Free OVHcloud AI Endpoints API Key, Base URL & Rate Limits
API ProviderOVHcloud AI Endpoints provides free API access to open-weight models (Qwen, Mistral, Llama, DeepSeek) hosted in European data centers.
How to get a free OVHcloud AI Endpoints API key
- 1 Go to endpoints.ai.cloud.ovh.net No registration needed for anonymous tier.
- 2 (Optional) Create an OVHcloud account for higher limits
- 3 Pick a model Qwen3-Coder, Mistral, Llama, DeepSeek available.
- 4 Start making requests Anonymous tier: just send requests. Registered: get API token.
- 5 Configure OpenAI client Base URL: https://oai.endpoints.kepler.ai.cloud.ovh.net/v1
Provider Snapshot
Supported Models 14 models
View in directory →| Model ID | Developer | Context | Availability | Free Tier | Use cases |
|---|---|---|---|---|---|
| qwen3.6-27b Qwen3.6-27B | Alibaba | 131K | Online | Yes | chat |
| qwen3.5-397b-a17b Qwen3.5-397B-A17B | Alibaba | 131K | Online | Yes | chat |
| qwen3.5-9b Qwen3.5-9B | Alibaba | 131K | Online | Yes | chat |
| qwen3-coder-30b-a3b-instruct Qwen3-Coder-30B-A3B-Instruct | Alibaba | 262K | Online | Yes | chatcoding |
| qwen2.5-vl-72b-instruct Qwen2.5-VL-72B-Instruct | OVHcloud AI Endpoints | 128K | Online | Yes | chat |
| mistral-small-3-2-24b-instruct Mistral-Small-3.2-24B-Instruct | OVHcloud AI Endpoints | 128K | Online | Yes | chat |
| mistral-nemo-instruct-2407 Mistral-Nemo-Instruct-2407 | OVHcloud AI Endpoints | 128K | Online | Yes | chat |
| mistral-7b-instruct-v0.3 Mistral-7B-Instruct-v0.3 | OVHcloud AI Endpoints | 32K | Online | Yes | chat |
| qwen3-32b Qwen3-32B | Alibaba | 131K | Online | Yes | chat |
| meta-llama-3_3-70b-instruct Meta-Llama-3_3-70B-Instruct | Meta | 131K | Online | Yes | chat |
| gpt-oss-20b gpt-oss-20b | OpenAI | 128K | Check provider | Yes | chatcoding |
| llama-3-1-8b-instruct Llama-3.1-8B-Instruct | Meta | 131K | Check provider | Yes | chat |
| qwen3guard-gen-8b Qwen3Guard-Gen-8B | OVHcloud AI Endpoints | 32K | Check provider | Yes | chat |
| qwen3guard-gen-0-6b Qwen3Guard-Gen-0.6B | OVHcloud AI Endpoints | 32K | Check provider | Yes | chat |
Developer Tools
Related Providers
View all →OVHcloud AI Endpoints FreeLLM Score free API access score
How we score →What is OVHcloud AI Endpoints?
EU-hosted free LLM APIs — GDPR compliant, no registration for anonymous tier.
OVHcloud AI Endpoints provides free API access to open-weight models (Qwen, Mistral, Llama, DeepSeek) hosted in European data centers. The anonymous tier requires no registration at all — just send requests. Registered users get higher rate limits. Ideal for EU developers who need GDPR-compliant hosting and low-latency European inference.
- No registration needed for anonymous tier
- EU-hosted (GDPR compliant)
- Qwen3-Coder, Mistral, Llama, DeepSeek
- OpenAI-compatible endpoint
API Compatibility: OpenAI SDK-compatible (Chat Completions)
OVHcloud AI Endpoints Free Tier Limits & Pricing
OVHcloud AI Endpoints API Setup Tutorials
OVHcloud AI Endpoints is fully compatible with popular AI coding assistants like Cursor, Claude Code, and more. To see step-by-step API configuration instructions for your favorite tool, please visit our Global Configuration Guide →
OVHcloud AI Endpoints Model Use Cases
What OVHcloud AI Endpoints's free models are best for, based on aggregated model capabilities:
OVHcloud AI Endpoints Limitations & Caveats
- Anonymous tier has very low, unpublished rate limits
- Some models experience cold starts (5-10s first request)
- EU-hosted only — higher latency outside Europe
OVHcloud AI Endpoints FAQ
What are the rate limits on OVHcloud's anonymous tier?
OVHcloud doesn't publish exact limits for the anonymous tier, but it's designed for testing — typically a few requests per minute. Register for a free account to get higher, documented limits.
Is OVHcloud AI Endpoints GDPR compliant?
Yes — all models run in OVHcloud's European data centers (France). Data never leaves the EU, making it suitable for GDPR-sensitive workloads.
Do I need an API key for the anonymous tier?
No — the anonymous tier requires no API key at all. Just send requests directly to the endpoint. This is unique among LLM providers.