Mistral Small 3.2 24B
Provider: Mistral AI EU Official API price
Overview
Mistral AI's 24B parameter mid-tier instruction model handles general tasks, supporting vision, function-calling, and JSON mode within a 32768 token context.
Strengths
- Input priced at $0.1/1M tokens
- Output priced at $0.3/1M tokens
- Cached input at $0.01/1M tokens
- Native vision and function-calling support
Best use cases
- Structured JSON extraction pipelines
- API tool integration workflows
- Multimodal document processing tasks
Pricing position
Input matches Llama 4 Scout at $0.1/1M, but output is double Mistral Small 3 ($0.08/1M) and higher than Qwen3.5-9B ($0.15/1M).
Caveats
Context window is limited to 32768 tokens, whereas peers like Ministral 3 8B offer 262144 tokens.
Notes drafted by an LLM from the figures on this page (2026-11-13) and rewritten when the price changes.
Key facts
- Price basis
- Official API price
- Max output
- 26K tokens
- Knowledge cutoff
- 2023-10-31
- Listed on OpenRouter
- 2025-06-20
- Tracked since
- 2026-05-08
- Last updated
- 2026-11-10
Features
Monthly cost estimate
| Scale | Input (M) | Output (M) | Monthly |
|---|---|---|---|
| 0.1M (hobby) | 0.1 | 0.05 | $0.03 |
| 1M (small app) | 1 | 0.5 | $0.25 |
| 10M (mid scale) | 10 | 5 | $2.50 |
| 100M (large) | 100 | 50 | $25.00 |
※ 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-3.2-24b-instruct)