Free Gemma 3 12B API via Cloudflare Workers AI — multilingual, vision-enabled open model within 10,000 free Neurons/day.
Gemma 3 12B is Google's well-rounded open model with long context, broad multilingual support and image understanding (vision).
Great for multilingual chat, summarization, and vision-grounded Q&A, with a strong quality-to-size ratio.
Covered by Cloudflare Workers AI's 10,000 free Neurons per day via the /ai/run endpoint.
Call Gemma 3 12B through Cloudflare's global edge using the unified /ai/run REST endpoint. Every Cloudflare account includes 10,000 Neurons per day for free, covering multilingual chat and vision-grounded tasks 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.
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.
curl https://api.cloudflare.com/client/v4/accounts/$CF_ACCOUNT_ID/ai/run/@cf/google/gemma-3-12b-it \
-H "Authorization: Bearer $CF_API_TOKEN" \
-d '{"messages":[{"role":"user","content":"List three uses for a paperclip."}]}'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/google/gemma-3-12b-it",
headers={"Authorization": f"Bearer {token}"},
json={"messages": [{"role": "user", "content": "List three uses for a paperclip."}]},
)
print(resp.json()["result"]["response"])