Mistral AI models

Mistral AI models on Gemini Enterprise Agent Platform offer fully managed and serverless models as APIs. To use a Mistral AI model on Agent Platform, send a request directly to the Agent Platform API endpoint. Because Mistral AI models use a managed API, there's no need to provision or manage infrastructure.

You can stream your responses to reduce the end-user latency perception. A streamed response uses server-sent events (SSE) to incrementally stream the response.

You pay for Mistral AI models as you use them (pay as you go). For pay-as-you-go pricing, see Mistral AI model pricing on the Gemini Enterprise Agent Platform pricing

page.

Available Mistral AI models

The following models are available from Mistral AI to use in Gemini Enterprise Agent Platform. To access a Mistral AI model, go to its Model Garden model card.

Mistral Medium 3

Mistral Medium 3 is a versatile model designed for a wide range of tasks, including programming, mathematical reasoning, understanding long documents, summarization, and dialogue. It excels at complex tasks requiring advanced reasoning abilities, visual understanding or a high level of specialization (e.g. creative writing, agentic workflows, code generation).

It boasts multi-modal capabilities, enabling it to process visual inputs, and supports dozens of languages, including over 80 coding languages. Additionally, it features function calling and agentic workflows.

Mistral Medium 3 is optimized for single-node inference, particularly for long-context applications. Its size allows it to achieve high throughput on a single node.

Go to the Mistral Medium 3 model card

Mistral OCR (25.05)

Mistral OCR (25.05) is an Optical Character Recognition API for document understanding. Mistral OCR (25.05) excels in understanding complex document elements, including interleaved imagery, mathematical expressions, tables, and advanced layouts such as LaTeX formatting. The model enables deeper understanding of rich documents such as scientific papers with charts, graphs, equations and figures.

Mistral OCR (25.05) is an ideal model to use in combination with a RAG system that takes multimodal documents (such as slides or complex PDFs) as input.

You can couple Mistral OCR (25.05) with other Mistral models to reformat the results. This combination ensures that the extracted content is not only accurate but also presented in a structured and coherent manner, making it suitable for various downstream applications and analyses.

Go to the Mistral OCR (25.05) model card

Mistral Small 3.1 (25.03)

Mistral Small 3.1 (25.03) features multimodal capabilities and a context of up to 128,000. The model can process and understand visual inputs and long documents, further expanding its range of applications compared to the previous Mistral AI Small model. Mistral Small 3.1 (25.03) is a versatile model designed for various tasks such as programming, mathematical reasoning, document understanding, and dialogue. Mistral Small 3.1 (25.03) is designed for low-latency applications to deliver best-in-class efficiency compared to models of the same quality.

Mistral Small 3.1 (25.03) has undergone a full post-training process to align the model with human preferences and needs, making it usable out-of-the-box for applications that require chat or precise instruction following.

Go to the Mistral Small 3.1 (25.03) model card

Codestral 2

Codestral 2 is Mistral's code generation specialized model built specifically for high-precision fill-in-the-middle (FIM) completion. It helps developers write and interact with code through a shared instruction and completion API endpoint. As it masters code and can also converse in a variety of languages, it can be used to design advanced AI applications for software developers.

The latest release of Codestral 2 delivers measurable upgrades over prior version Codestral (25.01):

• 30% increase in accepted completions.
• 10% more retained code after suggestion.
• 50% fewer runaway generations, improving confidence in longer edits.

Improved performance on academic benchmarks for short and long-context FIM completion.

• Code generation: code completion, suggestions, translation.
• Code understanding and documentation: code summarization and explanation.
• Code quality: code review, refactoring, bug fixing and test case generation.
• Code fill-in-the-middle: users can define the starting point of the code using a prompt, and the ending point of the code using an optional suffix and an optional stop. The Codestral model will then generate the code that fits in between, making it ideal for tasks that require a specific piece of code to be generated.

Go to the Codestral 2 model card

Use Mistral AI models

You can use curl commands to send requests to the Gemini Enterprise Agent Platform endpoint using the following model names:

• For Mistral Medium 3, use mistral-medium-3
• For Mistral OCR (25.05), use mistral-ocr-2505
• For Mistral Small 3.1 (25.03), use mistral-small-2503
• For Codestral 2, use codestral-2

For more information about using the Mistral AI SDK, see the Mistral AI Gemini Enterprise Agent Platform documentation.

Before you begin

To use Mistral AI models with Gemini Enterprise Agent Platform, you must perform the following steps. The Agent Platform API (aiplatform.googleapis.com) must be enabled to use Gemini Enterprise Agent Platform. If you already have an existing project with the Agent Platform API enabled, you can use that project instead of creating a new project.

Sign in to your Google Cloud account. If you're new to Google Cloud, create an account to evaluate how our products perform in real-world scenarios. New customers also get $300 in free credits to run, test, and deploy workloads.

In the Google Cloud console, on the project selector page, select or create a Google Cloud project.

Roles required to select or create a project

• Select a project: Selecting a project doesn't require a specific IAM role—you can select any project that you've been granted a role on.
• Create a project: To create a project, you need the Project Creator role (roles/resourcemanager.projectCreator), which contains the resourcemanager.projects.create permission. Learn how to grant roles.

Go to project selector

Verify that billing is enabled for your Google Cloud project.

Enable the Gemini Enterprise Agent Platform API.

Roles required to enable APIs

To enable APIs, you need the Service Usage Admin IAM role (roles/serviceusage.serviceUsageAdmin), which contains the serviceusage.services.enable permission. Learn how to grant roles.

Enable the API

In the Google Cloud console, on the project selector page, select or create a Google Cloud project.

Roles required to select or create a project

• Select a project: Selecting a project doesn't require a specific IAM role—you can select any project that you've been granted a role on.
• Create a project: To create a project, you need the Project Creator role (roles/resourcemanager.projectCreator), which contains the resourcemanager.projects.create permission. Learn how to grant roles.

Go to project selector

Verify that billing is enabled for your Google Cloud project.

Enable the Gemini Enterprise Agent Platform API.

Roles required to enable APIs

To enable APIs, you need the Service Usage Admin IAM role (roles/serviceusage.serviceUsageAdmin), which contains the serviceusage.services.enable permission. Learn how to grant roles.

Enable the API

1. Go to one of the following Model Garden model cards, then click Enable:
   • Go to the Mistral Medium 3 model card
   • Go to the Mistral OCR (25.05) model card
   • Go to the Mistral Small 3.1 (25.03) model card
   • Go to the Codestral 2 model card

Make a streaming call to a Mistral AI model

The following sample makes a streaming call to a Mistral AI model.

POST https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/mistralai/models/MODEL:streamRawPredict

{
"model": MODEL,
  "messages": [
   {
    "role": "ROLE",
    "content": "CONTENT"
   }],
  "max_tokens": MAX_TOKENS,
  "stream": true
}

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/mistralai/models/MODEL:streamRawPredict"

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/mistralai/models/MODEL:streamRawPredict" | Select-Object -Expand Content

data: {
    "id": "0e9c8e69e5924f729b39bc60bac9e0be",
    "object": "chat.completion.chunk",
    "created": 1720807292,
    "model": "MODEL",
    "choices": [
        {
            "index": 0,
            "delta": {
              "content": "OUTPUT"
            },
            "finish_reason": null,
            "logprobs": null
        }
    ]
}

data: {
    "id": "0e9c8e69e5924f729b39bc60bac9e0be",
    "object": "chat.completion.chunk",
    "created": 1720807292,
    "model": "MODEL",
    "choices": [
        {
            "index": 0,
            "delta": {
              "content": "OUTPUT"
            },
            "finish_reason": null,
            "logprobs": null
        }
    ]
}
...

Make a unary call to a Mistral AI model

The following sample makes a unary call to a Mistral AI model.

POST https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/mistralai/models/MODEL:rawPredict

{
"model": MODEL,
  "messages": [
   {
    "role": "ROLE",
    "content": "CONTENT"
   }],
  "max_tokens": MAX_TOKENS,
  "stream": false
}

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/mistralai/models/MODEL:rawPredict"

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/mistralai/models/MODEL:rawPredict" | Select-Object -Expand Content

{
    "id": "e71d13ffb77344a08e34e0a22ea84458",
    "object": "chat.completion",
    "created": 1720806624,
    "model": "MODEL",
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "OUTPUT",
                "tool_calls": null
            },
            "finish_reason": "stop",
            "logprobs": null
        }
    ],
    "usage": {
        "prompt_tokens": 17,
        "total_tokens": 295,
        "completion_tokens": 278
    }
}

Mistral AI model region availability and quotas

For Mistral AI models, a quota applies for each region where the model is available. The quota is specified in queries per minute (QPM) and tokens per minute (TPM). TPM includes both input and output tokens.

If you want to increase any of your quotas for Generative AI on Gemini Enterprise Agent Platform, you can use the Google Cloud console to request a quota increase. To learn more about quotas, see the Cloud Quotas overview.