Skip to main content
OpenRouter logo

Mistral Large 4 Preview API pricing on OpenRouter

Every OpenRouter Mistral Large 4 Preview rate we track, compared against 5 providers serving the same model.

Input from /1M
$0.700
Output /1M
$2.10
Input price rank
#2 of 5
Last updated
November 21, 2026

The cheapest Mistral Large 4 Preview input price we currently track is $0.679/1M on Liquid Inference.

The cheapest Mistral Large 4 Preview output price is $2.09/1M on Liquid Inference.

OpenRouter Mistral Large 4 Preview rates

Prices per 1M tokens. Batch and cached-input rates are shown where the provider publishes them.

OpenRouter Mistral Large 4 Preview pricing by mode
ModeInputOutput
Standard$0.700/1M$2.10/1M

About Mistral Large 4 Preview

Creator
Mistral
Modalities
text
Full Mistral Large 4 Preview details and every provider →Compare API pricing for every Mistral model →

Mistral Large 4 Preview on other providers

About OpenRouter

OpenRouter provides a unified API for accessing hundreds of AI models from multiple providers. It aggregates models from OpenAI, Anthropic, Google, Meta, Mistral, and many others, offering a single endpoint with automatic fallback routing and provider optimization.

Frequently Asked Questions

How much does Mistral Large 4 Preview cost on OpenRouter?

OpenRouter serves Mistral Large 4 Preview from $0.700 per 1M input tokens, across 1 tracked pricing mode. Prices are collected daily — see the table above for current input, output, and cached-input rates.

Is OpenRouter the cheapest way to run Mistral Large 4 Preview?

OpenRouter ranks #2 of 5 providers we track serving Mistral Large 4 Preview on input price. The cheapest input price right now is on Liquid Inference. The lowest output price is $2.09/1M on Liquid Inference. Rates change often, and throughput, latency and context limits differ between providers — check the comparison above before committing.

Does OpenRouter offer batch or cached pricing for Mistral Large 4 Preview?

We track 1 Mistral Large 4 Preview offering from OpenRouter. Batch and cached-input rates appear in the table above when the provider publishes them; blank cells mean we have no current figure for that mode.