Devstral Small 2505

About Devstral Small 2505

Devstral-Small-2505 is a 24B parameter agentic LLM fine-tuned from Mistral-Small-3.1, jointly developed by Mistral AI and All Hands AI for advanced software engineering tasks. It is optimized for codebase exploration, multi-file editing, and integration into coding agents, achieving state-of-the-art results on SWE-Bench Verified (46.8%). Devstral supports a 128k context window and uses a custom Tekken tokenizer. It is text-only, with the vision encoder removed, and is suitable for local deployment on high-end consumer hardware (e.g., RTX 4090, 32GB RAM Macs). Devstral is best used in agentic workflows via the OpenHands scaffold and is compatible with inference frameworks like vLLM, Transformers, and Ollama. It is released under the Apache 2.0 license.

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

Gemma 3n 4B

Google

Input: $0.06

Output: $0.12

Context: 33k

Laguna XS 2.1

Poolside

Input: $0.06

Output: $0.12

Context: 262k

Nova Micro 1.0

Amazon

Input: $0.04

Output: $0.14

Context: 128k

GLM 4.1V 9B Thinking

Zhipu Ai

Input: $0.04

Output: $0.14

Context: 66k

💡 Cheaper Alternatives

Same Brand (Mistral)

Cross Brand

🚀 Quick Start

Get started with Devstral Small 2505 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-2505",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)

Continue Your Decision