← All models
M
Mistral Large 3
Mistral
Frontier-level MoE model (675B total / 41B active params) at competitive price
Input price$0.50 / 1M tokens
Output price$1.50 / 1M tokens
Context window256k tokens
Last updated2026-04-20
Quick calculator
Per request
$0.001250
Daily
$12.50
Monthly
$375.00
per month · 30-day estimate
Yearly
$4,562.50
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