Codestral 25.08

Active

Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. [Blog Post](https://mistral.ai/news/codestral-25-08)

View current API pricing for this model

Input, output, and cached rates with source and verification time, plus same-workload cost examples.

Go to pricing page →

Input / 1M tokens

$0.30

Output / 1M tokens

$0.90

Record updated 2026-10-11

Modality:LLM

Context:256,000 tokens

Release:Jul 30, 2025

📊 Price Matrix 🧮 Spend Calculator 📢 Changes Model pricing page Vendor API pricing Check stack cost impact

Pricing

Platform

Scope

Input

Output

Details

Official

Standard

$0.30

$0.90

256k context · 8k max output

OpenRouter

Unified API Router

Standard

$0.30

$0.90

256k context · 205k max output

How much are you overpaying?

Enter your monthly spend on this model to see what the same workload could cost on cheaper alternatives.

Monthly spend on Codestral 25.08

Enter a monthly spend to see the listed-rate comparison.

Alternative models

Directional candidates based on stored listed rates and editorial scenario tags; validate quality and current terms before switching

Candidates with lower listed rates

Mistral NemoMistral

Significant cost savings

$0.02 / $0.03

Stored listed rate / 1M tokens

Listed average about 96% lower

Mistral Nemoopenrouter

Significant cost savings

$0.03 / $0.03

Stored listed rate / 1M tokens

Listed average about 95% lower

Llama Prompt Guard 2 22MGroq

Significant cost savings

$0.03 / $0.03

Stored listed rate / 1M tokens

Listed average about 95% lower

Qwen3-ASR FlashQwen

Significant cost savings

$0.04 / $0.04

Stored listed rate / 1M tokens

Listed average about 94% lower

Voxtral Mini 3B 2507AWS Bedrock

Significant cost savings

$0.04 / $0.04

Stored listed rate / 1M tokens

Listed average about 93% lower

Latest changes

No recent changes.

Benchmarks

No benchmark data available.

⚡Codestral 25.08 Comparisons & Scenario Guides

Popular Price & Spec Comparisons

vs Claude Sonnet 5 vs DeepSeek V4 Pro vs Gemini 3.7 Flash

Related Scenario Rankings

Coding Leaderboard Reasoning Leaderboard Budget Picks Mistral Pricing

❓Codestral 25.08 Frequently Asked Questions

How much does Codestral 25.08 cost per 1M tokens?▼

Codestral 25.08 is priced at $0.30 per 1M input tokens and $0.90 per 1M output tokens, with cached input at $0.03/1M on official. Check provider terms before deployment.

What is the context window for Codestral 25.08?▼

Codestral 25.08 supports up to 256,000 tokens context with a max completion limit of 8,192 tokens.

What are cost-saving alternatives to Codestral 25.08?▼

ModelPriceLab automatically calculates cheaper alternatives in the same model class, showing monthly spend differences and migration guides.

AI Cost Optimization

Does this change your best option?

Check your models and usage for free. See the relevant official changes, estimated cost, and a practical next step.

Check my models Apply for founder pilot