Devstral 2 API
About
Process massive datasets with Devstral 2, featuring an expansive 262K context window for long-document analysis. This model delivers cost-effective pricing at $0.44/1M input and $2.20/1M output tokens, native tool calling support, open weights architecture. Access Devstral 2 via the OpenRouter API with up to 210K output tokens.
Capabilities
Input Modalities
textpdf
Output Modalities
text
Reasoning
No
Structured Output
Yes
Tool Use
Yes
WeightsOpen
Temperature
Adjustable
Attachment
Supported
Limits
Context Window
262K
Tokens
Input Limit
262K
Tokens
Max Output
210K
Tokens
Pricing
Standard (per 1M tokens)
Input
$0.44
Output
$2.20
Caching (per 1M tokens)
Read
$0.04
Frequently Asked Questions
Devstral 2 by OpenRouter costs $0.44 per 1M input tokens and $2.20 per 1M output tokens. Cached reads cost $0.04 per 1M tokens.
Model Details
ID
mistralai/devstral-2512
Provider
OpenRouterFamily
devstral
Release Date
Dec 9, 2025
Knowledge Cutoff
Dec 1, 2025
API Integration
NPM Package
@openrouter/ai-sdk-provider
Environment Variables
OPENROUTER_API_KEY
API Base URL
https://openrouter.ai/api/v1