Mistral: Devstral 2 2512

Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...

74.1% PinchBench§#93 Code Mode‡$0.40/1M input tokens†
‡Kilo Code Leaderboard†OpenRouter§PinchBench
Context Window
262,144 tokens
Input Modalities
textfile

Try Mistral: Devstral 2 2512 in Kilo Code

Experience this model with the most popular open source coding agent. Free to start, pay only for AI usage. Use in popular IDEs like VS Code, JetBrains, command line, or cloud agents.

3M+

Downloads

500+

models supported

Free

to Start

Get Started with Kilo

Access 500+ models including Mistral: Devstral 2 2512 and many more in Kilo Code

Benchmarking Mistral: Devstral 2 2512

PinchBench data · refreshed daily

OpenClaw Benchmarks

PinchBench measures how Mistral: Devstral 2 2512 performs on real OpenClaw agent tasks: multi-step execution, tool use, recovery, latency, and cost.

Try with KiloClaw PinchBench run
Best models for OpenClaw

Average score

74.1%

#30 of 50 official models

Average time

96m 12s

48 runs · per OpenClaw task

Average cost

$2.183

Per benchmark run

Category breakdown

Best verified PinchBench v2 run by OpenClaw task family.

Uncategorized87.6% · 8/11 cleared

Top task results

Highest-scoring benchmark tasks from the same submission.

Uncategorized
00 Sanity
100.0%
Uncategorized
01 Calendar
100.0%
Uncategorized
03 Blog
100.0%
Uncategorized
04 Weather
100.0%
Uncategorized
05 Summary
100.0%
Uncategorized
06 Events
100.0%

Autonomous task execution

Mistral: Devstral 2 2512 shows emerging average success across OpenClaw-style benchmark runs, useful for recurring research, browser, and file-based automations.

Tool use and recovery

PinchBench tasks stress multi-step planning, tool calls, and judge-verified completion rather than single prompt coding snippets.

Agent workflow fit

Its deliberate average runtime and premium run cost help set expectations for long-running KiloClaw agents and production workflows.

Agentic benchmarks from the PinchBench Leaderboard

Real-World Usage

Real-world usage statistics from the Kilo Code community

Weekly Token Usage

Mode Rankings (Last Week)

Where this model ranks for each built-in mode

Code

Write, modify, and refactor code

#93

Ask

Get answers and explanations

No data

Debug

Diagnose and fix software issues

No data

Orchestrator

Coordinate tasks across multiple modes

No data

Real-world metrics from the Kilo Code Leaderboard

Pricing

Cost per 1 million tokens

Input Tokens
$0.40
per 1M tokens
Output Tokens
$2.00
per 1M tokens

Example Cost

Analyzing a 10,000 line codebase (≈40k input tokens, 10k output tokens) costs approximately $0.0360

Coding Capabilities

Features and parameters relevant to coding tasks

Coding Features

Function Calling
Can call external functions/APIs
Tool Choice
Control over function selection
Structured Outputs
JSON schema validation
Reasoning Tokens
Extended thinking for complex problems

Pricing details from OpenRouter

Technical Details

Architecture and implementation specifications

Model ID
mistralai/devstral-2512
Created
December 9, 2025
Tokenizer
Mistral
Input Modalities
text, file
Context Window
262,144 tokens
Input Price
$0.40 per 1M tokens
Output Price
$2.00 per 1M tokens
Cache Read Price
$0.04 per 1M tokens
Content Moderation
Disabled

Ready to try Mistral: Devstral 2 2512?

Install Kilo Code and start using Mistral: Devstral 2 2512 for your coding projects today. Choose from 500+ AI models with complete freedom.

  1. 1.

    Install Kilo Code

    Get the extension from VS Code Marketplace, JetBrains Plugin Repository, or the CLI.

  2. 2.

    Open the model selector

    Click the model name in the Kilo Code chat panel to open the selector.

  3. 3.

    Choose your model

    Search or browse to find and select your preferred model.

  4. 4.

    Start coding

    Use Code, Ask, Debug, or Plan mode — the model is ready immediately.

Get Started with Kilo