---
title: "Mistral Small — LLM-TEST.com"
url: /models/mistral-small/
canonical_url: https://llm-test.com/models/mistral-small/
language: en
type: model
summary: "A compact, efficient open-weights model released under Apache-2.0, ideal for self-hosting and edge deployment. Delivers solid general capability at very low cost."
last_updated: "2026-11-05"
---

# Mistral Small

_Mistral AI · Budget · open weights_

A compact, efficient open-weights model released under Apache-2.0, ideal for self-hosting and edge deployment. Delivers solid general capability at very low cost.

## At a glance

- Released: Jul 22, 2026
- Provider: Mistral AI
- Context window: 128,000 tokens
- Max output: 32,000 tokens
- Modalities: Text + image → text
- Knowledge cutoff: April 2026
- API model ID: `mistral-small-latest`
- License: Apache-2.0

## Pricing

- Standard: $0.10 input / $0.30 output per 1M tokens (aggregator estimate)
- Example: a 1,500-token prompt + 650-token answer ≈ $0.0003 (standard)

## What's new vs Mistral Small 3 (October 2025)

- Better instruction following and efficiency than Small 3
- Shorter context and lower ceiling than Mistral Large

## Best use cases

- **Self-hosting** — Runs on modest hardware under a permissive Apache-2.0 license.
- **Edge and on-prem** — Powers local assistants where data cannot leave the premises.
- **High-volume tasks** — Handles classification and drafting cheaply at scale.

## Strengths

- Fully open weights
- Low cost and resource needs
- Permissive license

## Limitations

- Lower capability ceiling
- Smaller context window

## Where to get access

- Consumer app: Le Chat (web, mobile) — https://chat.mistral.ai
- API: La Plateforme (the Mistral console) — https://console.mistral.ai
- Also available: open weights on Hugging Face for several models
- Docs: https://docs.mistral.ai

Full comparison and live pricing: https://llm-test.com/ · directory: https://llm-test.com/models/