要求 Llama 預測

您可以使用 curl 指令，透過下列模型名稱將要求傳送至 Gemini Enterprise Agent Platform 端點：

• 如要使用 Llama 4 Maverick 17B-128E，請使用 llama-4-maverick-17b-128e-instruct-maas
• 如要使用 Llama 4 Scout 17B-16E，請使用 llama-4-scout-17b-16e-instruct-maas
• 如要使用 Llama 3.3 70B，請使用 llama-3.3-70b-instruct-maas

如要瞭解如何對 Llama 模型發出串流和非串流呼叫，請參閱「呼叫開放模型的 MaaS API」。

事前準備

如要透過 Gemini Enterprise Agent Platform 使用 Llama 模型，請完成下列步驟。如要使用 Gemini Enterprise Agent Platform，必須啟用 Agent Platform API (aiplatform.googleapis.com)。如果您已啟用 Agent Platform API 的現有專案，可以使用該專案，不必建立新專案。

登入 Google Cloud 帳戶。如果您是 Google Cloud新手，歡迎 建立帳戶，親自評估產品在實際工作環境中的成效。新客戶還能獲得價值 $300 美元的免費抵免額，可用於執行、測試及部署工作負載。

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 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

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 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

1. 前往下列任一 Model Garden 模型資訊卡，然後按一下「啟用」：
   • 前往 Llama 4 Maverick 17B-128E 模型資訊卡
   • 前往 Llama 4 Scout 17B-16E 模型資訊卡
   • 前往 Llama 3.3 70B 模型資訊卡

對 Llama 模型發出串流呼叫

下列範例會對 Llama 模型發出串流呼叫。

POST https://LOCATION-aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION/endpoints/openapi/chat/completions

{
  "model": "meta/MODEL",
  "messages": [
    {
      "role": "ROLE",
      "content": "CONTENT"
    }
  ],
  "max_tokens": MAX_OUTPUT_TOKENS,
  "stream": true,
  "extra_body": {
    "google": {
      "model_safety_settings": {
        "enabled": ENABLE_LLAMA_GUARD,
        "llama_guard_settings": {}
      }
    }
  }
}

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/v1beta1/projects/PROJECT_ID/locations/LOCATION/endpoints/openapi/chat/completions"

$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/v1beta1/projects/PROJECT_ID/locations/LOCATION/endpoints/openapi/chat/completions" | Select-Object -Expand Content

data: {
  "choices": [
    {
      "delta": {
        "content": "CONTENT",
        "role": "assistant",
        "refusal: "REFUSAL_REASON" #If using Llama Guard and response was flagged by Llama Guard
      },
      "index": 0
    }
  ],
  "model": "meta/MODEL_NAME",
  "object": "chat.completion.chunk"
}

data: {
  "choices": [
    {
      "delta": {
        "content": "CONTENT",
        "role": "assistant"
      },
      "finish_reason": "stop",
      "index": 0
    }
  ],
  "model": "meta/MODEL_NAME",
  "object": "chat.completion.chunk",
  "usage": {
    "completion_tokens": 131,
    "prompt_tokens": 14,
    "total_tokens": 145
  }
}

對 Llama 模型發出一元呼叫

以下範例會對 Llama 模型進行一元呼叫。

POST https://LOCATION-aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION/endpoints/openapi/chat/completions

{
  "model": "meta/MODEL",
  "messages": [
    {
      "role": "ROLE",
      "content": "CONTENT"
    }
  ],
  "max_tokens": MAX_OUTPUT_TOKENS,
  "stream": false,
  "extra_body": {
    "google": {
      "model_safety_settings": {
        "enabled": ENABLE_LLAMA_GUARD,
        "llama_guard_settings": {}
      }
    }
  }
}

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/v1beta1/projects/PROJECT_ID/locations/LOCATION/endpoints/openapi/chat/completions"

$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/v1beta1/projects/PROJECT_ID/locations/LOCATION/endpoints/openapi/chat/completions" | Select-Object -Expand Content

{
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "CONTENT",
        "role": "assistant",
        "refusal: "REFUSAL_REASON" #If using Llama Guard and response was flagged by Llama Guard
      }
    }
  ],
  "model": "meta/llama3-405b-instruct-maas",
  "object": "chat.completion",
  "usage": {
    "completion_tokens": 367,
    "prompt_tokens": 14,
    "total_tokens": 381
  }
}

已標記的回覆

根據預設，使用 Llama 3.3 和 Llama 3.1 模型進行的所有預測都會啟用 Llama Guard 3 8B。根據預設，使用 Llama 3.2 模型進行的所有預測都會啟用 Llama Guard 3 11B 視覺功能。Llama Guard 會檢查輸入和輸出內容，協助保護回覆內容。如果 Llama Guard 判斷回覆內容不安全，就會標記該回覆。

如要停用 Llama Guard，請修改模型安全設定。詳情請參閱串流或一元範例中的 model_safety_settings 欄位。

使用 Vertex AI Studio

如要使用 Llama 模型，您可以在 Google Cloud 控制台使用 Vertex AI Studio 快速設計生成式 AI 模型原型並進行測試。舉例來說，您可以使用 Vertex AI Studio 比較 Llama 模型回覆與其他支援的模型，例如 Google 的 Gemini。

Llama 模型支援的區域和配額

如果是 Llama 模型，則配額適用於模型可用的每個區域。配額以每分鐘查詢次數 (QPM) 為單位。

如要增加 Gemini Enterprise Agent Platform 的生成式 AI 配額，可以透過 Google Cloud 控制台申請提高配額。如要進一步瞭解配額，請參閱「Cloud Quotas 總覽」。