# Devstral 2 / Devstral Small 2

> Mistral's frontier open-weights coding-agent family — a 123B dense Devstral 2 and a laptop-friendly 24B Devstral Small 2.

- Maker: Mistral AI
- Line: Devstral
- Canonical page: https://ai-tldr.dev/models/devstral-2/
- Updated: 2026-06-18

## In short

Devstral 2 / Devstral Small 2 is Mistral's frontier open-weights coding-agent family — a 123B dense Devstral 2 and a laptop-friendly 24B Devstral Small 2. Mistral AI released it on 9 December 2025. It has a 256K-token context window. You can use it through Mistral AI and OpenRouter.

## Facts

| Fact | Value | Source |
| --- | --- | --- |
| Context window | 256K (max output 256K) | [1] |
| Input price | $0.40 / 1M tokens (Devstral 2); $0.10 / 1M tokens (Devstral Small 2) | [2] |
| Output price | $2.00 / 1M tokens (Devstral 2); $0.30 / 1M tokens (Devstral Small 2) | [2] |
| Licence | Devstral 2: Modified MIT; Devstral Small 2: Apache 2.0 · open weights | [1] |
| Released | 9 December 2025 | [3] |
| Parameters | Devstral 2: 123B; Devstral Small 2: 24B | [1] |
| Knowledge cutoff | 2025 | [1] |

## Sources

1. [Devstral 2 (123B) model card — Hugging Face](https://huggingface.co/mistralai/Devstral-2-123B-Instruct-2512)
2. [Mistral pricing](https://mistral.ai/pricing)
3. [Mistral — Introducing Devstral 2 and Mistral Vibe CLI](https://mistral.ai/news/devstral-2-vibe-cli/)

## Overview

Devstral 2 is Mistral AI's December 2025 coding-agent family, released on December 9, 2025 in two open-weights sizes: Devstral 2, a 123-billion-parameter dense model, and Devstral Small 2, a 24-billion-parameter model that runs on consumer hardware. Both are built for agentic software engineering — exploring codebases, editing across many files, and powering tool-using coding agents — and ship alongside the open-source Mistral Vibe CLI.

On SWE-Bench Verified, Devstral 2 scores 72.2% and Devstral Small 2 scores 68.0%, which Mistral positions among the strongest open-weights results, with Devstral Small 2 landing near models several times its size. Both models use a 256K-token context window and a dense Transformer architecture (the Hugging Face config reports model_type 'ministral3' with rope-scaling, with no expert-routing fields), so every token uses all parameters rather than a Mixture-of-Experts subset.

The two models differ on licensing. Devstral 2 (123B) ships under a Modified MIT license that withholds rights from companies whose global consolidated monthly revenue exceeds $20 million, while Devstral Small 2 (24B) is permissively licensed under Apache 2.0. Devstral Small 2 is fine-tuned from Mistral-Small-3.1-24B-Base-2503 and is distributed in FP8 with support for vLLM, SGLang, Transformers, Ollama, LM Studio, and llama.cpp.

## Benchmarks

- SWE-Bench Verified (Devstral 2, 123B): 72.2% ([source](https://mistral.ai/news/devstral-2-vibe-cli/))
- SWE-Bench Multilingual (Devstral 2, 123B): 61.3% ([source](https://huggingface.co/mistralai/Devstral-2-123B-Instruct-2512))
- Terminal Bench 2 (Devstral 2, 123B): 32.6% ([source](https://huggingface.co/mistralai/Devstral-2-123B-Instruct-2512))
- SWE-Bench Verified (Devstral Small 2, 24B): 68% ([source](https://mistral.ai/news/devstral-2-vibe-cli/))
- SWE-Bench Multilingual (Devstral Small 2, 24B): 55.7% ([source](https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512))
- Terminal Bench 2 (Devstral Small 2, 24B): 22.5% ([source](https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512))

## Pricing

- Input: $0.40 / 1M tokens (Devstral 2); $0.10 / 1M tokens (Devstral Small 2) per 1M tokens
- Output: $2.00 / 1M tokens (Devstral 2); $0.30 / 1M tokens (Devstral Small 2) per 1M tokens

Mistral API list prices; a free trial period was offered at launch.

Source: https://mistral.ai/pricing

## Strengths

- Frontier open-weights coding scores: 72.2% (Devstral 2) and 68.0% (Devstral Small 2) on SWE-Bench Verified
- Devstral Small 2 (24B) runs locally on consumer hardware while staying near far larger models
- Large 256K-token context for whole-repository and multi-file agentic edits
- Open weights on Hugging Face — Apache 2.0 for Small 2, Modified MIT for the 123B model
- Low API pricing and a free trial period via the Mistral API, plus the open-source Mistral Vibe CLI

## Best for

- Agentic software engineering: exploring codebases and editing multiple files
- Terminal-native coding agents via the Mistral Vibe CLI or OpenHands-style scaffolds
- Self-hosted, privacy-sensitive coding assistants (Devstral Small 2 on a single workstation)
- Cost-efficient code generation and refactoring through the Mistral API

## How to access

- [Mistral AI](https://docs.mistral.ai/models/model-cards/devstral-2-25-12) — model id `devstral-2-25-12`
- [Mistral AI](https://docs.mistral.ai/models/model-cards/devstral-small-2-25-12) — model id `devstral-small-2-25-12`
- [OpenRouter](https://openrouter.ai/mistralai/devstral-2512) — model id `mistralai/devstral-2512`

## Devstral versions

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

## FAQ

### What is the difference between Devstral 2 and Devstral Small 2?

Devstral 2 is the 123-billion-parameter flagship that scores 72.2% on SWE-Bench Verified and ships under a Modified MIT license. Devstral Small 2 is a 24-billion-parameter model scoring 68.0% on SWE-Bench Verified, runs on consumer hardware, and is released under the permissive Apache 2.0 license. Both share a 256K context window and a dense Transformer architecture.

### Is Devstral 2 open weights, and what does the Modified MIT license allow?

Yes, both models have open weights on Hugging Face. Devstral Small 2 is Apache 2.0. The 123B Devstral 2 uses a Modified MIT license that withholds rights from any company whose global consolidated monthly revenue exceeds $20 million for the preceding month, who must obtain a separate commercial license from Mistral.

### How much does Devstral 2 cost on the Mistral API?

Per Mistral's pricing page, Devstral 2 is $0.40 per million input tokens and $2.00 per million output tokens, while Devstral Small 2 is $0.10 per million input and $0.30 per million output. Mistral offered a free trial period at launch.

### Can Devstral Small 2 run locally?

Yes. Devstral Small 2 has 24B parameters, ships in FP8, and is supported by vLLM, SGLang, Transformers, Ollama, LM Studio, and llama.cpp, making it deployable on a single high-memory workstation for private, agentic coding.

## Links

- [Mistral — Introducing Devstral 2 and Mistral Vibe CLI](https://mistral.ai/news/devstral-2-vibe-cli/)
- [Devstral 2 (123B) model card — Hugging Face](https://huggingface.co/mistralai/Devstral-2-123B-Instruct-2512)
- [Devstral Small 2 (24B) model card — Hugging Face](https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512)
- [Devstral Small 2 — Mistral Docs](https://docs.mistral.ai/models/model-cards/devstral-small-2-25-12)
- [Mistral pricing](https://mistral.ai/pricing)
- [Devstral 2 on OpenRouter](https://openrouter.ai/mistralai/devstral-2512)
- [Simon Willison — Devstral 2 notes](https://simonwillison.net/2025/Dec/9/devstral-2/)
- [VentureBeat — Mistral launches Devstral 2](https://venturebeat.com/ai/mistral-launches-powerful-devstral-2-coding-model-including-open-source)

Source: AI/TLDR LLM registry, https://ai-tldr.dev/models/devstral-2/