Free tier - verified
Is Cloudflare Workers AI free?
Yes. Cloudflare Workers AI offers a daily free allocation on the Workers Free and Paid plans. Whether a card is required is not stated. Trains on your data: No.
Read from developers.cloudflare.com. Compare every free LLM API
- Offer
- Free tier
- Card required
- Not stated
- Trains on data
- No
- Verified
- 2026-10-18
The offer
- Offer class
Standing free tier
Recorded as: free tier (daily allocation)
“Our free allocation allows anyone to use a total of 10,000 Neurons per day at no charge.”
developers.cloudflare.com “| Workers Free | 10,000 Neurons per day | N/A - Upgrade to Workers Paid |”
developers.cloudflare.com - How to get it
"Workers AI is included in both the Free and Paid Workers plans"
- Card required
Not stated
Free-tier limits
Values are copied exactly as the provider publishes them, units included. Not stated means the public docs give no value.
- Free allocation (shared across all models)
- 10,000 Neurons per day
- Text Generation rate limit
- 300 requests per minute, unless the model requires the Workers Paid plan
- Reset
- All limits reset daily at 00:00 UTC
| Model | Neuron rate | Free allocation | Rate limit | Source |
|---|---|---|---|---|
| @cf/openai/gpt-oss-120b | 31818 neurons per M input tokens68182 neurons per M output tokens | 10,000 Neurons per day (shared) | 300 requests per minute | developers.cloudflare.com |
| @cf/openai/gpt-oss-20b | 18182 neurons per M input tokens27273 neurons per M output tokens | 10,000 Neurons per day (shared) | 300 requests per minute | developers.cloudflare.com |
| @cf/moonshotai/kimi-k2.5 | 54545 neurons per M input tokens9091 neurons per M cached input tokens272727 neurons per M output tokens | 10,000 Neurons per day (shared) | 300 requests per minute | developers.cloudflare.com |
| @cf/zai-org/glm-4.7-flash | 5500 neurons per M input tokens36400 neurons per M output tokens | 10,000 Neurons per day (shared) | 300 requests per minute | developers.cloudflare.com |
| @cf/qwen/qwen3.8-27b | 40909 neurons per M input tokens290909 neurons per M output tokens | 10,000 Neurons per day (shared) | 300 requests per minute | developers.cloudflare.com |
| @cf/qwen/qwen3-30b-a3b-fp8 | 4625 neurons per M input tokens30475 neurons per M output tokens | 10,000 Neurons per day (shared) | 300 requests per minute | developers.cloudflare.com |
| @cf/google/gemma-4-26b-a4b-it | 9091 neurons per M input tokens27273 neurons per M output tokens | 10,000 Neurons per day (shared) | 300 requests per minute | developers.cloudflare.com |
| @cf/nvidia/nemotron-3-120b-a12b | 45455 neurons per M input tokens136364 neurons per M output tokens | 10,000 Neurons per day (shared) | 300 requests per minute | developers.cloudflare.com |
| @cf/meta/llama-4-scout-17b-16e-instruct | 24545 neurons per M input tokens77273 neurons per M output tokens | 10,000 Neurons per day (shared) | 300 requests per minute | developers.cloudflare.com |
| @cf/meta/llama-3.3-70b-instruct-fp8-fast | 26668 neurons per M input tokens204805 neurons per M output tokens | 10,000 Neurons per day (shared) | 300 requests per minute | developers.cloudflare.com |
| @cf/mistralai/mistral-small-3.1-24b-instruct | 31876 neurons per M input tokens50488 neurons per M output tokens | 10,000 Neurons per day (shared) | 300 requests per minute | developers.cloudflare.com |
| @cf/ibm-granite/granite-4.0-h-micro | 1542 neurons per M input tokens10158 neurons per M output tokens | 10,000 Neurons per day (shared) | 300 requests per minute | developers.cloudflare.com |
38 LLMs listed on the pricing page; 7 require a paid billing method (kimi-k2.6, kimi-k2.7-code, glm-5.2, glm-5.3, glm-5.3-flash, deepseek-v4-flash-0731, deepseek-v4-pro-0813), leaving 31 usable on the free allocation. 12 shown.
From the limits docs
“300 requests per minute, unless the model requires the Workers Paid plan”
“All limits reset daily at 00:00 UTC. If you exceed any one of the above limits, further operations will fail with an error.”
Does it train on your data?
No
No.
“No training: Cloudflare does not use Customer Content processed by Workers AI to train AI models.”
“Your inputs (for example, text prompts, images, and audio), outputs (for example, generated text, images, and translations), embeddings, and any training or adaptation data you provide are Customer Content as that term is defined in our Agreements.”
Restrictions
Frontier models need paid billing
“Some models require a paid billing method. This applies to @cf/moonshotai/kimi-k2.6, @cf/moonshotai/kimi-k2.7-code, @cf/zai-org/glm-5.2, @cf/zai-org/glm-5.3, @cf/zai-org/glm-5.3-flash, @cf/deepseek-ai/deepseek-v4-flash-0731, and @cf/deepseek-ai/deepseek-v4-pro-0813.”
developers.cloudflare.com
Upgrade path
"On Workers Paid, you will be charged at $0.011 / 1,000 Neurons for any usage above the free allocation of 10,000 Neurons per day."
FAQ
Is Cloudflare Workers AI free?
Yes. Cloudflare Workers AI offers a daily free allocation on the Workers Free and Paid plans. Whether a card is required is not stated. Trains on your data: No.
What are the Cloudflare Workers AI free limits?
10,000 Neurons per day shared across models; 300 requests per minute for text generation. 38 LLMs listed on the pricing page; 7 require a paid billing method (kimi-k2.6, kimi-k2.7-code, glm-5.2, glm-5.3, glm-5.3-flash, deepseek-v4-flash-0731, deepseek-v4-pro-0813), leaving 31 usable on the free allocation. 12 shown.
Does Cloudflare Workers AI train on your data?
No. The terms say: "No training: Cloudflare does not use Customer Content processed by Workers AI to train AI models."
Sources
Last verified from Cloudflare Workers AI's own pages below. Quotes are verbatim.
Newsletter
Know when a free tier changes
One email per week. New model releases, pricing and limit changes, and what they mean for what you build.