Tip
If you created a Scaleway Account but did not register a valid payment method, stricter limits apply to ensure usage stays within Free Tier only.
Rate limits
Reviewed on 09 December 2024 • Published on 27 August 2024
What are the limits?Link to this anchor
Any model served through Scaleway Generative APIs gets limited by:
- Tokens per minute
- Queries per minute
Base limits apply if you registered a valid payment method. This limits are increased automatically if you also validate your identity.
How can I increase the rate limits?Link to this anchor
We actively monitor usage and will improve rates based on feedback. If you need to increase your rate limits:
- Verify your identity to automatically increase your rate limit as described below
- Contact our support team, providing details on the model used and specific use case, for additional increase. Note that for increases of up to x5 or x10 volumes, we highly recommend using dedicated deployments with Managed Inference, which provides exactly the same features and API compatibility.
Chat modelsLink to this anchor
| Model string | Additional steps required | Requests per minute | Total tokens per minute |
|---|---|---|---|
llama-3.1-8b-instruct | None | 300 | 200K |
llama-3.1-70b-instruct | None | 300 | 200K |
llama-3.3-70b-instruct | None | 300 | 200K |
llama-3.3-70b-instruct | Identity verified | 600 | 400K |
mistral-nemo-instruct-2407 | None | 300 | 200K |
pixtral-12b-2409 | None | 300 | 200K |
qwen2.5-32b-instruct | None | 300 | 200K |
Embedding modelsLink to this anchor
| Model string | Requests per minute | Input tokens per minute |
|---|---|---|
bge-multilingual-gemma2 | 300 | 400K |
Why do we set rate limits?Link to this anchor
These limits safeguard against abuse or misuse of Scaleway Generative APIs, helping to ensure fair access to the API with consistent performance.
Was this page helpful?