Devstral Small 1.1 is a 24B parameter open-weight language model for software engineering agents, developed by Mistral AI in collaboration with All Hands AI. Finetuned from Mistral Small 3.1 and released under the Apache 2.0 license, it features a 128k token context window and supports both Mistral-style function calling and XML output formats. Designed for agentic coding workflows, Devstral Small 1.1 is optimized for tasks such as codebase exploration, multi-file edits, and integration into autonomous development agents like OpenHands and Cline. It achieves 53.6% on SWE-Bench Verified, surpassing all other open models on this benchmark, while remaining lightweight enough to run on a single 4090 GPU or Apple silicon machine. The model uses a Tekken tokenizer with a 131k vocabulary and is deployable via vLLM, Transformers, Ollama, LM Studio, and other OpenAI-compatible runtimes.
Devstral small 1.1 est un modèle spécialisé de Mistral : conçu pour un domaine précis.
Modèle spécialisé. Optimisé pour une tâche spécifique comme la génération de code, la création d'images ou la recherche web.
| Type | par 1M tokens |
|---|---|
| Entrée (prompt) | $0.100 |
| Sortie (complétion) | $0.300 |
| Lecture cache | $0.010 |
Ce modèle peut utiliser vos données pour l'entraînement