Mistral Launches Devstral 2, Small 2 and Vibe CLI for Coding

Mistral unveiled Devstral 2 (123B) and Devstral Small 2 (24B) — both with 256K token context windows and optimized for multi-file production code workflows. It also launched Vibe CLI, an open-source terminal agent for repo-aware coding and orchestration.

mistral cover

TL;DR

  • **Devstral 2 (123B, modified MIT)** and **Devstral Small 2 (24B, Apache 2.0)** released for on‑prem deployment and fine‑tuning; both support a **256K token context window**.
  • SWE-bench Verified: Devstral 2 72.2%, Devstral Small 2 68.0%; human eval: Devstral 2 42.8% win rate vs DeepSeek V3.2 (28.6% loss); up to 7× cost efficiency vs Claude Sonnet on real tasks.
  • Models are compact vs competitors (Devstral 2/Small 2 ≈ 5×/28× smaller than DeepSeek V3.2; 8×/41× smaller than Kimi K2). Deployment: Devstral 2 recommended on ≥4 H100-class GPUs; Devstral Small 2 runs single-GPU, consumer GPUs, and CPU-only (NVIDIA NIM planned).
  • Designed for multi-file, production workflows: repo-wide reasoning, dependency tracking, cross-file edits, retries/corrections, fine‑tuning for language or enterprise codebases; Small 2 adds image inputs for multimodal agents and local private inference.
  • **Mistral Vibe CLI**: open-source Apache-licensed terminal agent powered by Devstral; project-aware context, multi-file orchestration, file autocomplete, shell execution, slash commands, persistent history, programmatic use, and config via config.toml. Zed extension: https://zed.dev/extensions · README: https://github.com/mistralai/mistral-vibe/blob/main/README.md
  • Availability and pricing: currently free via Mistral API; post-free pricing for Devstral 2 $0.40/$2.00 per million tokens (input/output), Devstral Small 2 $0.10/$0.30; partnerships with Kilo Code and Cline; community on X, Discord, and GitHub.

Mistral releases Devstral 2 and Devstral Small 2, plus the Vibe CLI

Mistral has published a new pair of coding models and an open-source terminal agent intended for production code workflows. The lineup includes **Devstral 2 (123B parameters, modified MIT license)** and **Devstral Small 2 (24B parameters, Apache 2.0)**, both supporting a **256K token context window** and designed for on-prem deployment and fine-tuning.

Models and performance

Devstral 2 is positioned as an open-weight model optimized for code agents, achieving **72.2% on SWE-bench Verified**. Devstral Small 2 posts **68.0% on SWE-bench Verified** while remaining compact enough to run on consumer hardware. Mistral reports that both models are substantially smaller than several competitors—Devstral 2 and Small 2 are respectively 5x and 28x smaller than DeepSeek V3.2, and 8x and 41x smaller than Kimi K2—emphasizing model compactness alongside performance.

In human evaluations conducted through an independent annotation provider, Devstral 2 demonstrated a **42.8% win rate** against DeepSeek V3.2 (with a 28.6% loss rate), while still lagging behind Claude Sonnet 4.5 in preference. The announcement also cites **up to 7× better cost efficiency** than Claude Sonnet on real-world tasks.

Built for multi-file, production workflows

The models are described as capable of exploring entire codebases and orchestrating changes across multiple files, tracking dependencies, detecting failures, and retrying with corrections. Fine-tuning options exist to emphasize particular languages or adapt to large enterprise codebases. Devstral Small 2 additionally supports image inputs for multimodal agents and is suitable for locally deployed, private inference.

Mistral Vibe CLI — terminal-native agent

Mistral Vibe CLI is an open-source, Apache-licensed command-line coding assistant powered by Devstral. It integrates into the terminal or an IDE via the Agent Communication Protocol and provides tools for file manipulation, code search, version control, and command execution. Key capabilities include:

  • **Project-aware context** that scans file structure and Git status
  • **Multi-file orchestration** for architecture-level reasoning across a repository
  • Smart in-terminal references and commands (file autocomplete, shell execution, slash commands)
  • Persistent history, autocompletion, and configurable themes

Vibe CLI can run programmatically, supports toggling auto-approval for tool execution, and allows configuration of local models and providers through a config.toml. The Vibe CLI extension is available for Zed: https://zed.dev/extensions. Best-practice guidance is linked in the project README: https://github.com/mistralai/mistral-vibe/blob/main/README.md.

Availability, pricing, and deployment

Devstral 2 is currently free to use via Mistral’s API at https://console.mistral.ai/. After the free period, pricing will be **$0.40/$2.00 per million tokens (input/output) for Devstral 2** and **$0.10/$0.30 for Devstral Small 2**.

Deployment guidance:

  • **Devstral 2**: optimized for data-center GPUs; minimum **4 H100-class GPUs** recommended. Try it on http://build.nvidia.com.
  • **Devstral Small 2**: designed for single-GPU operation and runs across NVIDIA systems and consumer GPUs; also supports CPU-only configurations. NVIDIA NIM support is planned.

Mistral notes partnerships with agent tool providers Kilo Code (https://kilo.ai/) and Cline (https://cline.bot/) to integrate Devstral into existing toolchains.

Community and hiring

Community touchpoints and contribution channels include X/Twitter (https://x.com/mistralai), Discord (https://discord.com/invite/mistralai), and GitHub (https://github.com/mistralai). Open positions and career information are on the Mistral careers page: https://mistral.ai/careers.

Original source: https://mistral.ai/news/devstral-2-vibe-cli

Continue the conversation on Slack

Did this article spark your interest? Join our community of experts and enthusiasts to dive deeper, ask questions, and share your ideas.

Join our community