Mistral Small 2
General language model Generally available Open WeightsMistral AI's 22B Apache 2.0 open-weights model designed for low-latency text generation, precise tool use, and efficient local deployment.
Overview
Mistral Small 2 (snapshot `mistral-small-2409`) is a 22-billion parameter language model released by Mistral AI in September 2024. Designed as an efficient, low-latency solution for routine enterprise workloads, Mistral Small 2 balances cost, speed, and reasoning performance.
The model offers a 128,000-token context window with up to 8,192 output tokens. It features enhanced function calling, JSON schema output parsing, code completion, and strong multilingual capabilities across European and Asian languages.
Released under the permissive Apache 2.0 open-source license, Mistral Small 2 can be self-hosted without commercial restriction. It is also available via Mistral AI's hosted API ($0.20 / 1M input tokens, $0.60 / 1M output tokens).
Technical Specifications
Context Window
128,000 tokens
Max Input Tokens
128,000
Max Output Tokens
8,192
Parameters
22.0B
Released
2024-09-12
Modalities
Text → Text (Both)
Capabilities
Text Generation
Code Generation
Function Calling
Use Cases
Content Creation
Customer Support
Languages
English (en)
Spanish (es)
French (fr)
German (de)
Access Routes
| Route | Type | Protocol | Region / Scope | Provider | Status |
|---|---|---|---|---|---|
| Mistral AI | Hosted API (Direct provider) | Mistral REST API | Global | Mistral AI | Available |
Identifiers
- mistral-small-2 Canonical identifier Default
- mistral-small-2409 Canonical identifier Default
- mistral-small-latest Canonical identifier Default