ovhcloud
OVHcloud
4 models on OVHcloud, with the price per million tokens and who ends up holding your prompt.
- Company based in
- 🇫🇷 France
- How it serves
- Runs 4 models itself
- Training on your prompts
- no training
- Data policy source
- docs.ovhcloud.com
- Policy checked
- 2026-10-20
Models
| Model | Input $/M | Output $/M | Blended* | Holds your prompt | Training |
|---|---|---|---|---|---|
| GPT OSS 120B | ≈$0.09 €0.08 | ≈$0.45 €0.40 | ≈$0.18 | runs it 🇫🇷 France | no training |
| GPT OSS 20B | ≈$0.04 €0.04 | ≈$0.17 €0.15 | ≈$0.08 | runs it 🇫🇷 France | no training |
| Llama-3.3-70B-Instruct | ≈$0.75 €0.67 | ≈$0.75 €0.67 | ≈$0.75 | runs it 🇫🇷 France | no training |
| Qwen3.8 27B | ≈$0.45 €0.40 | ≈$3.02 €2.70 | ≈$1.09 | runs it 🇫🇷 France | no training |
≈ converted from EUR at 1 EUR = $1.1193 (ECB reference rate, 2026-10-23)
Blended is our calculation: (3 × input + output) ÷ 4, US dollars per million tokens — most calls read far more than they write. Tiers that are cheaper because they train on your data are not used for the “from” price.