Free Gemma 4 26B API via Cloudflare Workers AI — Google's efficient multilingual open model within 10,000 free Neurons/day.
Gemma 4 26B is Google's latest-generation open model, using an efficient mixture-of-experts design (~4B active parameters of 26B) to deliver strong quality at low compute cost.
Broad multilingual coverage with solid reasoning and instruction-following — a great default for assistants, summarization, and content generation.
Runs within Cloudflare Workers AI's 10,000 free Neurons per day through the /ai/run endpoint.
Call Gemma 4 26B through Cloudflare's global edge using the unified /ai/run REST endpoint. Every Cloudflare account includes 10,000 Neurons per day for free, so multilingual assistants and content tools run 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/google/gemma-4-26b-a4b-it \
-H "Authorization: Bearer $CF_API_TOKEN" \
-d '{"messages":[{"role":"user","content":"Translate \"good morning\" into Japanese, French, and Swahili."}]}'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-4-26b-a4b-it",
headers={"Authorization": f"Bearer {token}"},
json={"messages": [{"role": "user", "content": "Translate 'good morning' into Japanese, French, and Swahili."}]},
)
print(resp.json()["result"]["response"])