# Devstral Small (25.05)

> The original Devstral — Mistral and All Hands AI's first open Apache-2.0 24B coding agent for solving real GitHub issues.

- Maker: Mistral AI
- Line: Devstral
- Canonical page: https://ai-tldr.dev/models/devstral-small-1/
- Updated: 2026-06-17

## In short

Devstral Small (25.05) is the original Devstral — Mistral and All Hands AI's first open Apache-2.0 24B coding agent for solving real GitHub issues. Mistral AI released it on 21 May 2025 as an open-weight model. It has a 128K-token context window and costs $0.10 per million input tokens and $0.30 per million output tokens. You can use it through Mistral AI.

## Facts

| Fact | Value | Source |
| --- | --- | --- |
| Context window | 128K | [1] |
| Input price | $0.10 / 1M tokens | [2] |
| Output price | $0.30 / 1M tokens | [2] |
| Licence | Apache 2.0 · open weights | [1] |
| Released | 21 May 2025 | [1] |
| Parameters | 24B | [1] |
| Knowledge cutoff | 2025 | [1] |

## Sources

1. [Devstral Small (2505) model card — Hugging Face](https://huggingface.co/mistralai/Devstral-Small-2505)
2. [Mistral — Devstral announcement](https://mistral.ai/news/devstral/)

## Overview

Devstral Small, released May 21, 2025, was the first model in Mistral AI's Devstral line — an agentic large language model for software engineering, built in collaboration with All Hands AI. It is a 24-billion-parameter open model under the Apache 2.0 license, designed to solve real GitHub issues rather than answer isolated coding prompts.

On SWE-Bench Verified, Devstral Small scores 46.8%, which Mistral reported as outperforming prior open-source state-of-the-art by about 6 points and, under the same OpenHands scaffold, exceeding far larger models such as DeepSeek-V3-0324 (671B) and Qwen3 235B-A22B. It uses a 128K-token context window and the Tekken tokenizer with a 131k-token vocabulary.

Devstral Small is fine-tuned from Mistral-Small-3.1-24B-Base-2503 and is text-only — the vision encoder was removed for coding-agent use. It is light enough to run on a single RTX 4090 or a 32GB Mac, and was distributed through the Mistral API (model ID devstral-small-2505), Hugging Face, Ollama, Kaggle, Unsloth, and LM Studio. It has since been superseded by the Devstral 1.1 and Devstral 2 generations.

## Benchmarks

- SWE-Bench Verified: 46.8% ([source](https://mistral.ai/news/devstral/))

## Pricing

- Input: $0.10 / 1M tokens per 1M tokens
- Output: $0.30 / 1M tokens per 1M tokens

Mistral API pricing as published in the May 2025 announcement; weights are also free under Apache 2.0.

Source: https://mistral.ai/news/devstral/

## Strengths

- First open Apache 2.0 Devstral coding agent — fully self-hostable
- Runs locally on a single RTX 4090 or a 32GB Mac
- Outperformed much larger open models on SWE-Bench Verified under the same OpenHands scaffold
- 128K-token context for repository-scale agentic tasks
- Widely distributed: Hugging Face, Ollama, Kaggle, Unsloth, LM Studio, and the Mistral API

## Best for

- Open, self-hosted coding agents for resolving GitHub issues
- Local, privacy-preserving software-engineering assistants on a single GPU
- Agentic code workflows inside OpenHands-style scaffolds
- Cost-efficient code generation through the Mistral API

## How to access

- [Mistral AI](https://mistral.ai/news/devstral/) — model id `devstral-small-2505`

## Devstral versions

- [Devstral 2 / Devstral Small 2](https://ai-tldr.dev/models/devstral-2/) (9 December 2025)
- [Devstral Medium & Small 1.1 (25.07)](https://ai-tldr.dev/models/devstral-medium-small-1-1/) (10 July 2025)
- Devstral Small (25.05) (21 May 2025) — this page

## FAQ

### What is Devstral Small (25.05)?

Devstral Small is Mistral AI's first Devstral model, released May 21, 2025 with All Hands AI. It is a 24B open Apache 2.0 agentic coding model designed to solve real GitHub issues, scoring 46.8% on SWE-Bench Verified with a 128K context window.

### Is Devstral Small open source and can it run locally?

Yes. It is released under Apache 2.0 with open weights on Hugging Face (model ID devstral-small-2505), fine-tuned from Mistral-Small-3.1-24B-Base-2503. It is light enough to run on a single RTX 4090 or a Mac with 32GB RAM and is also available via Ollama, Kaggle, Unsloth, and LM Studio.

### How did Devstral Small compare to larger models?

Mistral reported that, under the same OpenHands scaffold, Devstral Small's 46.8% SWE-Bench Verified score exceeded much larger open models such as DeepSeek-V3-0324 (671B) and Qwen3 235B-A22B, while outperforming the prior open-source state-of-the-art by about 6 points.

### Is Devstral Small still the current version?

No. Devstral Small (25.05) has been superseded by Devstral Small 1.1 (July 2025) and the December 2025 Devstral 2 family. Its Apache 2.0 weights remain available on Hugging Face for download and self-hosting.

## Links

- [Mistral — Devstral announcement](https://mistral.ai/news/devstral/)
- [Devstral Small (2505) model card — Hugging Face](https://huggingface.co/mistralai/Devstral-Small-2505)

Source: AI/TLDR LLM registry, https://ai-tldr.dev/models/devstral-small-1/