What's free
10,000 Neurons/day, all account plans
- Credit card
- not required
- Phone verification
- not required
- Commercial use
- allowed
Free limits
| requests per minute | 300 |
|---|
text generation; models that require Workers Paid: 20 requests/minute per model. The daily allowance is 10,000 Neurons, a unit that is not requests or tokens. Source: the provider's page, read 2026-10-08.
In the provider's words
10,000 Neurons/day (free allocation). Per-task request limits: text generation 300 requests/min (models that require Workers Paid: 20 requests/min per model); text embeddings 3,000/min; speech recognition, text-to-image, translation, image-to-text 720/min
The catch
Resets daily at 00:00 UTC; overage on a Workers Paid plan bills at $0.011/1,000 Neurons. A few models (e.g. Kimi K2.6/K2.7-code, GLM-5.2) now require a Workers Paid plan
Free models · sample
@cf/meta/llama-3.3-70b-instruct-fp8-fast@cf/meta/llama-3.1-8b-instruct@cf/mistralai/mistral-small-3.1-24b-instruct@cf/qwen/qwen2.5-coder-32b-instruct@cf/deepseek-ai/deepseek-r1-distill-qwen-32b@cf/google/gemma-3-12b-itA sample of models reachable on the free tier — the live catalog changes. Pull the current set with GET https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/v1/models.
Quickstart — chat completions
from openai import OpenAI
client = OpenAI(base_url="https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/v1", api_key="<YOUR_FREE_API_KEY>")
resp = client.chat.completions.create(
model="@cf/meta/llama-3.3-70b-instruct-fp8-fast",
messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)…or with curl:
curl https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"@cf/meta/llama-3.3-70b-instruct-fp8-fast","messages":[{"role":"user","content":"Hello!"}]}'Appears in
Compare
Change history
How this free tier has changed since we started tracking it (2026-07-30) — generated from the git history of providers.json.
- 2026-10-08 Updated rate limits
- 2026-08-02 Updated the catch
- 2026-07-30 Added to the hub