Cloudflare Workers AI Free Tier
10,000 free Workers AI Neurons per day for open LLMs and embeddings
What you get from Cloudflare Workers AI Free Tier for free
Overview
Cloudflare Workers AI runs open-weight models on Cloudflare's GPU network, callable from a Worker binding or the REST API (including an OpenAI-compatible endpoint). Workers AI is included in both the Workers Free and Workers Paid plans, and the pricing page states: "Our free allocation allows anyone to use a total of 10,000 Neurons per day at no charge."
Free Tier Quotas & Limits
- 10,000 Neurons per day, all models combined; "All limits reset daily at 00:00 UTC."
- On Workers Free there is no overage: usage stops at the allocation. Workers Paid bills $0.011 per 1,000 Neurons beyond it.
- Rate limits per task type: text generation 300 requests per minute, text embeddings 3,000 (bge-large-en-v1.5: 1,500), speech recognition 720.
- Models listed as requiring a paid billing method on the pricing page (Kimi K2.6/K2.7-code, GLM-5.2/5.3/5.3-flash, DeepSeek V4/V4.1 Flash and V4 Pro) need Workers Paid or prepaid AI Gateway credits.
Neuron cost per million tokens differs by model: for example @cf/meta/llama-3.1-8b-instruct uses 25,608 Neurons per million input tokens and 75,147 per million output tokens, while @cf/qwen/qwen3-30b-a3b-fp8 uses 4,625 and 30,475.
Key Free Models
@cf/meta/llama-3.3-70b-instruct-fp8-fast, @cf/meta/llama-3.1-8b-instruct, @cf/openai/gpt-oss-120b, @cf/openai/gpt-oss-20b, @cf/qwen/qwen3-30b-a3b-fp8, @cf/qwen/qwq-32b, @cf/qwen/qwen2.5-coder-32b-instruct, @cf/mistralai/mistral-small-3.1-24b-instruct, @cf/google/gemma-3-12b-it, @cf/google/gemma-4-26b-a4b-it, @cf/deepseek-ai/deepseek-r1-distill-qwen-32b, @cf/zai-org/glm-4.7-flash, and the BGE embedding models (@cf/baai/bge-m3 and others).
How to Get Started
Create a free Cloudflare account, open Workers AI in the dashboard, create an API token with Workers AI permission and call https://api.cloudflare.com/client/v4/accounts/<account_id>/ai/run/<model>, or bind AI in a Worker.
Models served free
Limits as the provider publishes them; a dash means none is published.
| Model | Context | RPM | RPD | TPM | Tools | Vision |
|---|---|---|---|---|---|---|
| @cf/meta/llama-3.3-70b-instruct-fp8-fastText Generation: 300 requests per minute; counts against 10,000 free Neurons/day | — | 300 | — | — | — | — |
| @cf/openai/gpt-oss-120bText Generation: 300 requests per minute; counts against 10,000 free Neurons/day | — | 300 | — | — | — | — |
| @cf/openai/gpt-oss-20bText Generation: 300 requests per minute; counts against 10,000 free Neurons/day | — | 300 | — | — | — | — |
| @cf/qwen/qwen3-30b-a3b-fp8Text Generation: 300 requests per minute; counts against 10,000 free Neurons/day | — | 300 | — | — | — | — |
| @cf/mistralai/mistral-small-3.1-24b-instructText Generation: 300 requests per minute; counts against 10,000 free Neurons/day | — | 300 | — | — | — | — |
| @cf/google/gemma-4-26b-a4b-itText Generation: 300 requests per minute; counts against 10,000 free Neurons/day | — | 300 | — | — | — | — |
| @cf/zai-org/glm-4.7-flashText Generation: 300 requests per minute; counts against 10,000 free Neurons/day | — | 300 | — | — | — | — |
| @cf/baai/bge-m3Text Embeddings: 3,000 requests per minute; counts against 10,000 free Neurons/day | — | 3,000 | — | — | — | — |
History
Listed on , first verification pending · last automated check : no change found. Automated findings never change this page until a person confirms them (how we verify).
- Listedby a person · Published from a draft after review
Still works?
Work at Cloudflare? Add an aifree.dev badge
<a href="https://aifree.dev/offer/cloudflare-workers-ai-free-tier"><img src="https://aifree.dev/badge/cloudflare-workers-ai-free-tier" alt="Cloudflare Workers AI Free Tier on aifree.dev" height="20"></a>[](https://aifree.dev/offer/cloudflare-workers-ai-free-tier)Understand it
A few minutes of play-along, no sign-up.
- Why can I run Llama on my laptop but not GPT? · Open weights vs closed API models, and model licenses · 5 min
- How does a 30 GB model fit on my laptop? · Quantization (bits per weight) · 5 min
More free coding tools
Related offers
100,000 requests/day - 100,000 Worker requests per day
Free tier - Per-organization limits tracked as RPM, RPD, TPM, TPD
30,000,000 tokens/month - 30M tokens/month on the free tier (input + output, incl. reasoning)
6 months - 6 months of Pro-resources access, one-time per account
12 months - One-year license via the GitHub Student Pack
$240 - Free while GitHub student status is active