# Mistral: Mistral Small 4 (batch)

Provider: mistralai  
Category: llm  
Model ID: `mistralai/mistral-small-2603:batch`

Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...

## Specs

- Context length: 262144 tokens
- Max output: 209715 tokens
- Modalities: text, image
- Released: 2026-03-16

## Pricing

- Input: $0.07 per million tokens
- Output: $0.30 per million tokens

## Providers

- **mistralai** — ctx 262144, input $0.07/M, output $0.30/M

## Verdict

Mistral Small 4 is a cost-efficient workhorse for high-volume batch processing where speed matters less than price. At $0.07/Mtok input and $0.30/Mtok output, it undercuts most competitors by 60-80% while maintaining solid performance on routine tasks. The 262K context window handles long documents without chunking. Trade-off: batch-only means no real-time responses, and you'll see weaker reasoning on complex multi-step problems compared to larger Mistral models or Claude. Reach for this when you're processing thousands of documents overnight and need predictable costs more than cutting-edge accuracy.

---
Last verified: 2026-10-19T02:30:34.239Z  
Canonical URL: https://switchy.build/directory/models/mistral-small-2603-batch