# Mistral Small 3.2 24B Instruct

> Mistral Small 3.2 24B Instruct is an open-weight 24B instruction model under Apache 2.0, with a 131k context window. It improves instruction following and function calling over Mistral Small 3.1 and takes text and image input.

**ID**: `mistralai/mistral-small-3.2-24b-instruct`  
**Creator**: Mistral AI  
**Category**: text  
**Context**: 131K tokens  
**Pricing**: $0.07 / $0.20 per 1M · billed by your provider (BYOK)  
**Released**: 2025-06-19  
**Links**: [Weights on Hugging Face](https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506) · [Announcement](https://docs.mistral.ai/models/mistral-small-3-2-25-06) · [AnyRouter release](https://anyrouter.dev/blog/releases/2026-09-27)  
**Web page**: https://anyrouter.dev/model/mistralai/mistral-small-3.2-24b-instruct

**Input modalities**: text, image  
**Output modalities**: text  

**Tokenizer**: Mistral

**Capabilities**: chat, streaming, function-calling

**Aliases**: `mistralai/mistral-small-3.2-24b-instruct-2506`

## Usage

**Endpoint**: `POST https://anyrouter.dev/api/v1/chat/completions`

```bash
curl https://anyrouter.dev/api/v1/chat/completions \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "mistralai/mistral-small-3.2-24b-instruct",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'
```

## Providers

| Provider | Input | Output |
| --- | --- | --- |
| ovhcloud-byok | $0.10/M (list) | $0.31/M (list) |
| openrouter-byok | $0.07/M (list) | $0.20/M (list) |
| venice-byok | $0.09/M (list) | $0.25/M (list) |
| nousresearch-byok | $0.10/M (list) | $0.30/M (list) |
| aimlapi-byok | $0.08/M (list) | $0.21/M (list) |
| nano-gpt-byok | $0.07/M (list) | $0.20/M (list) |
| fluence-byok | $0.08/M (list) | $0.22/M (list) |
| cortecs-byok | $0.07/M (list) | $0.20/M (list) |

BYOK routes are billed by your own provider key — AnyRouter charges $0. Rates marked (list) are the provider's published list price.

## Model card

- Total parameters: 24B [3]
- Native context: 131072 tokens [2,3]
- License: Apache-2.0, open weights (https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506) [1]

### Strengths [1]

- Fewer infinite or repetitive generations than 3.1
- More robust function-calling template
- Image input

### Use cases [1]

- Function and tool calling
- Image understanding
- Instruction following

### Links

- announcement: https://docs.mistral.ai/models/mistral-small-3-2-25-06
- model card: https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506
- Previous version: https://anyrouter.dev/model/mistralai/mistral-small-3.1-24b-instruct

### Sources

1. [Mistral-Small-3.2-24B-Instruct-2506 model card](https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506/raw/main/README.md) (accessed 2026-10-14)
2. [Mistral-Small-3.2 config.json](https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506/raw/main/config.json) (accessed 2026-10-14)
3. [Mistral-Small-3.1-24B-Instruct-2503 model card](https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503/raw/main/README.md) (accessed 2026-10-14)

## Source

- Upstream docs: https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506
