A specialised model for exploring repositories, editing multiple files and using tools. Delivers strong SWE-bench performance on one GPU.
| SWE-bench Verified | 65.8 | |
|---|---|---|
| SWE-bench Multilingual | 51.6 | |
| Terminal Bench | 32 |
Which GPU does Devstral Small 2 24B need?
The entry configuration is 1x RTX3090, which delivers around 24 tokens per second. For more parallel requests and headroom on speed, go with 1x H200.
How much does Devstral Small 2 24B cost?
An hour of Devstral Small 2 24B runs from $0.45 to $8.26 depending on the GPU configuration. Billing is hourly: you pay for server time, not for tokens.
How do I call Devstral Small 2 24B from my code?
Once deployed you get an OpenAI-compatible endpoint: point any OpenAI client at the base_url you receive and pass devstral-small-2:24b as the model name. Code written against the OpenAI API needs no changes.
Does the data stay private?
Yes. Devstral Small 2 24B runs on a dedicated GPU server inside a private loop: requests and responses never reach the model vendor and are not used for training.
What context window and license does Devstral Small 2 24B have?
Devstral Small 2 24B holds 32K tokens of context per request and ships under the Apache 2.0 license, so you can use it commercially on your own hosting terms.