Scaleway
17 modelsProvider docs
As of Nov 22, 2026, Scaleway lists 17 supported models in the Sovyron catalog, including DeepSeek V4.1 Flash 1017, LightOnOCR-3 0.8B, GLM-5.3, Qwen3.8 27B and DeepSeek V4 Flash 0731 across the deepseek-flash, lightonocr, glm, qwen, mistral-medium and gemma families. The cheapest rate in the table is Mistral Small 3.2 24B Instruct at $0.3925 per 1M output tokens, the priciest Mistral Medium 3.5 128B at $8.4113. On a 3:1 input:output blend the metered rates span $0.0841–$3.3645 per 1M tokens, and every price is Scaleway's own, normalized to USD. Offer mix: metered per-token rates only, with no free-tier or subscription offers in the catalog. Open a model to compare it with the cheapest offer across all providers.
Supported models and pricing
17 of 17 models
| Model | 1M input | 1M output | 1M cache read | Context | Released |
|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | $0.672 | $2.016 | $0.134 | 256k | Oct 17, 2026 |
| LightOnOCR-3 0.8B | $2.464 | free | — | 262k | Oct 8, 2026 |
| GLM-5.3 | $2.01 | $6.15 | — | 256k | Aug 14, 2026 |
| Qwen3.8 27B | $0.684 | $3.762 | $0.137 | 262k | Aug 14, 2026 |
| DeepSeek V4 Flash 0731 | $0.468 | $0.936 | $0.0936 | 256k | Jul 31, 2026 |
| GLM-5.2 | $2.0187 | $6.1682 | — | 256k | Jun 13, 2026 |
| Mistral Medium 3.5 128B | $1.6823 | $8.4113 | — | 256k | Apr 29, 2026 |
| Qwen3.6 35B-A3B | $0.2804 | $1.6823 | — | 128k | Apr 17, 2026 |
| Gemma 4 26B A4B IT | $0.2804 | $0.5607 | — | 256k | Apr 2, 2026 |
| Qwen3.5 397B-A17B | $0.6729 | $4.0374 | — | 256k | Feb 15, 2026 |
| GPT OSS 120B | $0.1682 | $0.6729 | — | 128k | Aug 5, 2025 |
| Qwen3 235B A22B Instruct 2507 | $0.8411 | $2.5234 | — | 260k | Jul 21, 2025 |
| Mistral Small 3.2 24B Instruct | $0.1682 | $0.3925 | — | 128k | Jun 20, 2025 |
| Qwen3 Embedding 8B | $0.1121 | free | — | 33k | Jun 5, 2025 |
| Llama-3.3-70B-Instruct | $1.0093 | $1.0093 | — | 100k | Dec 6, 2024 |
| BGE Multilingual Gemma2 | $0.1121 | free | — | 8k | Jul 25, 2024 |
| Whisper Large v3 | — | — | — | — | Sep 1, 2023 |