Devstral small 1.1
About this model
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.
Performance Tier
Devstral small 1.1 is a specialized model from Mistral : built for a specific domain.
Domain-specific model. Optimized for a particular task such as code generation, image creation, or web search.
Pricing
This model is included in Elosia plans| Type | per 1M tokens |
|---|---|
| Input (prompt) | $0.100 |
| Output (completion) | $0.300 |
| Cache read | $0.010 |
Capabilities
Benchmarks
Recommended Use Cases
Strengths
- Lightweight coding model for fast iteration
- Open-weight and suitable for edge deployment
- Good for inline code completion and small edits
Limitations
- Limited reasoning for complex architectural decisions
- Lower SWE-bench performance than larger alternatives
Resources
This model may use your data for training
