OVHcloud AI Endpoints is a cloud platform that resells models with its own infrastructure, billing and regional hosting. Its prices tend to track the first-party rate, with the platform's own quotas and service-level terms attached.
It lists 14 models on this page. 12 of them have a public price. 2 are offered at $0. Coverage spans text and chat (12) and classification and safety (2). The lowest-priced model hosted here is GPT OSS 20B.
OVHcloud AI Endpoints is the lowest paid channel for 2 models that have at least two competing paid hosts, which is where its pricing genuinely leads rather than being the only option.
| Cheapest here? | |||||
|---|---|---|---|---|---|
| Qwen3Guard-Gen-0.6BClassify / Safetyqwen3guard-gen-0.6b | Free | — | 32,768 | Only channel | |
| Qwen3Guard-Gen-8BClassify / Safetyqwen3guard-gen-8b | Free | — | 32,768 | Only channel | |
| GPT OSS 20Bgpt-oss-20b | $0.05 | $0.18 | — | 131,072 | 2.3× pricier |
| Mistral-7B-Instruct-v0.3mistral-7b-instruct-v0.3 | $0.11 | $0.11 | — | 65,536 | Lowest anywhere |
| Qwen3-Coder 30B-A3B Instructqwen3-coder-30b-a3b-instruct | $0.07 | $0.26 | — | 262,144 | 1.1× pricier |
| Qwen3.5 9Bqwen3.5-9b | $0.12 | $0.18 | — | 262,144 | 2.0× pricier |
| Mistral Nemo Instruct 2407mistral-nemo-instruct-2407 | $0.14 | $0.14 | — | 65,536 | 5.6× pricier |
| Mistral Small 3.2 24B Instruct 2506mistral-small-3.2-24b-instruct-2506 | $0.10 | $0.31 | — | 131,072 | Lowest anywhere |
| GPT OSS 120Bgpt-oss-120b | $0.09 | $0.47 | — | 131,072 | 3.1× pricier |
| Meta-Llama-3_3-70B-Instructmeta-llama-3_3-70b-instruct | $0.74 | $0.74 | — | 131,072 | 3.8× pricier |
| Qwen2.5-VL 72B Instructqwen2.5-vl-72b-instruct | $1.01 | $1.01 | — | 32,768 | 1.3× pricier |
| Qwen3.8 27Bqwen3.8-27b | $0.47 | $3.19 | — | 262,144 | 10.1× pricier |
| Qwen3.6 27Bqwen3.6-27b | $0.47 | $3.19 | — | 262,144 | 2.2× pricier |
| Qwen3.5 397B-A17Bqwen3.5-397b-a17b | $0.71 | $4.25 | — | 262,144 | 4.3× pricier |