Devstral Small
by Mistral AIChat
Devstral-Small-2505 is a 24B parameter agentic LLM fine-tuned from Mistral-Small-3.1, jointly developed by Mistral AI and All Hands AI for advanced software engineering tasks. It is optimized for codebase exploration, multi-file editing, and integration into coding agents, achieving state-of-the-art results on SWE-Bench Verified (46.8%).
- Context
- 256K tokens
- Max output
- 256,000 tokens
- Weights
- unknown
mistral/devstral-small · also seen as devstral-small-latest
Specifications
Full facts as recorded, incl. what is unknown.
- Released
- —
- Weights
- unknown
- Input
- Text
- Output
- Text
- Context window
- 256,000 max across endpoints
- Max output
- 256,000
- Providers
- 1 + 1 gateway, not counted as providers
- Epoch Capabilities Index
- not evaluated
- Direct price range
- $0.10 in · $0.30 out per 1M tokens · from its one provider
More details
- Last updated
- —
- Knowledge cutoff
Capabilities
Across all endpoints: supported if any endpoint supports it.
- Tool calling
- Parallel toolsunknown
- Structured output
- Reasoningunknown
- Image inputunknown
- PDF inputunknown
- Audio inputunknown
- Audio outputunknown
- Video inputunknown
- Prompt cachingunknown
- Web searchunknown
- Computer useunknown
- System messagesunknown
- Assistant prefill
- Temperatureunknown
- Streamingunknown
- Attachmentsunknown
Endpoints
One row per provider and variant; gateways are listed separately.
Loading endpoints…
Price history
No change since 19 Oct 2026. The cheapest direct price has been $0.10 in / $0.30 out per 1M tokens at Mistral on every data refresh since then.
Tracked from 19 Oct 2026. Headline-eligible direct prices only, so a price the sanity check flags never draws a spike. Series as JSON
Cost calculator
Loading endpoints…
Similarly priced models
Blended rate per 1M tokens, each at its own cheapest provider (10M input : 2M output mix).
| Model | Blended/1M | In/1M | Out/1M | Context | vs Devstral Small |
|---|---|---|---|---|---|
| Baidu Ernie 4.5 21B A3B ThinkingBaidu | $0.105 | $0.07 | $0.28 | 131K | +0% |
| Laguna S 2.1Poolside | $0.105 | $0.09 | $0.18 | 1.05M | −0% cheaper |
| Nex-N2.5-ProNex AGI | $0.104 | $0.075 | $0.25 | 262K | −1% cheaper |
| The Drummer Cydonia 24B v2TheDrummer | $0.104 | $0.10 | $0.121 | 32.8K | −1% cheaper |
| The Drummer Magidonia 24B v4.3TheDrummer | $0.104 | $0.10 | $0.121 | 32.8K | −1% cheaper |
| Qwen3 14BAlibaba (Qwen) | $0.107 | $0.08 | $0.24 | 131K | +2% |
| Llama-4-Scout-17B-16E-Instruct-FP8Meta | $0.107 | $0.08 | $0.24 | 192K | +2% |
| Seed 1.6 Flash (250715)ByteDance Seed | $0.108 | $0.07 | $0.30 | 256K | +3% |
More from Mistral AI
Newest Mistral AI models in the catalogue. All Mistral AI models
| Model | Released | Context | Listed price |
|---|---|---|---|
| Mistral Large 4 | 2026-10-06 | 1.05M | from $0.68 |
| Voxtral Small 24B 2507 STT | 2026-08-13 | — | unpriced |
| Leanstral 1.5 | 2026-06-30 | 262K | unpriced |
| Mistral Code Latest | 2026-06-02 | 128K | from $0.30 |
| Mistral Code Agent Latest | 2026-06-02 | 256K | from $0.40 |
| Voxtral Mini Transcribe | 2026-05-15 | 16.4K | unpriced |
| Mistral Medium 3.5 | 2026-04-30 | 262K | from $1.50 |
| Mistral Medium 3.5 | 2026-04-29 | 262K | from $1.50 |