AI Endpoints

Easily access world-renowned pre-trained AI models.
Innovate with simple and secure APIs on OVHcloud's robust and confidential infrastructure. Optimize your applications with scalable AI capabilities, eliminating the need for deep expertise. Gain efficiency with powerful AI Endpoints, designed for simplicity and reliability.

Try another model

Mistral-Small-3.2-24B-Instruct-2506

Visual LLM

Building upon Mistral Small 3 (2501), Mistral Small 3.2 (2506) adds state-of-the-art vision understanding and enhances long context capabilities up to 128k tokens without compromising text performance. With 24 billion parameters, this model achieves top-tier capabilities in both text and vision tasks. This model is a minor update of Mistral-Small-3.1-24B-Instruct-2503, which is an instruction-finetuned version of: Mistral-Small-3.1-24B-Base-2503.

Supported FeaturesFunction callingVisionStreaming

Output Formatsraw_textjson_objectjson_schema

Pricing

0.09€/ Mtoken input

0.28€/ Mtoken output

Published on

huggingface

Release date

20 Jun 2025

Added to the catalogue

30 Jun 2025

Context Sizes

128k

Parameters

24B

Licence

Apache 2.0

https://oai.endpoints.kepler.ai.cloud.ovh.net/v1

Example of how to use Mistral-Small-3.2-24B-Instruct-2506 Vision Language Model API in python

Introduction

The following examples walk you through the use of a VLM (Vision Language Model), able to take images and texts prompts and generate text. To send a multimodal input to the model, you have to use a content list that will contain the text prompt and the base64 encoded image.

A VLM encodes the image as embeddings and uses tokens to represent and process the image along the usual text tokens, so an image will use some of the input context length of the model.

With a simple HTTP client (requests)

First, install the requests library:

pip install requests

Next, export your access token to the OVH_AI_ENDPOINTS_ACCESS_TOKEN environment variable:

export OVH_AI_ENDPOINTS_ACCESS_TOKEN=<your-access-token>

If you do not have an access token key yet, follow the instructions in the AI Endpoints – Getting Started.

If you don't have any images available for testing, save the following image locally as sample.jpg:

And then run the following example Python code to ask the VLM to describe this image (or perform another task by adapting the content field of the messages dictionary):

import mimetypes
import os
import requests
import base64

image_filepath = "sample.jpg"
with open(image_filepath, "rb") as img_file:
    image_data = img_file.read()

# detect MIME type (default to jpeg if unknown)
mime_type, _ = mimetypes.guess_type(image_filepath)
if mime_type is None:
    mime_type = "image/jpeg"

encoded_image = f"data:{mime_type};base64,{base64.b64encode(image_data).decode('utf-8')}"
 
headers = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {os.getenv('OVH_AI_ENDPOINTS_ACCESS_TOKEN')}",
}

# With /chat/completions
url = "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1/chat/completions"
payload = {
    "max_tokens": 512,
    "messages": [
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "Describe this image."
                },
                {
                    "type": "image_url",
                    "image_url": {
                        "url": encoded_image
                    }
                }
            ]
        }
    ],
    "model": "Mistral-Small-3.2-24B-Instruct-2506",
    "temperature": 0.2,
}
response = requests.post(url, json=payload, headers=headers)
if response.status_code == 200:
    # Handle response
    response_data = response.json()
    # Parse JSON response
    choices = response_data["choices"]
    for choice in choices:
        text = choice["message"]["content"]
        # Process text and finish_reason
        print(text)
else:
    print("Error:", response.status_code, response.text)

# With /responses
url = "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1/responses"
payload = {
    "max_output_tokens": 512,
    "input": [
        {
            "role": "user",
            "type": "message",
            "content": [
                {
                    "type": "input_text",
                    "text": "Describe this image."
                },
                {
                    "type": "input_image",
                    "image_url": encoded_image
                }
            ]
        }
    ],
    "store": False, # Stateful mode is not supported
    "model": "Mistral-Small-3.2-24B-Instruct-2506",
    "temperature": 0,
}
response = requests.post(url, json=payload, headers=headers)
if response.status_code == 200:
    # Handle response
    response_data = response.json()
    text = response_data["output"][0]["content"][0]["text"]
    print(text)
else:
    print("Error:", response.status_code, response.text)

With the Python OpenAI library

The Mistral-Small-3.2-24B-Instruct-2506 API is compatible with the OpenAI specification.

First install the openai library:

pip install openai

Next, export your access token to the OVH_AI_ENDPOINTS_ACCESS_TOKEN environment variable:

export OVH_AI_ENDPOINTS_ACCESS_TOKEN=<your-access-token>

If you do not have an access token key yet, follow the instructions in the AI Endpoints – Getting Started.

Finally, run the following Python code:

import mimetypes
import os
import base64

from openai import OpenAI

url = "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1"

client = OpenAI(
    base_url=url,
    api_key=os.getenv("OVH_AI_ENDPOINTS_ACCESS_TOKEN")
)

def read_encoded_image(image_filepath: str) -> str:
    with open(image_filepath, "rb") as img_file:
        image_data = img_file.read()

    # detect MIME type (default to jpeg if unknown)
    mime_type, _ = mimetypes.guess_type(image_filepath)
    if mime_type is None:
        mime_type = "image/jpeg"

    encoded_image = f"data:{mime_type};base64,{base64.b64encode(image_data).decode('utf-8')}"
    return encoded_image

def multimodal_chat_completion(new_message: str, image_filepath: str = None) -> str:
    new_user_message = {
        "role": "user",
        "content": [
            {
                "type": "text",
                "text": new_message
            }
        ]
    }

    if image_filepath is not None:
        image_content = {
            "type": "image_url",
            "image_url": {
                "url": read_encoded_image(image_filepath)
            }
        }
        new_user_message["content"].append(image_content)

    history_openai_format = [new_user_message]

    return client.chat.completions.create(
        model="Mistral-Small-3.2-24B-Instruct-2506",
        messages=history_openai_format,
        temperature=0.2,
        max_tokens=1024
    ).choices.pop().message.content

def multimodal_responses(new_message: str, image_filepath: str = None) -> str:
    new_user_message = {
        "role": "user",
        "type": "message",
        "content": [
            {
                "type": "input_text",
                "text": new_message
            }
        ]
    }

    if image_filepath is not None:
        image_content = {
            "type": "input_image",
            "image_url": read_encoded_image(image_filepath)
        }
        new_user_message["content"].append(image_content)

    history_openai_format = [new_user_message]

    return client.responses.create(
        model="Mistral-Small-3.2-24B-Instruct-2506",
        input=history_openai_format,
        temperature=0.2,
        max_output_tokens=1024,
        store=False # Stateful mode is not supported
    ).output[0].content[0].text

if __name__ == '__main__':
    # With chat completion endpoint
    print(multimodal_chat_completion("Describe this image.", "sample.jpg"))
    # With responses endpoint
    print(multimodal_responses("Describe this image.", "sample.jpg"))

Model rate limit

When using AI Endpoints, the following rate limits apply:

Anonymous: 2 requests per minute, per IP and per model.
Authenticated with an API access key: 400 requests per minute, per Public Cloud project and per model.

If you exceed this limit, a 429 error code will be returned.

If you require higher usage, please get in touch with us to discuss increasing your rate limits.

Going Further

Want to explore the full capabilities of the LLM API? Dive into our dedicated Structured Output and Function Calling guides.

For a broader overview of AI Endpoints, explore the full AI Endpoints Documentation.

Reach out to our support team or join the OVHcloud Discord #ai-endpoints channel to share your questions, feedback, and suggestions for improving the service, to the team and the community.

AI Endpoints

Mistral-Small-3.2-24B-Instruct-2506

Example of how to use Mistral-Small-3.2-24B-Instruct-2506 Vision Language Model API in python

Introduction

With a simple HTTP client (requests)

With the Python OpenAI library

Model rate limit

Going Further

Get started with Mistral-Small-3.2-24B-Instruct-2506

AI Endpoints - Getting Started

AI Endpoints - Features, Capabilities and Limitations

AI Endpoints - Troubleshooting

AI Endpoints - Structured Output

AI Endpoints - Function Calling

AI Endpoints - Using Virtual Models