Codestral token cost

When to use Codestral

Code-focused Mistral model for completion and repo assistance. Estimate with real code prompts: token density differs from prose.

Pricing

Input

$1.00/1M

Output

$3.00/1M

Verified

2026-08-12

Official pricing source · Open main calculator · Cheaper long context models

Estimate with TokenCalculator

Preselect Codestral in the calculator to count tokens and project request or monthly cost. Exact vs Approx follows this model's tokenizer family. See the Exact vs Approx guide for honesty rules.

Estimate cost for Codestral · Count tokens · Pricing guide

Compare

• DeepSeek Coder vs Codestral
• Qwen2.5 Coder 32B (Together) vs Codestral
• Codestral vs GPT-4.1 Mini
• Ministral 8B
• Mistral Large (2407)
• Mistral Large 3
• Mistral Medium 3

All featured comparisons · More Mistral models

Related tools

Estimate API cost · Count tokens · Check context fit · Estimate cache savings · Compare batch pricing · Cheapest LLM API

Related guides

LLM API pricing · Exact vs Approx · How prompt cost is calculated · Prompt caching explained

Sources and references

Official documentation used for definitions, counting methods, or rate cards. Always confirm critical budgets on the provider page.

• Mistral official pricing