Scaleway Generative APIs
Serverless OpenAI-compatible API for open-weight models, hosted in Paris, France by Scaleway (Iliad group).
Data stays in Paris and the first 1,000,000 tokens are free, which suits French and EU teams testing open-weight models under GDPR terms. Billing is in EUR, so the USD figures shown are conversions at about 1.17 and move with the exchange rate. Rates on shared models run above US hosts: slightly for gpt-oss-120b ($0.18 / $0.70 against $0.15 / $0.60 at Fireworks AI or Together AI), far more for DeepSeek-V4-Flash-0731 ($0.47 / $0.94 against $0.06 / $0.18 at DeepInfra). GLM-5.2 and DeepSeek-V4-Flash are capped at 256k context.
- Headquarters
- 🇫🇷 France
- Parent jurisdiction
- 🇫🇷 France (parent: Iliad)
- EU self-serve plan
- Available; check eligible plans and regions
- GDPR DPA
- Yes
- Billing
- payg
- Free tier
- First 1,000,000 tokens free
- Open source
- No
- Website
- www.scaleway.com
- Source last checked
- 2026-10-06
- Pricing evidence
- Published rates
Pricing
Calculated from the listed vendor rates; exclusions still apply. How to read these estimates.
| Model | Input / 1M tokens | Output / 1M tokens | Cached / 1M tokens | Context | Details |
|---|---|---|---|---|---|
| GLM-5.2 | $2.11 | $6.44 | — | 256k | frontieropen weights |
| DeepSeek-V4-Flash-0731 | $0.47 | $0.94 | $0.09 | 256k | midopen weights |
| Qwen3-235B-A22B-Instruct-2507 | $0.88 | $2.63 | — | 250k | midopen weights |
| gpt-oss-120b | $0.18 | $0.7 | — | 128k | midopen weights |
| Mistral Small 3.2 24B | $0.18 | $0.41 | — | 128k | smallopen weights |
Scaleway bills in EUR; USD values here converted at ~1.17 USD/EUR (EUR list: glm-5.2 1.80/5.50, deepseek-v4-flash-0731 0.40/0.80 cached 0.08, qwen3-235b 0.75/2.25, gpt-oss-120b 0.15/0.60, mistral-small-3.2 0.15/0.35). Data processed in Paris; GDPR terms via Scaleway's AI Services Specific Conditions. GLM-5.2 and DeepSeek-V4-Flash are capped at 256k context (1M during preview). Batch API is 50% off.
Managed alternatives
At 500M input tokens / month, 50M output tokens / month. Adjust usage and requirements.
Scaleway Generative APIs · Mistral Small 3.2 24B: $1,326/yr estimated.
- Groq · gpt-oss-20b: $630/yr estimated · $696/yr bill differencePublished rates
- OpenAI · GPT-6 Luna: $900/yr estimated · $426/yr bill differencePublished rates
- Mistral AI · Ministral 3 8B: $990/yr estimated · $336/yr bill differencePublished rates
- Alibaba Cloud Model Studio (Qwen) · Qwen3.8-Flash: $1,182/yr estimated · $144/yr bill differencePublished rates
- Fireworks AI · GLM 5.3 Flash: $1,200/yr estimated · $126/yr bill differencePublished rates
No cheaper managed estimate matches your filters. Adjust your usage or compare with your actual contract bill.
The price difference leaves out migration costs, operating costs and any features you’d need to replace. We compare the selected model or the cheapest listed model in the chosen capability tier. Sharing a tier does not mean equal quality.
Self-hosted options
Operating cost is not estimated. These options are not counted as savings against managed services.
Found a wrong rate or plan restriction? Report a correction with a current source.