Free GPT-OSS 120B API via Cloudflare Workers AI — OpenAI's open-weight flagship reasoning within 10,000 free Neurons/day.
GPT-OSS 120B is OpenAI's open-weight flagship — strong at reasoning, coding, and tool use, with adjustable reasoning effort so you can trade speed against depth per request.
Built for agentic and analytical work with native tool-calling. A top pick when you want frontier reasoning from a self-hostable, openly licensed model.
Runs within Cloudflare Workers AI's 10,000 free Neurons per day allowance via the /ai/run endpoint.
Call GPT-OSS 120B through Cloudflare's global edge using the unified /ai/run REST endpoint. Every Cloudflare account includes 10,000 Neurons per day for free, enough to explore frontier open-weight reasoning at no cost.
Use your own Cloudflare Account ID and an API token with Workers AI access via Authorization: Bearer <token>.
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.
curl https://api.cloudflare.com/client/v4/accounts/$CF_ACCOUNT_ID/ai/run/@cf/openai/gpt-oss-120b \
-H "Authorization: Bearer $CF_API_TOKEN" \
-d '{"messages":[{"role":"user","content":"Solve: 17 * 24 and show your reasoning."}]}'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-120b",
headers={"Authorization": f"Bearer {token}"},
json={"messages": [{"role": "user", "content": "Solve: 17 * 24 and show your reasoning."}]},
)
print(resp.json()["result"]["response"])