Devstral Small (free) Check detailed information and pricing for AI models

Context Length 131,072 tokens, mistralai from provided

131,072
Context Tokens
Free
Prompt Price
Free
Output Price
10/16
Feature Support
Efficiency #7

Model Overview

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.

Basic Information

Developer
mistralai
Model Series
Other
Release Date
2025-05-21
Context Length
131,072 tokens
Variant
free

Pricing Information

This model is free to use

Data Policy

Terms of Service

학습 정책

1

Supported Features

Supported (10)

Top K
Seed
Frequency Penalty
Presence Penalty
Repetition Penalty
Min P
Logit Bias
Tool Usage
Logprobs
Top Logprobs

Unsupported (6)

Image Input
Response Format
Structured Outputs
Reasoning
Web Search Options
Top A

Other Variants

Actual Usage Statistics

#53
Out of 346 total models
17.0B
Total Tokens Last 30 Days
608.79M
Daily Average Usage
18%
Weekly Usage Change

Usage Trend for the Last 30 Days

Models by Same Author (mistralai)

Magistral Small 2506
40,000 tokens
$0.50 / $1.50
Magistral Medium 2506
40,960 tokens
$2.00 / $5.00
Magistral Medium 2506 (thinking)
40,960 tokens
$2.00 / $5.00
Mistral Medium 3
32,768 tokens
$0.40 / $2.00
Mistral Small 3.1 24B (free)
96,000 tokens
Free