Free LLM API Hub
Star on GitHub52

OVHcloud AI Endpoints

Ongoing verified 2026-10-08 · 2d ago no cardOpenAI-compatible

EU-hosted, no-account access to open models

Official docs ↗Visit website ↗Report a change

What's free

Seven models are currently listed as Free: two Qwen3Guard moderation models, Stable Diffusion XL and four NVIDIA Riva TTS voices; access is available anonymously or with an API key tied to a Public Cloud project

Credit card
not required
Phone verification
not confirmed
Commercial use
not confirmed

Free limits

Free limits as the provider publishes them
requests per minute2

anonymous access, per IP and per model. With an API access key the page gives 400 requests per minute per Public Cloud project and per model, but the getting-started guide says keys from projects without a payment method (Discovery mode) cannot use the service, so that figure needs a project with a payment method. Source: the provider's page, read 2026-10-09.

In the provider's words

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 free-model tier

PlanOngoing free tier
How it renewsFree with no end date
Expiresno expiry
Modalitiestext, image, audio
OpenAI base URLhttps://oai.endpoints.kepler.ai.cloud.ovh.net/v1

Free models · sample

Qwen3Guard-Gen-8BQwen3Guard-Gen-0.6Bstable-diffusion-xl-base-v10nvr-tts-de-denvr-tts-es-esnvr-tts-it-itnvr-tts-en-us

A sample of models reachable on the free tier — the live catalog changes. Pull the current set with GET https://oai.endpoints.kepler.ai.cloud.ovh.net/v1/models.

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="Qwen3Guard-Gen-8B",
    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":"Qwen3Guard-Gen-8B","messages":[{"role":"user","content":"Hello!"}]}'

Appears in

Free LLM APIs with no credit cardOpenAI-compatible free LLM APIsPermanently free LLM APIsFree multimodal LLM APIsNo credit cardOpenAI-compatibleSpeech (STT/TTS)Image generation

Compare

Compare with another provider →

Change history

How this free tier has changed since we started tracking it (2026-07-30) — generated from the git history of providers.json.

← All providers