← All models
M

Magistral Medium

Mistral

Mistral's reasoning model — strong for complex analytical and math tasks

Input price$2.00 / 1M tokens
Output price$5.00 / 1M tokens
Context window128k tokens
Last updated2026-04-20

Quick calculator

tokens
tokens
req/day
Per request
$0.004500
Daily
$45.00
Monthly
$1,350.00
per month · 30-day estimate
Yearly
$16,425.00

Tips to reduce cost

  • Use prompt caching to reuse repeated system prompts
  • Trim whitespace and reduce verbose instructions
  • Use a smaller model for classification or routing tasks
  • Batch async requests to get 50% discount (OpenAI/Anthropic)
  • Cache identical requests at the application layer

Similar models from Mistral

Compared at your current token settings