, Mistral, Gemma, DeepSeek, and Qwen. Unlike other providers, billing is based on Neurons rather than tokens, making it hard to predict exact request counts. Ideal for low-latency edge deployments.
- 50+ models on the free tier
- 10,000 Neurons/day
- Global edge network for low latency
- Text, image, audio, and embedding models
API Compatibility: OpenAI SDK-compatible (via REST)
All Free Cloudflare Workers AI Models — Context Windows & Rate Limits
| Model | Context | Max Output | Modality | Rate Limit | Status | |
|---|---|---|---|---|---|---|
| @cf/meta/llama-3.3-70b-instruct-fp8-fast | 131K | 131K | 10K neurons/day (shared) | Details | ||
| @cf/meta/llama-3.1-8b-instruct-fp8-fast | 131K | 131K | 10K neurons/day (shared) | Details | ||
| @cf/meta/llama-3.2-11b-vision-instruct | 131K | 131K | 10K neurons/day (shared) | Details | ||
| @cf/meta/llama-4-scout-17b-16e-instruct | 10.0M | 131K | 10K neurons/day (shared) | Details | ||
| @cf/mistralai/mistral-small-3.1-24b-instruct | 128K | 131K | 10K neurons/day (shared) | Details | ||
| @cf/google/gemma-4-26b-a4b-it | 256K | 131K | 10K neurons/day (shared) | Details | ||
| @cf/qwen/qwq-32b | 32K | 131K | 10K neurons/day (shared) | Details | ||
| @cf/deepseek-ai/deepseek-r1-distill-qwen-32b | 32K | 131K | 10K neurons/day (shared) | Details | ||
| + 42 more models | 131K | 131K | 10K neurons/day (shared) | Details |
Frequently Asked Questions about Cloudflare Workers AI Free API
Is Cloudflare Workers AI free to use?
Cloudflare Workers AI offers a permanently free tier with 9 available models. No credit card is required to get started — just sign up and generate an API key.
What models does Cloudflare Workers AI offer for free?
Cloudflare Workers AI provides 9 free models covering chat, vision, reasoning use cases. Supported modalities include text, image. Browse the full list above with context windows and rate limits.
How do I use Cloudflare Workers AI with Claude Code or Cursor?
Click "Details" on any model above to get one-click configuration snippets for Claude Code (cc), Cursor, Codex, and more.
All Cloudflare Workers AI models listed here use an OpenAI-compatible endpoint, so any tool that accepts a custom baseURL will work.