Mistral AI 模型

Gemini Enterprise Agent Platform 上的 Mistral AI 模型以 API 形式提供全代管式无服务器模型。如需使用 Agent Platform 上的 Mistral AI 模型，请直接向 Agent Platform API 端点发送请求。由于 Mistral AI 模型使用托管式 API，因此无需预配或管理基础架构。

您可以流式传输回答，以降低最终用户对延迟时间的感知度。流式回答使用服务器发送的事件 (SSE) 来逐步流式传输回答。

Mistral AI 模型按实际用量付费（随用随付）。如需了解随用随付价格，请参阅 Gemini Enterprise Agent Platform 价格页面上的 Mistral AI 模型价格。

可用的 Mistral AI 模型

Mistral AI 提供了以下模型，可在 Gemini Enterprise Agent Platform 中使用。如需访问 Mistral AI 模型，请前往其 Model Garden 模型卡片。

使用 Mistral AI 模型

您可以使用 curl 命令通过以下模型名称向 Gemini Enterprise Agent Platform 端点发送请求：

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

如需详细了解如何使用 Mistral AI SDK，请参阅 Mistral AI Gemini Enterprise Agent Platform 文档。

准备工作

如需将 Mistral AI 模型与 Gemini Enterprise Agent Platform 搭配使用，您必须执行以下步骤。必须启用 Agent Platform API (aiplatform.googleapis.com) 才能使用 Gemini Enterprise Agent Platform。如果您已有启用了 Agent Platform API 的项目，则可以使用该项目，而无需创建新项目。

1. In the Cloud de Confiance console, on the project selector page, select or create a Cloud de Confiance 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

2. Verify that billing is enabled for your Cloud de Confiance project.

3. Enable the Gemini Enterprise Agent Platform API, if it is not already enabled.

   Roles required to enable APIs

   To enable APIs, you need the serviceusage.services.enable permission. If you created the project, then you likely already have this permission through the Owner role (roles/owner). Otherwise, you can get this permission through the Service Usage Admin role (roles/serviceusage.serviceUsageAdmin). Learn how to grant roles.

   Enable the API

4. 前往以下 Model Garden 模型卡片之一，然后点击启用：
   • 前往 Mistral Medium 3 模型卡片
   • 前往 Mistral OCR (25.05) 模型卡片
   • 前往 Mistral Small 3.1 (25.03) 模型卡片
   • 前往 Codestral 2 模型卡片

对 Mistral AI 模型进行流式调用

以下示例对 Mistral AI 模型进行流式调用。

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
        }
    ]
}
...

对 Mistral AI 模型进行一元调用

以下示例对 Mistral AI 模型进行一元调用。

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 模型区域可用性和配额

对于 Mistral AI 模型，提供该模型的每个区域都有相应的配额。配额在每分钟查询次数 (QPM) 和每分钟词元数 (TPM) 中指定。TPM 包括输入和输出词元。

如果要增加代理平台 (Agent Platform) 的任何配额，您可以使用 Cloud de Confiance 控制台申请增加配额。如需详细了解配额，请参阅 Cloud 配额概览。