LogoTop AI Hubs

Mistral: Devstral Small

Other
Text
Paid

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.

Parameters

-

Context Window

128,000

tokens

Input Price

$0.06

per 1M tokens

Output Price

$0.12

per 1M tokens

Capabilities

Model capabilities and supported modalities

Performance

Reasoning

Good reasoning with solid logical foundations

Math

-

Coding

Specialized in code generation with excellent programming capabilities

Knowledge

-

Modalities

Input Modalities

text

Output Modalities

text

LLM Price Calculator

Calculate the cost of using this model

$0.000090
$0.000360
Input Cost:$0.000090
Output Cost:$0.000360
Total Cost:$0.000450
Estimated usage: 4,500 tokens

Monthly Cost Estimator

Based on different usage levels

Light Usage
$0.0018
~10 requests
Moderate Usage
$0.0180
~100 requests
Heavy Usage
$0.1800
~1000 requests
Enterprise
$1.8000
~10,000 requests
Note: Estimates based on current token count settings per request.
Last Updated: 1970/01/21