Devstral Small 1.1

About Devstral Small 1.1

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.

Model Specifications

💰 Real-World Cost Examples

Estimated monthly costs for common use cases

Mistral Model Lineup

Compare all models from Mistral to find the best fit

Similar Models from Other Providers

Cross-brand alternatives with similar capabilities

ERNIE 4.5 21B A3B Thinking

Baidu

Input: $0.07

Output: $0.28

Context: 131k

ERNIE 4.5 21B A3B

Baidu

Input: $0.07

Output: $0.28

Context: 120k

Spotlight

Other

Input: $0.18

Output: $0.18

Context: 131k

Llama Guard 4 12B

Meta

Input: $0.18

Output: $0.18

Context: 1.0M

💡 Cheaper Alternatives

Same Brand (Mistral)

Cross Brand

🚀 Quick Start

Get started with Devstral Small 1.1 API

from openai import OpenAI

client = OpenAI(
    base_url="https://api.provider.com/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="mistralai/devstral-small-2507",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)

Continue Your Decision