Mistral · synced 2026-08-11

mistral-medium

Input / 1M
$2.70
Output / 1M
$8.10
Cached input
Context
32K

A 1,000-token prompt costs $0.00270 to send. Token counts for Mistral models are estimated — approximated, because this family has no public tokenizer.

Pinned versions at the same rate: mistral-medium-2312

Priced closest to this

Model Provider Input Output
command-a-03-2025 Cohere $2.50 $10.00
command-r-plus Cohere $2.50 $10.00
command-r-plus-08-2024 Cohere $2.50 $10.00
gpt-4o OpenAI $2.50 $10.00
gpt-4o-audio-preview OpenAI $2.50 $10.00
gpt-4o-search-preview OpenAI $2.50 $10.00