# Devstral Small Usage, Cost & Rank | OpenCode Data

Mistral coding agent model for repository tasks and software engineering workflows

- Page: https://opencode.ai/data/mistral/devstral-small-2507
- JSON: https://opencode.ai/data/mistral/devstral-small-2507.json
- Model ID: mistral/devstral-small-2507
- Lab: Mistral

## Model facts

| Fact | Value |
| --- | --- |
| Context window | 128K |
| Max output | 128K |
| Knowledge cutoff | 2025-05 |
| Release date | 2025-07-10 |
| Input modalities | text |
| Output modalities | text |
| Reasoning | No |
| Tool calling | Yes |
| Open weights | Yes |
| Weights | [Hugging Face](https://huggingface.co/mistralai/Devstral-Small-2507) |

## Benchmarks

| Benchmark | Score | Metric | Source |
| --- | --- | --- | --- |
| SWE-Bench Verified | 53.6 | resolved | https://mistral.ai/news/devstral-2507 |

## Methodology

- Updates: Aggregated every hour. Days and weeks use UTC.
- Tokens: Input, output, reasoning, and cached tokens for each request.
- Users and sessions: Approximate counts of distinct users and OpenCode sessions.
- Cost: Session cost is the average cost per OpenCode session. Token prices are list prices from the OpenCode model catalog.
- Retention: The share of a model's users in one week who use it again the next week.
- Citation: Cite OpenCode Data (opencode.ai/data) with the update time shown at the top of the page.