What's free
Several open-weight models in the catalog (e.g. Qwen3Guard) listed as $0 per token, permanently, via two access modes: anonymous (no account) and authenticated (API key tied to a Public Cloud project)
Rate limits
Anonymous access: 2 requests/min per IP per model. Authenticated (API key): 400 requests/min per project per model. Exceeding either returns HTTP 429
The catch
European provider (France), relevant for EU data-sovereignty/GDPR-conscious use. The authenticated tier needs a valid payment method on the project (though "Free" models themselves don't charge); anonymous access needs neither an account nor a card. A separate general $200 Public Cloud trial voucher also exists but is unrelated to this permanent free-model tier
Quickstart — chat completions
from openai import OpenAI
client = OpenAI(base_url="https://oai.endpoints.kepler.ai.cloud.ovh.net/v1", api_key="<YOUR_FREE_API_KEY>")
resp = client.chat.completions.create(
model="<a-free-model>",
messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)…or with curl:
curl https://oai.endpoints.kepler.ai.cloud.ovh.net/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"<a-free-model>","messages":[{"role":"user","content":"Hello!"}]}'