Mistral · legacy

Magistral Medium API pricing

Mistral model for multilingual reasoning.

Input / million
$2.00
Cached input / million
$0.2000
Output / million
$5.00
Context window
128,000

Example cost

A request with 10,000 input tokens and 2,000 output tokens costs approximately $0.0300 at the recorded standard rate.

  • 10,000 standard input tokens / 1,000,000 × $2
  • 0 cached tokens / 1,000,000 × $0.2
  • 2,000 output tokens / 1,000,000 × $5

Pricing rules and limitations

Official API list price; eligible batch processing is 50% lower and eligible cached input is 90% lower.

Price history

EffectiveUntilInputOutputStatus
2026-03-01Current / scheduled$2.00$5.00legacy