# Mistral Large 4 API pricing

Frontier multimodal reasoning. Mistral Large 4 by Mistral, model id `mistral/mistral-large-4`. Text model, called on `POST /v1/chat/completions` through INFRO on a provider account you connect.

## List rate

- $0.70 per 1M input tokens, $2.10 per 1M output tokens, $0.07 per 1M cached input tokens.
- The vendor's own published rate, read on 2026-11-07 from https://docs.mistral.ai/inference/pricing. Your provider bills you at the rate on your own account; INFRO adds 0% to model spend.

## Providers that serve it

- OpenRouter: `mistral/mistral-large-4`

Source: https://infro.io/models/mistral/mistral-large-4
