prices synced 2026-07-28

Devstral 2 2512

Mistral · Multimodal · Released Dec 2025

Compare

A 123B dense transformer from Mistral designed for code generation and agentic workflows, with support for 256K token context.

Strengths
Handles complex coding tasks and can maintain context across large codebases and multi-step reasoning within its extended context window.
Best for
Agentic coding workflows, repository-scale code analysis, and tasks requiring extended reasoning over large code contexts.
Limitations
The large model size requires significant computational resources; not suitable for resource-constrained environments or latency-critical applications.

Input / 1M

$0.4

Output / 1M

$2.00

Cached input / 1M

$0.04

Context window

262K

Price history

Price per 1M tokens over timeOutput $2.00; Input $0.4 as of Jun 2026.$0$0.5$1.00$1.50$2.00Output on 11 Jun 2026: $2.00Out $2.00Input on 11 Jun 2026: $0.4In $0.4Jun 2026

Snapshots

Effective Input Output Cached in Note Source
11 Jun 2026 $0.4 $2.00 $0.04 Imported from OpenRouter openrouter.ai

More from Mistral

Report a problem