# Mistral Small 24B
**Summary:** Mistral Small 24B is a versatile medium-sized, high-performance multilingual and multimodal model from Mistral, designed for conversational agents and virtual assistants. It supports a wide range of European languages, is optimized for both speed and quality, and can process both text and image input. Images can be provided as URLs or base64-encoded strings, allowing the model to analyze and respond to visual content in addition to text. This model is particularly effective for applications requiring fast and reliable chat completions, making it suitable for real-time interactions in various domains. The model supports advanced capabilities like streaming and tool calling, enhancing its usability in interactive applications.
| **Intelligence** | **Speed** | **Sovereignty** | **Input** | **Output** |
| :-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
|   |   |   |    |    |
| *Moderate* | *High* | *Moderate* | *Text, Image* | *Text* |
## Central parameters
**Description:** Medium-sized model with 24B parameters featuring a 128k token context window. Images are processed as input tokens, so including images in your requests will increase the total input token count. Token billing is based on the total number of tokens processed, including both input and output tokens.
**Model identifier:** `mistralai/Mistral-Small-24B-Instruct`
## IONOS AI Model Hub Lifecycle and Alternatives
| **IONOS Launch** | **End of Life** | **Alternative** | **Successor** |
| :--------------: | :-------------: | :------------------------------------------------------------------------------------------------------------------------------------------------: | :-----------: |
| *August 1, 2025* | N/A | [**Llama 3.3 (70B)**](https://docs.ionos.com/sections-test/guides/ai/ai-model-hub/models/llms/meta-llama-3-3-70b) | |
## Origin
| **Provider** | **Country** | **License** | **Flavor** | **Release** |
| :--------------------------------------------------------------------: | :---------: | :----------------------------------------------------------------------------------------------: | :--------: | :-------------: |
| [**Mistral AI**](https://mistral.ai/) | France | [**License**](https://www.apache.org/licenses/LICENSE-2.0.html) | Instruct | *June 25, 2025* |
## Technology
| **Context window** | **Parameters** | **Quantization** | **Multilingual** | **Further details** |
| :----------------: | :------------: | :--------------: | :--------------: | :-----------------------------------------------------------------------------------------------------------------------: |
| *128k* | *24B* | *fp8* | *Yes* | [**Hugging Face**](https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506) |
## Modalities
| **Text** | **Image** | **Audio** |
| :--------------: | :-------: | :-----------: |
| Input and output | Input | Not supported |
## Endpoints
| **Chat Completions** | **Embeddings** | **Image generation** |
| :------------------: | :------------: | :------------------: |
| v1/chat/completions | Not supported | Not supported |
### Vision Model Example
```json
{
"model": "mistralai/Mistral-Small-24B-Instruct",
"messages": [
{
"role": "user",
"content": [
{
"type": "text",
"text": "What do you see in this image?"
},
{
"type": "image_url",
"image_url": {
"url": "https://www.ionos.com/favicon.ico?v2",
"detail": "auto"
}
}
]
}
],
"temperature": 0.7,
"max_tokens": 1000
}
```
### Base64 image example
When providing a base64 encoded image, use the `image_url` type and map the `url` field to your data URI. Example: `data:image/jpeg;base64,...`
```json
{
"model": "mistralai/Mistral-Small-24B-Instruct",
"messages": [
{
"role": "user",
"content": [
{
"type": "text",
"text": "What's in this image?"
},
{
"type": "image_url",
"image_url": {
"url": "data:image/vnd.microsoft.icon;base64,AAABAAcAEBAQAAEABAAoAQAAdgAAABgYEAABAAQA6AEAAJ4BAAAgIBAAAQAEAOgCAACGAwAAMDAQAAEABABoBgAAbgYAAEBAEAABAAQAaAoAANYMAABISBAAAQAEAOgNAAA+FwAAYGAQAAEABADoFgAAJiUAACgAAAAQAAAAIAAAAAEAB...AAAAAAAAAAAAAAAAAAAAAA="
}
}
]
}
],
"temperature": 0.7,
"max_tokens": 1000
}
```
**Response:**
```json
{
"id": "chatcmpl-20dce5f1-5556-4c1e-ae47-7a497a376746",
"object": "chat.completion",
"created": 1769429443,
"model": "mistralai/Mistral-Small-24B-Instruct",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "The image displays a single, thin, vertical white line against a solid dark blue background. The line appears to be positioned towards the left side of the image. The overall design is minimalistic and abstract, with a focus on the contrast between the white line and the dark background.",
"refusal": null,
"annotations": null,
"audio": null,
"function_call": null,
"tool_calls": [],
"reasoning": null,
"reasoning_content": null
},
"logprobs": null,
"finish_reason": "stop",
"stop_reason": null,
"token_ids": null
}
],
"service_tier": null,
"system_fingerprint": null,
"usage": {
"prompt_tokens": 29,
"total_tokens": 86,
"completion_tokens": 57,
"prompt_tokens_details": null
},
"prompt_logprobs": null,
"prompt_token_ids": null,
"kv_transfer_params": null
}
```
## Features
| **Streaming** | **Reasoning** | **Tool calling** |
| :-----------: | :-----------: | :--------------: |
| Supported | Not supported | Supported |
## Rate limits
Rate limits ensure fair usage and reliable access to the AI Model Hub. In addition to the [contract-wide rate limits](https://docs.ionos.com/sections-test/guides/ai/ai-model-hub/how-tos/rate-limits), no model-specific limits apply.