OVHcloud AI models & pricing
OVHcloud AI hosts 15 models (15 with public pricing) covering 1 modalities. EU-sovereign AI endpoints — Llama, Mistral, Qwen, Mixtral. Cheapest input starts at $0.0400/M tokens; the most premium goes up to $0.910/M. Use Future AGI's Agent Command Center to route any OVHcloud AI model with cost-optimized fallback and unified observability.
chat 15
| Model ↕ | Input / 1M ↕ | Output / 1M ↕ | Context ↕ | Caps |
|---|---|---|---|---|
| GPT Oss 20B | $0.0400/M | $0.150/M | 131,000 | reasoning |
| GPT Oss 120B | $0.0800/M | $0.400/M | 131,000 | reasoning |
| Qwen3.32b | $0.0800/M | $0.230/M | 32,000 | tools · reasoning |
| Mistral Small 3.2 24B Instruct 2506 | $0.0900/M | $0.280/M | 128,000 | tools · vision |
| Llama 3.1 8B Instruct | $0.1000/M | $0.1000/M | 131,000 | tools |
| Mistral 7B Instruct v0.3 | $0.1000/M | $0.1000/M | 127,000 | tools |
| Mistral Nemo Instruct 2407 | $0.130/M | $0.130/M | 118,000 | tools |
| Mamba Codestral 7B v0.1 | $0.190/M | $0.190/M | 256,000 | |
| Llava V1.6 Mistral 7B Hf | $0.290/M | $0.290/M | 32,000 | vision |
| Mixtral 8×7B Instruct v0.1 | $0.630/M | $0.630/M | 32,000 | |
| DeepSeek R1 Distill Llama 70B | $0.670/M | $0.670/M | 131,000 | tools · reasoning |
| Meta Llama 3.1 70B Instruct | $0.670/M | $0.670/M | 131,000 | |
| Meta Llama 3.3 70B Instruct | $0.670/M | $0.670/M | 131,000 | tools |
| Qwen2.5 Coder 32B Instruct | $0.870/M | $0.870/M | 32,000 | |
| Qwen2.5 VL 72B Instruct | $0.910/M | $0.910/M | 32,000 | vision |
FAQ
How many OVHcloud AI models are there?
15 OVHcloud AI models are listed across 1 modality on this page. 15 have public per-token pricing.
How is OVHcloud AI pricing verified?
Pricing is aggregated from BerriAI/litellm, models.dev, and OpenRouter and refreshed weekly. Each row shows a per-model "verified" date. If a price is wrong, click the row to open the model page and use the inline "suggest edit" link — submissions go into a public review queue.
Which OVHcloud AI model is cheapest?
Input pricing on OVHcloud AI starts at $0.0400 per 1M tokens. Sort the table by price (or use the in-page filter at the top) to find the cheapest model that matches your capability requirements.
Can I route to OVHcloud AI via an OpenAI-compatible API?
Yes — point your OpenAI client at Future AGI's Agent Command Center, configure a OVHcloud AI target, and call OVHcloud AI models with the standard /v1/chat/completions surface. The same gateway can route to other providers as fallback. Free for the first 100K requests/month.