OVHcloud AI Endpoints

by docs.ovhcloud.com

AI models and chat Added on November 3rd, 2026 Checked and working on November 3rd, 2026

What it does

OVHcloud AI Endpoints serves open-weight models such as Llama 3.3 70B, Mistral Small, Qwen and gpt-oss through an OpenAI-compatible API, hosted in Europe, for example to add chat, summaries or image description to an application. POST JSON to /v1/chat/completions, with streaming and tool calling. Free without a key at up to 2 requests per minute per IP address and per model; an API key from a paid Public Cloud project raises this to 400 requests per minute, billed per token.

API
JSON
REST

At a glance

API key: Not needed · More APIs with no key
Pricing: Free without a key at up to 2 requests per minute per IP address and per model; an API key from a paid Public Cloud project raises this to 400 requests per minute, billed per token.
From the browser: Yes (CORS)
Formats: JSON
Interface: REST
Provider: docs.ovhcloud.com
Last checked: Working on November 3rd, 2026

More information: https://docs.ovhcloud.com/en/guides/public-cloud/ai-machine-learning/ai-endpoints-getting-started

Used in: Build a chatbot on free AI API tiers

Is this your service? Show that it is listed

Put this badge on your website or in your README; it links to this page. About the badge

HTML

<a href="https://free-web-services.com/web-services/ai/llm/ovhcloud-ai-endpoints.html"><img src="https://free-web-services.com/badge.svg" width="208" height="44" alt="Listed on Free Web Services" /></a>

Markdown

[![Listed on Free Web Services](https://free-web-services.com/badge.svg)](https://free-web-services.com/web-services/ai/llm/ovhcloud-ai-endpoints.html)

OVHcloud AI Endpoints — docs.ovhcloud.com

Example request

curl

curl -X POST 'https://oai.endpoints.kepler.ai.cloud.ovh.net/v1/chat/completions' \
  -H 'Content-Type: application/json' \
  -d '{"model":"Mistral-Small-3.2-24B-Instruct-2506","messages":[{"role":"user","content":"Say hello in one word."}],"max_tokens":10}'

JavaScript

const response = await fetch("https://oai.endpoints.kepler.ai.cloud.ovh.net/v1/chat/completions", {
  method: 'POST',
  headers: {
    "Content-Type": "application/json",
  },
  body: JSON.stringify({"model":"Mistral-Small-3.2-24B-Instruct-2506","messages":[{"role":"user","content":"Say hello in one word."}],"max_tokens":10}),
});
const data = await response.json();
console.log(data);

Python

import requests

response = requests.post(
    "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1/chat/completions",
    headers={
        "Content-Type": "application/json",
    },
    json={
        "model": "Mistral-Small-3.2-24B-Instruct-2506",
        "messages": [
            {
                "role": "user",
                "content": "Say hello in one word.",
            },
        ],
        "max_tokens": 10,
    },
    timeout=30,
)
print(response.json())

The JavaScript works in a web page as well as in Node.js 18 or newer.