Mistral Small 4

Provider: Mistral AI EU Official API price

Input price
$0.15
/ 1M tokens
Output price
$0.60
/ 1M tokens
Cache price
$0.015
/ 1M tokens (read)
Context
262K tokens
Max output 210K tokens

Overview

Mistral Small 4, from EU provider Mistral AI, is positioned as a high-tier reasoning specialist model. It targets complex workloads requiring extensive context processing, multimodal input, and advanced analytical capabilities.

Strengths

  • Boasts an extensive 262,144 token context window for processing very large inputs.
  • Offers advanced capabilities including vision, function-calling, JSON mode, and robust reasoning.
  • Supports multimodal applications with integrated vision capabilities for diverse use cases.
  • Features a low cache read price of $0.015/1M tokens, beneficial for recurrent queries.
  • Equipped with robust "thinking" capability for complex problem-solving and detailed analysis.

Best use cases

  • Deep analysis of lengthy documents, legal texts, or extensive codebases.
  • Automated processing and understanding of visual information and diagrams.
  • Building sophisticated AI agents capable of interacting with external tools via function-calling.
  • Extracting structured data and generating JSON outputs from unstructured text.
  • Complex problem-solving and strategic decision-making requiring advanced reasoning.

Pricing position

At $0.15/1M input and $0.6/1M output, Mistral Small 4 is the most premium offering among listed Mistral models. It is competitively priced, matching Llama 4 Maverick and GPT-4o-mini, while offering more favorable output pricing than MiniMax M2.5, Qwen3 235B, and Qwen3.6 35B.

Caveats

This model does not offer a free tier, meaning all usage will incur costs from the outset. For simpler tasks or those not requiring its extensive capabilities, a more cost-effective Mistral sibling might be a better choice. The maximum output token limit is currently unknown, which could be a consideration for applications requiring very long generative responses.

Notes drafted by an LLM from the figures on this page (2026-05-21) and rewritten when the price changes.

Key facts

Price basis
Official API price
Max output
210K tokens
Listed on OpenRouter
2026-03-16
Tracked since
2026-05-08
Last updated
2026-11-10

Features

Image inputFunction callingJSON outputReasoning

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.04
1M (small app) 1 0.5 $0.45
10M (mid scale) 10 5 $4.50
100M (large) 100 50 $45.00

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from Mistral AI

Similar-priced models

Source: OpenRouter API (mistralai/mistral-small-2603)