OVHcloud AI Endpoints
- Categories
- Inference hosts
- Owned by
- OVH Groupe SA (EPA: OVH) · also owns OVHcloud, OVHcloud Managed Kubernetes
- HQ
- FR
- Website
- https://www.ovhcloud.com/en/public-cloud/ai-endpoints/
- Pricing page
- https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/
- Fee model
- per_token
- Fees
- Per million tokens (EUR), separate input/output; STT per second; some models (Qwen3Guard, SDXL, Riva TTS) free
- Free tier
- Some models free (Qwen3Guard-Gen, stable-diffusion-xl, NVIDIA Riva TTS)
- OpenAI-compatible API
- yes
- Bring your own key
- no
- Notes
- List prices in EUR; USD in offer rows converted at ECB EURUSD 1.1481 2026-09-17 (latest ECB reference rate). OpenAI-compatible base URL https://oai.endpoints.kepler.ai.cloud.ovh.net/v1. Catalog lists quantization and max context per model.
- Sources
- https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/ collected 2026-09-18
LLM prices (8 models, USD per 1M tokens)
| Model | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| gpt-oss-120b gpt-oss-120b |
$0.092 | $0.459 | — | — | ✓ src |
| gpt-oss-20b gpt-oss-20b |
$0.046 | $0.172 | — | — | ✓ src |
| Llama 3.3 70B Instruct Meta-Llama-3_3-70B-Instruct |
$0.769 | $0.769 | — | — | ✓ src |
| Qwen2.5-VL 72B Qwen2.5-VL-72B-Instruct |
$1.04 | $1.04 | — | — | ✓ src |
| Qwen3.5 9B Qwen3.5-9B |
$0.115 | $0.172 | — | — | ✓ src |
| Qwen3.5-397B-A17B Qwen3.5-397B-A17B |
$0.689 | $4.13 | — | — | ✓ src |
| Qwen3.6 27B Qwen3.6-27B |
$0.459 | $3.10 | — | — | ✓ src |
| Qwen3.8-27B Qwen3.8-27B |
$0.459 | $3.10 | — | — | ✓ src |