Call Responses API

Gemini Enterprise Agent Platform 的 xAI Grok 模型支援 Responses API,可用於生成回覆。

本頁面說明如何使用 Responses API 呼叫 Grok 模型。

事前準備

如要透過 Gemini Enterprise Agent Platform 使用 Grok 模型,請務必完成下列步驟。必須啟用 Gemini Enterprise Agent Platform API (aiplatform.googleapis.com)。

  1. 登入 Google Cloud 帳戶。如果您未曾使用過 Google Cloud,歡迎 建立帳戶,親自體驗實際使用我們產品的成效。新客戶還能獲得價值 $300 美元的免費抵免額,用於執行、測試及部署工作負載。
  2. 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

  3. Verify that billing is enabled for your Google Cloud project.

  4. 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

  5. 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

  6. Verify that billing is enabled for your Google Cloud project.

  7. 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

對 Responses API 進行無狀態呼叫

store 的預設值為 false,因此除非您將 store 設為 true,否則要求不具狀態。下列範例會明確將 store 設為 false (在 Python 中為 False)。

對 Responses API 發出非串流呼叫

下列範例說明如何對 Responses API 進行非串流呼叫:

Python

在試用這個範例之前,請先按照「使用用戶端程式庫的 Agent Platform 快速入門導覽課程」中的 Python 設定說明操作。

如要向 Agent Platform 進行驗證,請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。

執行這個範例前,請務必設定 OPENAI_BASE_URL 環境變數或 OAuth 憑證。詳情請參閱「驗證和憑證」。

import google.auth
import google.auth.transport.requests
from openai import OpenAI
credentials, _ = google.auth.default(
    scopes=["https://www.googleapis.com/auth/cloud-platform"]
)
credentials.refresh(google.auth.transport.requests.Request())
client = OpenAI(
    base_url="https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/endpoints/openapi",
    api_key=credentials.token,
)
response = client.responses.create(
    model="MODEL",
    input="INPUT",
    max_output_tokens=MAX_OUTPUT_TOKENS,
    stream=False,
    store=False,
)
print(response)
  • PROJECT_ID: Google Cloud 專案 ID。
  • MODEL:要使用的模型名稱,例如 xai/grok-4.7。
  • INPUT:模型的提示或輸入內容。
  • MAX_OUTPUT_TOKENS:回覆內可以生成的詞元數量上限。一個詞元約為四個字元。100 個詞元約等於 60 到 80 個字。

    如要取得較短的回覆,請指定較低的值;如要取得可能較長的回覆,請調高此值。

REST

設定環境後,您可以使用 REST 測試文字提示詞。下列範例會將要求傳送至發布者模型端點。

使用任何要求資料之前,請先修改下列項目的值:

  • PROJECT_ID: Google Cloud 專案 ID。
  • MODEL:要使用的模型名稱,例如 xai/grok-4.7。
  • INPUT:模型的提示或輸入內容。
  • MAX_OUTPUT_TOKENS:回覆內可以生成的詞元數量上限。一個詞元約為四個字元。100 個詞元約等於 60 到 80 個字。

    如要取得較短的回覆,請指定較低的值;如要取得可能較長的回覆,請調高此值。

HTTP 方法和網址:

POST https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/endpoints/openapi/responses

JSON 要求內文:

{
  "model": "MODEL",
  "input": "INPUT",
  "max_output_tokens": MAX_OUTPUT_TOKENS,
  "stream": false,
  "store": false
}

如要傳送要求,請選擇以下其中一個選項:

curl

將要求主體儲存在名為 request.json 的檔案中,然後執行下列指令:

curl -X POST \
-H "Authorization: Bearer $(gcloud auth application-default print-access-token)" \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
"https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/endpoints/openapi/responses"

PowerShell

將要求主體儲存在名為 request.json 的檔案中,然後執行下列指令:

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

Invoke-WebRequest `
-Method POST `
-Headers $headers `
-ContentType: "application/json; charset=utf-8" `
-InFile request.json `
-Uri "https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/endpoints/openapi/responses" | Select-Object -Expand Content

以下範例顯示完整的 curl 要求:

curl -s -X POST \
  -H "Authorization: Bearer $(gcloud auth application-default print-access-token)" \
  -H "Content-Type: application/json" \
  "https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/endpoints/openapi/responses" \
  -d '{
    "model": "xai/grok-4.7",
    "input": "Explain black holes in one short sentence.",
    "max_output_tokens": 100,
    "stream": false,
    "store": false
  }'

根據 Responses API 定義,非串流回應會包含專屬 ID、模型中繼資料、使用統計資料,以及含有生成的文字的輸出陣列。

{
  "background": false,
  "completed_at": 1778892918,
  "created_at": 1778892916,
  "error": null,
  "frequency_penalty": 0,
  "id": "c8AHavnIMP6UifEPgIfcgAg",
  "incomplete_details": null,
  "instructions": null,
  "max_output_tokens": null,
  "max_tool_calls": null,
  "metadata": {
    "system_fingerprint": "fp_39c5j0a3e9"
  },
  "model": "MODEL",
  "object": "response",
  "output": [
    {
      "content": [
        {
          "annotations": [],
          "logprobs": [],
          "text": "OUTPUT_TEXT",
          "type": "output_text"
        }
      ],
      "id": "msg_c8AHavnIMP6UifEPgIfcgAg",
      "role": "assistant",
      "status": "completed",
      "type": "message"
    }
  ],
  "parallel_tool_calls": true,
  "presence_penalty": 0,
  "previous_response_id": null,
  "prompt_cache_key": null,
  "reasoning": {
    "effort": "medium",
    "summary": "detailed"
  },
  "safety_identifier": null,
  "service_tier": "default",
  "status": "completed",
  "store": false,
  "temperature": 0.7,
  "text": {
    "format": {
      "type": "text"
    }
  },
  "tool_choice": "auto",
  "tools": [],
  "top_logprobs": 0,
  "top_p": 0.95,
  "truncation": "disabled",
  "usage": {
    "extra_properties": {
      "google": {
        "traffic_type": "ON_DEMAND"
      }
    },
    "input_tokens": 335,
    "input_tokens_details": {
      "cached_tokens": 320
    },
    "num_server_side_tools_used": 0,
    "num_sources_used": 0,
    "output_tokens": 305,
    "output_tokens_details": {
      "reasoning_tokens": 284
    },
    "total_tokens": 640
  },
  "user": null
}

對 Responses API 發出串流呼叫

下列範例說明如何對 Responses API 發出串流呼叫:

Python

在試用這個範例之前,請先按照「使用用戶端程式庫的 Agent Platform 快速入門導覽課程」中的 Python 設定說明操作。

如要向 Agent Platform 進行驗證,請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。

執行這個範例前,請務必設定 OPENAI_BASE_URL 環境變數或 OAuth 憑證。詳情請參閱「驗證和憑證」。

import google.auth
import google.auth.transport.requests
from openai import OpenAI
credentials, _ = google.auth.default(
    scopes=["https://www.googleapis.com/auth/cloud-platform"]
)
credentials.refresh(google.auth.transport.requests.Request())
client = OpenAI(
    base_url="https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/endpoints/openapi",
    api_key=credentials.token,
)
stream = client.responses.create(
    model="MODEL",
    input="INPUT",
    max_output_tokens=MAX_OUTPUT_TOKENS,
    stream=True,
    store=False,
)
for event in stream:
    if event.type == "response.output_text.delta":
        print(event.delta, end="")
  • PROJECT_ID: Google Cloud 專案 ID。
  • MODEL:要使用的模型名稱,例如 xai/grok-4.7。
  • INPUT:模型的提示或輸入內容。
  • MAX_OUTPUT_TOKENS:回覆內可以生成的詞元數量上限。一個詞元約為四個字元。100 個詞元約等於 60 到 80 個字。

    如要取得較短的回覆,請指定較低的值;如要取得可能較長的回覆,請調高此值。

REST

設定環境後,您可以使用 REST 測試文字提示詞。下列範例會將要求傳送至發布者模型端點。

使用任何要求資料之前,請先修改下列項目的值:

  • PROJECT_ID: Google Cloud 專案 ID。
  • MODEL:要使用的模型名稱,例如 xai/grok-4.7。
  • INPUT:模型的提示或輸入內容。
  • MAX_OUTPUT_TOKENS:回覆內可以生成的詞元數量上限。一個詞元約為四個字元。100 個詞元約等於 60 到 80 個字。

    如要取得較短的回覆,請指定較低的值;如要取得可能較長的回覆,請調高此值。

HTTP 方法和網址:

POST https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/endpoints/openapi/responses

JSON 要求內文:

{
  "model": "MODEL",
  "input": "INPUT",
  "max_output_tokens": MAX_OUTPUT_TOKENS,
  "stream": true,
  "store": false
}

如要傳送要求,請選擇以下其中一個選項:

curl

將要求主體儲存在名為 request.json 的檔案中,然後執行下列指令:

curl -X POST \
-H "Authorization: Bearer $(gcloud auth application-default print-access-token)" \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
"https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/endpoints/openapi/responses"

PowerShell

將要求主體儲存在名為 request.json 的檔案中,然後執行下列指令:

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

Invoke-WebRequest `
-Method POST `
-Headers $headers `
-ContentType: "application/json; charset=utf-8" `
-InFile request.json `
-Uri "https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/endpoints/openapi/responses" | Select-Object -Expand Content
 

對 Responses API 發出有狀態呼叫

如要提出有狀態要求,您必須設定組織政策服務,允許這類要求。具體來說,請更新限制 constraints/vertexai.allowedPartnerModelFeatures,將 publishers/xai/models/MODEL_NAME:stateful_responses_api 新增至允許的值 (例如 publishers/xai/models/grok-4.7:stateful_responses_api)。詳情請參閱「控管模型存取權」。

Responses API 透過有狀態要求支援多輪對話。store 的預設值為 false,因此如要提出有狀態要求,必須明確將 store 設為 true。在有狀態的對話中,您可以在 previous_response_id 欄位中提供 id,藉此參照先前的回覆。

建立回覆

以下範例顯示使用 Responses API 的兩輪對話:

第 1 輪:初始要求

在第一個回合中,提出要求並將 store 設為 true。如果省略 store 參數,則預設為 false,且不會儲存回應。

Python

在試用這個範例之前,請先按照「使用用戶端程式庫的 Agent Platform 快速入門導覽課程」中的 Python 設定說明操作。

如要向 Agent Platform 進行驗證,請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。

執行這個範例前,請務必設定 OPENAI_BASE_URL 環境變數或 OAuth 憑證。詳情請參閱「驗證和憑證」。

import google.auth
import google.auth.transport.requests
from openai import OpenAI
credentials, _ = google.auth.default(
    scopes=["https://www.googleapis.com/auth/cloud-platform"]
)
credentials.refresh(google.auth.transport.requests.Request())
client = OpenAI(
    base_url="https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/endpoints/openapi",
    api_key=credentials.token,
)
response = client.responses.create(
    model="MODEL",
    input="randomly pick 3 colors, just return the words of the colors",
    store=True,
)
print(response)
  • PROJECT_ID: Google Cloud 專案 ID。
  • MODEL:要使用的模型名稱,例如 xai/grok-4.7。

第 1 輪的回覆範例:

{
  "background": false,
  "completed_at": 1793834418,
  "created_at": 1793834418,
  "error": null,
  "frequency_penalty": 0,
  "id": "5f76a045-71d9-45af-8b07-1f2feae0675a",
  "incomplete_details": null,
  "instructions": null,
  "max_output_tokens": null,
  "max_tool_calls": null,
  "metadata": {
    "system_fingerprint": "fp_grok47_0"
  },
  "model": "xai/grok-4.7",
  "object": "response",
  "output": [
    {
      "content": [
        {
          "annotations": [],
          "logprobs": [],
          "text": "cerulean amber violet",
          "type": "output_text"
        }
      ],
      "id": "msg_5f76a045-71d9-45af-8b07-1f2feae0675a",
      "role": "assistant",
      "status": "completed",
      "type": "message"
    }
  ],
  "parallel_tool_calls": true,
  "presence_penalty": 0,
  "previous_response_id": null,
  "prompt_cache_key": null,
  "reasoning": {
    "effort": "high",
    "summary": "detailed"
  },
  "safety_identifier": null,
  "service_tier": "default",
  "status": "completed",
  "store": true,
  "temperature": 0.7,
  "text": {
    "format": {
      "type": "text"
    }
  },
  "tool_choice": "auto",
  "tools": [],
  "top_logprobs": 0,
  "top_p": 0.95,
  "truncation": "disabled",
  "usage": {
    "context_details": {
      "input_tokens": 220,
      "output_tokens": 144
    },
    "extra_properties": {
      "google": {
        "traffic_type": "ON_DEMAND"
      }
    },
    "input_tokens": 220,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "num_server_side_tools_used": 0,
    "num_sources_used": 0,
    "output_tokens": 144,
    "output_tokens_details": {
      "reasoning_tokens": 139
    },
    "total_tokens": 364
  },
  "user": null
}

REST

設定環境後,您可以使用 REST 測試文字提示詞。下列範例會將要求傳送至發布者模型端點。

使用任何要求資料之前,請先修改下列項目的值:

  • PROJECT_ID: Google Cloud 專案 ID。
  • MODEL:要使用的模型名稱,例如 xai/grok-4.7。

HTTP 方法和網址:

POST https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/endpoints/openapi/responses

JSON 要求內文:

{
  "model": "MODEL",
  "input": "randomly pick 3 colors, just return the words of the colors",
  "store": true
}

如要傳送要求,請選擇以下其中一個選項:

curl

將要求主體儲存在名為 request.json 的檔案中,然後執行下列指令:

curl -X POST \
-H "Authorization: Bearer $(gcloud auth application-default print-access-token)" \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
"https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/endpoints/openapi/responses"

PowerShell

將要求主體儲存在名為 request.json 的檔案中,然後執行下列指令:

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

Invoke-WebRequest `
-Method POST `
-Headers $headers `
-ContentType: "application/json; charset=utf-8" `
-InFile request.json `
-Uri "https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/endpoints/openapi/responses" | Select-Object -Expand Content

以下範例顯示完整的 curl 要求:

curl -X POST \
  -H "Authorization: Bearer $(gcloud auth application-default print-access-token)" \
  -H "Content-Type: application/json" \
  "https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/endpoints/openapi/responses" \
  -d '{
    "model": "xai/grok-4.7",
    "input": "randomly pick 3 colors, just return the words of the colors",
    "store": true
  }'

第 1 輪的回覆範例:

{
  "background": false,
  "completed_at": 1793834418,
  "created_at": 1793834418,
  "error": null,
  "frequency_penalty": 0,
  "id": "5f76a045-71d9-45af-8b07-1f2feae0675a",
  "incomplete_details": null,
  "instructions": null,
  "max_output_tokens": null,
  "max_tool_calls": null,
  "metadata": {
    "system_fingerprint": "fp_grok47_0"
  },
  "model": "xai/grok-4.7",
  "object": "response",
  "output": [
    {
      "content": [
        {
          "annotations": [],
          "logprobs": [],
          "text": "cerulean amber violet",
          "type": "output_text"
        }
      ],
      "id": "msg_5f76a045-71d9-45af-8b07-1f2feae0675a",
      "role": "assistant",
      "status": "completed",
      "type": "message"
    }
  ],
  "parallel_tool_calls": true,
  "presence_penalty": 0,
  "previous_response_id": null,
  "prompt_cache_key": null,
  "reasoning": {
    "effort": "high",
    "summary": "detailed"
  },
  "safety_identifier": null,
  "service_tier": "default",
  "status": "completed",
  "store": true,
  "temperature": 0.7,
  "text": {
    "format": {
      "type": "text"
    }
  },
  "tool_choice": "auto",
  "tools": [],
  "top_logprobs": 0,
  "top_p": 0.95,
  "truncation": "disabled",
  "usage": {
    "context_details": {
      "input_tokens": 220,
      "output_tokens": 144
    },
    "extra_properties": {
      "google": {
        "traffic_type": "ON_DEMAND"
      }
    },
    "input_tokens": 220,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "num_server_side_tools_used": 0,
    "num_sources_used": 0,
    "output_tokens": 144,
    "output_tokens_details": {
      "reasoning_tokens": 139
    },
    "total_tokens": 364
  },
  "user": null
}

第 2 輪:後續要求

在第二輪中,請在 previous_response_id 參數中參照先前回應的 ID。如要儲存這項回覆 (例如繼續對話或稍後擷取),請將 store 設為 true。

Python

在試用這個範例之前,請先按照「使用用戶端程式庫的 Agent Platform 快速入門導覽課程」中的 Python 設定說明操作。

如要向 Agent Platform 進行驗證,請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。

執行這個範例前,請務必設定 OPENAI_BASE_URL 環境變數或 OAuth 憑證。詳情請參閱「驗證和憑證」。

import google.auth
import google.auth.transport.requests
from openai import OpenAI
credentials, _ = google.auth.default(
    scopes=["https://www.googleapis.com/auth/cloud-platform"]
)
credentials.refresh(google.auth.transport.requests.Request())
client = OpenAI(
    base_url="https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/endpoints/openapi",
    api_key=credentials.token,
)
response = client.responses.create(
    model="MODEL",
    input="What is the second color?",
    previous_response_id="PREVIOUS_RESPONSE_ID",
    store=True,
)
print(response)
  • PROJECT_ID: Google Cloud 專案 ID。
  • MODEL:要使用的模型名稱,例如 xai/grok-4.7。
  • PREVIOUS_RESPONSE_ID:先前回覆的 ID,用於延續對話。

第 2 輪的回覆範例:

{
  "background": false,
  "completed_at": 1793835029,
  "created_at": 1793835029,
  "error": null,
  "frequency_penalty": 0,
  "id": "ee8b6aa6-777e-4aa2-8db4-46bbfe84491b",
  "incomplete_details": null,
  "instructions": null,
  "max_output_tokens": null,
  "max_tool_calls": null,
  "metadata": {
    "system_fingerprint": "fp_grok47_0"
  },
  "model": "xai/grok-4.7",
  "object": "response",
  "output": [
    {
      "content": [
        {
          "annotations": [],
          "logprobs": [],
          "text": "amber",
          "type": "output_text"
        }
      ],
      "id": "msg_ee8b6aa6-777e-4aa2-8db4-46bbfe84491b",
      "role": "assistant",
      "status": "completed",
      "type": "message"
    }
  ],
  "parallel_tool_calls": true,
  "presence_penalty": 0,
  "previous_response_id": "5f76a045-71d9-45af-8b07-1f2feae0675a",
  "prompt_cache_key": null,
  "reasoning": {
    "effort": "high",
    "summary": "detailed"
  },
  "safety_identifier": null,
  "service_tier": "default",
  "status": "completed",
  "store": true,
  "temperature": 0.7,
  "text": {
    "format": {
      "type": "text"
    }
  },
  "tool_choice": "auto",
  "tools": [],
  "top_logprobs": 0,
  "top_p": 0.95,
  "truncation": "disabled",
  "usage": {
    "context_details": {
      "input_tokens": 239,
      "output_tokens": 41
    },
    "extra_properties": {
      "google": {
        "traffic_type": "ON_DEMAND"
      }
    },
    "input_tokens": 239,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "num_server_side_tools_used": 0,
    "num_sources_used": 0,
    "output_tokens": 41,
    "output_tokens_details": {
      "reasoning_tokens": 40
    },
    "total_tokens": 280
  },
  "user": null
}

REST

設定環境後,您可以使用 REST 測試文字提示詞。下列範例會將要求傳送至發布者模型端點。

使用任何要求資料之前,請先修改下列項目的值:

  • PROJECT_ID: Google Cloud 專案 ID。
  • MODEL:要使用的模型名稱,例如 xai/grok-4.7。
  • PREVIOUS_RESPONSE_ID:先前回覆的 ID。

HTTP 方法和網址:

POST https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/endpoints/openapi/responses

JSON 要求內文:

{
  "model": "MODEL",
  "input": "What is the second color?",
  "previous_response_id": "PREVIOUS_RESPONSE_ID",
  "store": true
}

如要傳送要求,請選擇以下其中一個選項:

curl

將要求主體儲存在名為 request.json 的檔案中,然後執行下列指令:

curl -X POST \
-H "Authorization: Bearer $(gcloud auth application-default print-access-token)" \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
"https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/endpoints/openapi/responses"

PowerShell

將要求主體儲存在名為 request.json 的檔案中,然後執行下列指令:

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

Invoke-WebRequest `
-Method POST `
-Headers $headers `
-ContentType: "application/json; charset=utf-8" `
-InFile request.json `
-Uri "https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/endpoints/openapi/responses" | Select-Object -Expand Content

以下範例顯示完整的 curl 要求:

curl -X POST \
  -H "Authorization: Bearer $(gcloud auth application-default print-access-token)" \
  -H "Content-Type: application/json" \
  "https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/endpoints/openapi/responses" \
  -d '{
    "model": "xai/grok-4.7",
    "input": "What is the second color?",
    "previous_response_id": "5f76a045-71d9-45af-8b07-1f2feae0675a",
    "store": true
  }'

第 2 輪的回覆範例:

{
  "background": false,
  "completed_at": 1793835029,
  "created_at": 1793835029,
  "error": null,
  "frequency_penalty": 0,
  "id": "ee8b6aa6-777e-4aa2-8db4-46bbfe84491b",
  "incomplete_details": null,
  "instructions": null,
  "max_output_tokens": null,
  "max_tool_calls": null,
  "metadata": {
    "system_fingerprint": "fp_grok47_0"
  },
  "model": "xai/grok-4.7",
  "object": "response",
  "output": [
    {
      "content": [
        {
          "annotations": [],
          "logprobs": [],
          "text": "amber",
          "type": "output_text"
        }
      ],
      "id": "msg_ee8b6aa6-777e-4aa2-8db4-46bbfe84491b",
      "role": "assistant",
      "status": "completed",
      "type": "message"
    }
  ],
  "parallel_tool_calls": true,
  "presence_penalty": 0,
  "previous_response_id": "5f76a045-71d9-45af-8b07-1f2feae0675a",
  "prompt_cache_key": null,
  "reasoning": {
    "effort": "high",
    "summary": "detailed"
  },
  "safety_identifier": null,
  "service_tier": "default",
  "status": "completed",
  "store": true,
  "temperature": 0.7,
  "text": {
    "format": {
      "type": "text"
    }
  },
  "tool_choice": "auto",
  "tools": [],
  "top_logprobs": 0,
  "top_p": 0.95,
  "truncation": "disabled",
  "usage": {
    "context_details": {
      "input_tokens": 239,
      "output_tokens": 41
    },
    "extra_properties": {
      "google": {
        "traffic_type": "ON_DEMAND"
      }
    },
    "input_tokens": 239,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "num_server_side_tools_used": 0,
    "num_sources_used": 0,
    "output_tokens": 41,
    "output_tokens_details": {
      "reasoning_tokens": 40
    },
    "total_tokens": 280
  },
  "user": null
}

取得回覆

您可以根據 ID 擷取先前生成的回覆。

Python

在試用這個範例之前,請先按照「使用用戶端程式庫的 Agent Platform 快速入門導覽課程」中的 Python 設定說明操作。

如要向 Agent Platform 進行驗證,請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。

執行這個範例前,請務必設定 OPENAI_BASE_URL 環境變數或 OAuth 憑證。詳情請參閱「驗證和憑證」。

import json
import google.auth
import google.auth.transport.requests
from openai import OpenAI
credentials, _ = google.auth.default(
    scopes=["https://www.googleapis.com/auth/cloud-platform"]
)
credentials.refresh(google.auth.transport.requests.Request())
client = OpenAI(
    base_url="https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/endpoints/openapi",
    api_key=credentials.token,
)
response_id = "RESPONSE_ID"
retrieved_response = client.responses.retrieve(response_id)
print(json.dumps(retrieved_response.model_dump(), indent=2))
  • PROJECT_ID: Google Cloud 專案 ID。
  • RESPONSE_ID:要擷取的回應 ID。

回應範例:

{
  "background": false,
  "completed_at": 1793834418,
  "created_at": 1793834418,
  "error": null,
  "frequency_penalty": 0,
  "id": "5f76a045-71d9-45af-8b07-1f2feae0675a",
  "incomplete_details": null,
  "instructions": null,
  "max_output_tokens": null,
  "max_tool_calls": null,
  "metadata": {
    "system_fingerprint": "fp_grok47_0"
  },
  "model": "xai/grok-4.7",
  "object": "response",
  "output": [
    {
      "content": [
        {
          "annotations": [],
          "logprobs": [],
          "text": "cerulean amber violet",
          "type": "output_text"
        }
      ],
      "id": "msg_5f76a045-71d9-45af-8b07-1f2feae0675a",
      "role": "assistant",
      "status": "completed",
      "type": "message"
    }
  ],
  "parallel_tool_calls": true,
  "presence_penalty": 0,
  "previous_response_id": null,
  "prompt_cache_key": null,
  "reasoning": {
    "effort": "high",
    "summary": "detailed"
  },
  "safety_identifier": null,
  "service_tier": "default",
  "status": "completed",
  "store": true,
  "temperature": 0.7,
  "text": {
    "format": {
      "type": "text"
    }
  },
  "tool_choice": "auto",
  "tools": [],
  "top_logprobs": 0,
  "top_p": 0.95,
  "truncation": "disabled",
  "usage": {
    "context_details": {
      "input_tokens": 220,
      "output_tokens": 144
    },
    "extra_properties": {
      "google": {
        "traffic_type": "ON_DEMAND"
      }
    },
    "input_tokens": 220,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "num_server_side_tools_used": 0,
    "num_sources_used": 0,
    "output_tokens": 144,
    "output_tokens_details": {
      "reasoning_tokens": 139
    },
    "total_tokens": 364
  },
  "user": null
}

REST

設定環境後,您可以使用 REST 測試文字提示詞。下列範例會將要求傳送至發布者模型端點。

使用任何要求資料之前,請先修改下列項目的值:

  • PROJECT_ID: Google Cloud 專案 ID。
  • RESPONSE_ID:要擷取的回應 ID。

HTTP 方法和網址:

GET https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/endpoints/openapi/responses/RESPONSE_ID

如要傳送要求,請選擇以下其中一個選項:

curl

執行下列指令:

curl -X GET \
-H "Authorization: Bearer $(gcloud auth application-default print-access-token)" \
"https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/endpoints/openapi/responses/RESPONSE_ID"

PowerShell

執行下列指令:

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

Invoke-WebRequest `
-Method GET `
-Headers $headers `
-Uri "https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/endpoints/openapi/responses/RESPONSE_ID" | Select-Object -Expand Content

以下範例顯示完整的 curl 要求:

curl -H "Authorization: Bearer $(gcloud auth application-default print-access-token)" \
  -H "Content-Type: application/json" \
  "https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/endpoints/openapi/responses/5f76a045-71d9-45af-8b07-1f2feae0675a"

回應範例:

{
  "background": false,
  "completed_at": 1793834418,
  "created_at": 1793834418,
  "error": null,
  "frequency_penalty": 0,
  "id": "5f76a045-71d9-45af-8b07-1f2feae0675a",
  "incomplete_details": null,
  "instructions": null,
  "max_output_tokens": null,
  "max_tool_calls": null,
  "metadata": {
    "system_fingerprint": "fp_grok47_0"
  },
  "model": "xai/grok-4.7",
  "object": "response",
  "output": [
    {
      "content": [
        {
          "annotations": [],
          "logprobs": [],
          "text": "cerulean amber violet",
          "type": "output_text"
        }
      ],
      "id": "msg_5f76a045-71d9-45af-8b07-1f2feae0675a",
      "role": "assistant",
      "status": "completed",
      "type": "message"
    }
  ],
  "parallel_tool_calls": true,
  "presence_penalty": 0,
  "previous_response_id": null,
  "prompt_cache_key": null,
  "reasoning": {
    "effort": "high",
    "summary": "detailed"
  },
  "safety_identifier": null,
  "service_tier": "default",
  "status": "completed",
  "store": true,
  "temperature": 0.7,
  "text": {
    "format": {
      "type": "text"
    }
  },
  "tool_choice": "auto",
  "tools": [],
  "top_logprobs": 0,
  "top_p": 0.95,
  "truncation": "disabled",
  "usage": {
    "context_details": {
      "input_tokens": 220,
      "output_tokens": 144
    },
    "extra_properties": {
      "google": {
        "traffic_type": "ON_DEMAND"
      }
    },
    "input_tokens": 220,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "num_server_side_tools_used": 0,
    "num_sources_used": 0,
    "output_tokens": 144,
    "output_tokens_details": {
      "reasoning_tokens": 139
    },
    "total_tokens": 364
  },
  "user": null
}

刪除回覆

您可以依 ID 刪除先前生成的回覆。

刪除回覆後,您就無法擷取該回覆,也無法在新要求中將其 ID 用作 previous_response_id。刪除回覆不會從同一對話的後續回覆中移除其內容:透過 previous_response_id 參照該回覆的每個回覆都會保留該內容做為背景資訊,直到您也刪除該回覆為止。如要移除整個對話,請刪除其中所有儲存的回覆。

Python

在試用這個範例之前,請先按照「使用用戶端程式庫的 Agent Platform 快速入門導覽課程」中的 Python 設定說明操作。

如要向 Agent Platform 進行驗證,請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。

執行這個範例前,請務必設定 OPENAI_BASE_URL 環境變數或 OAuth 憑證。詳情請參閱「驗證和憑證」。

import google.auth
import google.auth.transport.requests
from openai import OpenAI
credentials, _ = google.auth.default(
    scopes=["https://www.googleapis.com/auth/cloud-platform"]
)
credentials.refresh(google.auth.transport.requests.Request())
client = OpenAI(
    base_url="https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/endpoints/openapi",
    api_key=credentials.token,
)
response_id = "RESPONSE_ID"
delete_response = client.responses.delete(response_id)
print(delete_response)
  • PROJECT_ID: Google Cloud 專案 ID。
  • RESPONSE_ID:要刪除的回覆 ID。

回應範例:

{
  "deleted": true,
  "id": "5f76a045-71d9-45af-8b07-1f2feae0675a",
  "object": "response"
}

REST

設定環境後,您可以使用 REST 測試文字提示詞。下列範例會將要求傳送至發布者模型端點。

使用任何要求資料之前,請先修改下列項目的值:

  • PROJECT_ID: Google Cloud 專案 ID。
  • RESPONSE_ID:要刪除的回覆 ID。

HTTP 方法和網址:

DELETE https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/endpoints/openapi/responses/RESPONSE_ID

如要傳送要求,請選擇以下其中一個選項:

curl

執行下列指令:

curl -X DELETE \
-H "Authorization: Bearer $(gcloud auth application-default print-access-token)" \
"https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/endpoints/openapi/responses/RESPONSE_ID"

PowerShell

執行下列指令:

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

Invoke-WebRequest `
-Method DELETE `
-Headers $headers `
-Uri "https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/endpoints/openapi/responses/RESPONSE_ID" | Select-Object -Expand Content

以下範例顯示完整的 curl 要求:

curl -X DELETE \
  -H "Authorization: Bearer $(gcloud auth application-default print-access-token)" \
  -H "Content-Type: application/json" \
  "https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/endpoints/openapi/responses/5f76a045-71d9-45af-8b07-1f2feae0675a"

回應範例:

{
  "deleted": true,
  "id": "5f76a045-71d9-45af-8b07-1f2feae0675a",
  "object": "response"
}

後續步驟