Cracked AI Engineering

Codestral vs Kimi K2 Instruct

Codestral offers 256K tokens context vs 131K tokens, Codestral is more cost-effective. Compare full specs, pricing, and choose the best model for your use case.

Quick Overview

Codestral

Vercel AI Gateway

256K tokens context • $0.30 / $0.90 per 1M tokens

View full specifications →

Kimi K2 Instruct

Vercel AI Gateway

131K tokens context • $1.00 / $3.00 per 1M tokens

View full specifications →

Detailed Comparison

Specification
Codestral
Kimi K2 Instruct
Provider
Vercel AI Gateway
Vercel AI Gateway
Context Window
256K tokens
131K tokens
Max Output Tokens
4K tokens
16K tokens
Input Pricing (per 1M tokens)
$0.30
$1.00
Output Pricing (per 1M tokens)
$0.90
$3.00
Release Date
May 2024
Jul 2025

Capabilities

Capability
Codestral
Kimi K2 Instruct
Text Generation
Function Calling

Which Model Should You Choose?

Choose Codestral if:

  • • You need a larger context window
  • • Cost efficiency is a priority

Choose Kimi K2 Instruct if: