---
title: "Mistral Small 4 API pricing: ⁨$0.15⁩ in, ⁨$0.60⁩ out · DotsAgent"
description: "Mistral Small 4 by Mistral AI: price per million input, cached and output tokens, context window, agent features and what a real agent task costs on it."
url: https://dotsagent.io/models/mistral-small-4
---

[Mistral AI](https://dotsagent.io/providers/mistral)

· Small and fast

# Mistral Small 4 API pricing and specs

An Apache-licensed mixture-of-experts model with 6.5B active parameters that switches between instruct and reasoning modes.

Input

$0.15

Cached input

—

Output

$0.60

US dollars per million tokens, standard tier, short-prompt rate

It replaces Mistral Small 3.2 and Magistral Small. Cached-input pricing is not published per model.

## Spec sheet

- **API model string**: `mistral-small-2603`
- **Provider**: [Mistral AI](https://dotsagent.io/providers/mistral)
- **Context**: 256K tokens
- **Max output**: —
- **Released**: March 16, 2026
- **Batch API**: 50% off, results within hours
- **Documented agent features**: Tool callingStructured outputAdjustable reasoning

## What a task costs

Four reference workloads priced at this model's list rates, with caching applied after the first call. Your numbers will differ; the calculator lets you change every assumption.

| Workload | Per task | Per 1,000 tasks |
| --- | --- | --- |
| Support bot 4 calls, short tool lookups | $0.006 | $6 |
| Coding agent 30 calls, files and test output | $0.526 | $526 |
| Browser agent 25 calls, screenshots and page text | $0.216 | $216 |
| Research agent 15 calls, long search results | $0.162 | $162 |

[Change the assumptions](https://dotsagent.io/cost#model=mistral-small-4)

## Other Mistral AI models

- [Mistral Medium 3.5](https://dotsagent.io/models/mistral-medium-3-5): $1.50 / $7.50

## Similar cost elsewhere

Models from other providers whose cost on the 30-step coding workload is closest to this one.

- [Gemini 3.8 Flash](https://dotsagent.io/models/gemini-3-8-flash): $0.742 per coding task

- [Qwen3.7-Plus](https://dotsagent.io/models/qwen3-7-plus): $0.343 per coding task

- [Gemini 3.5 Flash-Lite](https://dotsagent.io/models/gemini-3-5-flash-lite): $0.333 per coding task

- [DeepSeek-V4-Pro-0813](https://dotsagent.io/models/deepseek-v4-pro-0813): $0.961 per coding task

## Sources

1. [docs.mistral.ai](https://docs.mistral.ai/models/mistral-small-4-0-26-03)/models/mistral-small-4-0-26-03
2. [mistral.ai](https://mistral.ai/pricing/api/)/pricing/api/

Independent reference for people who build AI agents. Not affiliated with any vendor named here.

© 2026 DotsAgent · Facts checked October 1, 2026