Scaleway SAS Models
French cloud provider hosting Generative APIs in Paris, France. Applies a zero data retention policy by default: prompts and outputs are not stored, and data never leaves European jurisdiction. Requesty routes to 3 Scaleway SAS models starting at $0.17 per 1M input tokens with context windows up to 256K tokens. One API key and an OpenAI-compatible SDK. Provider rates plus 5% on pay as you go, or 0% with your own keys.
Flagship model
deepseek-v4-flash-0731Intelligence Index
51.8
Coding Index
69.1
GPQA Diamond
90.8%
All Scaleway SAS models
| Model | Context | Max Output | Input/1M | Output/1M | Capabilities | Coding |
|---|---|---|---|---|---|---|
| 256K | 33K | $0.46 | $0.93 | 69 | ||
| 256K | 33K | $2.09 | $6.38 | 69 | ||
| 128K | 33K | $0.17 | $0.70 | 30 |
About Scaleway SAS on Requesty
How many Scaleway SAS models are available through Requesty?
Requesty routes to 3 Scaleway SAS models including regional variants, with pricing synced in real time to the upstream provider.
What is the cheapest Scaleway SAS model?
The cheapest Scaleway SAS model starts at $0.17 per million input tokens. See the pricing column in the table below for full per-model rates.
Does Requesty add markup on Scaleway SAS pricing?
No. Requesty passes through exactly what Scaleway SAS charges. You pay the same per-token rates as going direct, plus you get smart routing, caching, analytics, and one unified API for 600+ models.
Is my data used to train Scaleway SAS models?
Scaleway SAS's terms state that API data is not used for training. See their privacy policy for the authoritative statement.
Where are Scaleway SAS models hosted?
Scaleway SAS models are hosted in 🇪🇺 EU (France). Some models are available in additional regions through AWS Bedrock, Azure, or Google Vertex AI: filter by region on the Scaleway SAS rows in the models explorer.