Skip to content
Sovyron

OVHcloud AI Endpoints

11 modelsProvider docs

As of Nov 22, 2026, OVHcloud AI Endpoints lists 11 supported models in the Sovyron catalog, including Qwen3.8 27B, Qwen3.6 27B, Qwen3.5 9B, Qwen3.5 397B-A17B and Qwen3Guard-Gen-0.6B across the qwen, gpt-oss, mistral-small, qwen-vl and llama families. The cheapest rate in the table is Qwen3.5 9B at $0.18 per 1M output tokens, the priciest Qwen3.5 397B-A17B at $4.25. On a 3:1 input:output blend the metered rates span $0.0825–$1.595 per 1M tokens, and every price is OVHcloud AI Endpoints's own, normalized to USD. Offer mix: 2 free-tier offers. Open a model to compare it with the cheapest offer across all providers.

Supported models and pricing

11 of 11 models
OVHcloud AI Endpoints model prices in USD per 1M tokens, updated Nov 22, 2026
Model1M input1M output1M cache readContextReleasedTags
Qwen3.8 27B$0.47$3.19—262kAug 14, 2026
Qwen3.6 27B$0.47$3.19—262kApr 22, 2026
Qwen3.5 9B$0.12$0.18—262kFeb 23, 2026
Qwen3.5 397B-A17B$0.71$4.25—262kFeb 15, 2026
Qwen3Guard-Gen-0.6Bfreefree—33kJan 22, 2026free
Qwen3Guard-Gen-8Bfreefree—33kJan 22, 2026free
GPT OSS 120B$0.09$0.47—131kAug 5, 2025
GPT OSS 20B$0.05$0.18—131kAug 5, 2025
Mistral Small 3.2 24B Instruct 2506$0.1$0.31—131kJun 20, 2025
Qwen2.5-VL 72B Instruct$1.01$1.01—33kJan 26, 2025
Meta-Llama-3_3-70B-Instruct$0.74$0.74—131kDec 6, 2024