Cracked AI Engineering

Devstral Medium vs Kimi K2 Instruct 0905

Kimi K2 Instruct 0905 offers 262K tokens context vs 131K tokens. Compare full specs, pricing, and choose the best model for your use case.

Quick Overview

Devstral Medium

OpenRouter

131K tokens context • $0.40 / $2.00 per 1M tokens

View full specifications →

Kimi K2 Instruct 0905

OpenRouter

262K tokens context • $0.60 / $2.50 per 1M tokens

View full specifications →

Detailed Comparison

Specification
Devstral Medium
Kimi K2 Instruct 0905
Provider
OpenRouter
OpenRouter
Context Window
131K tokens
262K tokens
Max Output Tokens
131K tokens
16K tokens
Input Pricing (per 1M tokens)
$0.40
$0.60
Output Pricing (per 1M tokens)
$2.00
$2.50
Release Date
Jul 2025
Sep 2025

Capabilities

Capability
Devstral Medium
Kimi K2 Instruct 0905
Text Generation
Function Calling

Which Model Should You Choose?

Choose Devstral Medium if:

  • • Cost efficiency is a priority

Choose Kimi K2 Instruct 0905 if:

  • • You need a larger context window