Devstral Small
View website
Released May 2025, a 24B agentic coding model from Mistral AI. Scores 68.0% on SWE-bench Verified despite being up to 5x smaller than peers. Open-weight under Apache 2.0.
At a glance
- Context window
- 128K tokens
- Max output
- 33K tokens
- Knowledge cutoff
- Dec 2024
- Modalities
- Text Text → Text Text
Capabilities
Function calling
Function calling
Connect to external tools, APIs, and systems.
Code execution
Code execution
Write and execute code in a sandboxed environment.
Pricing by provider
| Provider | Input / 1M tokens | Output / 1M tokens | |
|---|---|---|---|
|
Mistral
|
$0.10 | $0.30 |
Heads up: We do our best to keep these specs & prices accurate. However, cloud costs may fluctuate based on region, usage, and other factors not listed here. These are estimates based on common setups and are for informational purposes only. Always verify current rates & exact specs with the provider before provisioning.
Compare with other models
Estimated prices shown. Actual costs may vary based on context length, batch size, caching, and provider-specific pricing tiers.