Provider: Mistral AI

Mistral 3.1 Small Price

A nimble French model that fits on a single modern GPU but still codes and writes decently.

Current Pricing

Price per 1 million tokens

Input Tokens

$0.10

per 1M tokens you send

Output Tokens

$0.30

per 1M tokens you receive

Input tokens are what you send to the AI, output tokens are what the AI sends back. These rates are set by the provider and reflect the current Mistral AI Mistral 3.1 Small API pricing. Price accurate as of June 2025.

Quick Cost Calculator

Light Usage

~$0.04

per month

  • 100K input tokens
  • 100K output tokens
  • ~75 pages of text

Medium Usage

~$0.4

per month

  • 1M input tokens
  • 1M output tokens
  • ~750 pages of text

Heavy Usage

~$4

per month

  • 10M input tokens
  • 10M output tokens
  • ~7,500 pages of text

Description

128-token-head rotary-attention model (7-B dense + MoE adapters) aimed at on-device reasoning, fully RAG-ready out of the box.

Technical Details

Context window: 128000 tokens

The context window is the maximum amount of text the model can "see" at once. Larger windows allow for longer conversations or documents.

Ready to reduce your AI costs?

Join thousands of users who have switched to API.chat and are saving on their AI expenses while enjoying a better experience.