Scaleway
16 modelsProvider docs
As of Oct 4, 2026, Scaleway lists 16 supported models in the Sovyron catalog, including Qwen3.8 27B, DeepSeek V4 Flash 0731, GLM-5.2, Qwen3.6 35B-A3B and Mistral Medium 3.5 128B — qwen, deepseek-flash, glm, mistral-medium, gemma and mistral-small families. Its metered rates span $0.0023–$3 per 1M tokens on a 3:1 input:output blend, and every price in the table is Scaleway's own, normalized to USD — open a model to compare it with the cheapest offer across all providers.
Supported models and pricing
16 of 16 models
| Model | 1M input | 1M output | 1M cache read | Context | Released |
|---|---|---|---|---|---|
| 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 | $1.8 | $5.5 | — | 256k | Jun 13, 2026 |
| Qwen3.6 35B-A3B | $0.25 | $1.5 | — | 128k | May 1, 2026 |
| Mistral Medium 3.5 128B | $1.5 | $7.5 | — | 256k | Apr 29, 2026 |
| Gemma 4 26B A4B IT | $0.25 | $0.5 | — | 256k | Apr 1, 2026 |
| Qwen3.5 397B-A17B | $0.6 | $3.6 | — | 256k | Mar 17, 2026 |
| Qwen3 235B A22B Instruct 2507 | $0.75 | $2.25 | — | 260k | Jul 1, 2025 |
| Mistral Small 3.2 24B Instruct | $0.15 | $0.35 | — | 128k | Jun 20, 2025 |
| Qwen3 Embedding 8B | $0.1 | free | — | 33k | Jun 5, 2025 |
| Qwen3-Coder 30B-A3B Instruct | $0.2 | $0.8 | — | 128k | Apr 1, 2025 |
| Llama-3.3-70B-Instruct | $0.9 | $0.9 | — | 100k | Dec 6, 2024 |
| Pixtral 12B 2409 | $0.2 | $0.2 | — | 128k | Sep 25, 2024 |
| BGE Multilingual Gemma2 | $0.1 | free | — | 8k | Jul 26, 2024 |
| GPT OSS 120B | $0.15 | $0.6 | — | 128k | Jan 1, 2024 |
| Whisper Large v3 | $0.003 | free | — | — | Sep 1, 2023 |