OVHcloud AI Endpoints
14 modelsProvider docs
As of Oct 4, 2026, OVHcloud AI Endpoints lists 14 supported models in the Sovyron catalog, including Qwen3.8 27B, Qwen3.6 27B, Qwen3.5 397B-A17B, Qwen3.5 9B and Qwen3Guard-Gen-0.6B — qwen, gpt-oss, mistral-small and mistral families. Its metered rates span $0.0825–$1.595 per 1M tokens on a 3:1 input:output blend, and every price in the table is OVHcloud AI Endpoints's own, normalized to USD — open a model to compare it with the cheapest offer across all providers. Offer mix: 2 free-tier offers.
Supported models and pricing
14 of 14 models
| Model | 1M input | 1M output | 1M cache read | Context | Released | Tags |
|---|---|---|---|---|---|---|
| Qwen3.8 27B | $0.47 | $3.19 | — | 262k | Sep 2, 2026 | |
| Qwen3.6 27B | $0.47 | $3.19 | — | 262k | Jun 1, 2026 | |
| Qwen3.5 397B-A17B | $0.71 | $4.25 | — | 262k | May 18, 2026 | |
| Qwen3.5 9B | $0.12 | $0.18 | — | 262k | Apr 22, 2026 | |
| Qwen3Guard-Gen-0.6B | free | free | — | 33k | Jan 22, 2026 | free |
| Qwen3Guard-Gen-8B | free | free | — | 33k | Jan 22, 2026 | free |
| Qwen3-Coder 30B-A3B Instruct | $0.07 | $0.26 | — | 262k | Oct 28, 2025 | |
| GPT OSS 120B | $0.09 | $0.47 | — | 131k | Aug 28, 2025 | |
| GPT OSS 20B | $0.05 | $0.18 | — | 131k | Aug 28, 2025 | |
| Mistral Small 3.2 24B Instruct 2506 | $0.1 | $0.31 | — | 131k | Jul 16, 2025 | |
| Meta-Llama-3_3-70B-Instruct | $0.74 | $0.74 | — | 131k | Apr 1, 2025 | |
| Mistral 7B Instruct v0.3 | $0.11 | $0.11 | — | 66k | Apr 1, 2025 | |
| Qwen2.5-VL 72B Instruct | $1.01 | $1.01 | — | 33k | Mar 31, 2025 | |
| Mistral Nemo Instruct 2407 | $0.14 | $0.14 | — | 66k | Nov 20, 2024 |