Devstral Small
Devstral Small is Mistral AI's language model with a 256K context window and up to 64K output tokens, available from 4 providers, starting at $0.100 / 1M input and $0.300 / 1M output. Mistral AI's lightweight agentic coding model built with All Hands AI, specializing in tool-use, codebase exploration, and multi-file editing.
mistral-devstral-small |
| Language |
| Active |
| Mistral AI |
| 256K tokens |
| 64K tokens |
| Text |
| Text |
| · 10 months ago |
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities4/13
Reasoning·
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling·
Structured Outputs✓
Native JSON Schema✓
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill✓
Pricing by Provider
| Provider | Standard | ||
|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | |
Mistral AI | $0.100 | $0.300 | N/A |
 OpenRouter | $0.100 | $0.300 | $0.010 |
 Vercel AI Gateway | $0.100 | $0.300 | N/A |
 Fireworks AI | $0.900 | $0.900 | N/A |
Cost Calculator
Preset:
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Devstral 2 Small 24B Instruct | — | — | — | — | Available |
| Devstral Small | 256K | $0.100 | $0.300 | Current |
Other models
| Model | Tier | Released | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|---|
| Cydonia 24B V4.1 | — | 131K | $0.300 | $0.500 | |
| Mistral Small 4 | — | — | — | — | — |
| Mistral Small 4 Non-Reasoning | — | — | — | — | — |
| Mistral Medium 3.5 | — | 262K | $1.50 | $7.50 | |
| Mistral Large 3 675B Instruct | — | 128K | $0.500 | $1.50 | |
| Mistral Medium 3.1 | — | 131K | $0.400 | $2.00 | |
| Mistral Small 3.2 24B Instruct | — | 128K | $0.075 | $0.200 | |
| Mistral Medium 3 | — | 131K | $0.400 | $2.00 | |
| Mistral Small 3.2 | — | — | 131K | $0.060 | $0.180 |
| Mistral Small 3.1 | — | — | — | — | — |