Home / Cloudflare Workers AI / Text Generation

Free GPT-OSS 20B API on Cloudflare

Free GPT-OSS 20B API via Cloudflare Workers AI — fast open-weight reasoning within 10,000 free Neurons/day.

About the Model

Why use GPT-OSS 20B?

GPT-OSS 20B is the smaller, faster sibling of GPT-OSS 120B — great when you want quick responses and lower latency while keeping solid reasoning and tool-use.

Capabilities

A strong everyday workhorse for chatbots, drafting, and lightweight agents, with the same open license as the 120B model.

Why it's free

Covered by Cloudflare Workers AI's 10,000 free Neurons per day through the /ai/run endpoint.

How to Access for Free (via Cloudflare Workers AI)

Free access on Cloudflare Workers AI

Call GPT-OSS 20B through Cloudflare's global edge using the unified /ai/run REST endpoint. Every Cloudflare account includes 10,000 Neurons per day for free — great for fast, low-latency reasoning at no cost.

Authentication (BYOK)

Use your own Cloudflare Account ID and an API token with Workers AI access via Authorization: Bearer <token>.

Try it in your browser

Pick a model, paste your own free key, and run. Your key is sent once to call the provider and never stored on our servers.

The model's reply will stream here.

Code Examples

curl
curl https://api.cloudflare.com/client/v4/accounts/$CF_ACCOUNT_ID/ai/run/@cf/openai/gpt-oss-20b \
  -H "Authorization: Bearer $CF_API_TOKEN" \
  -d '{"messages":[{"role":"user","content":"Summarize the plot of Hamlet in two sentences."}]}'
python
import os, requests

account = os.environ["CF_ACCOUNT_ID"]
token = os.environ["CF_API_TOKEN"]

resp = requests.post(
    f"https://api.cloudflare.com/client/v4/accounts/{account}/ai/run/@cf/openai/gpt-oss-20b",
    headers={"Authorization": f"Bearer {token}"},
    json={"messages": [{"role": "user", "content": "Summarize the plot of Hamlet in two sentences."}]},
)
print(resp.json()["result"]["response"])