Call Responses API

Gemini Enterprise Agent Platform 上的 XAI Grok 模型支持用于生成回答的 Responses API。

本页介绍了如何使用 Responses API 调用 Grok 模型。

准备工作

如需将 Grok 模型与 Gemini Enterprise Agent Platform 搭配使用，您必须执行以下步骤。必须启用 Gemini Enterprise Agent Platform API (aiplatform.googleapis.com)。

  1. 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

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

  3. 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

对 Responses API 进行无状态调用

如需使用无状态功能，请在请求中将 store 明确设置为 false（或在 Python 中设置为 False）。store 的默认值为 true。

对 Responses API 进行非流式调用

以下示例展示了如何对 Responses API 进行非流式调用：

Python

试用此示例之前，请按照《Agent Platform 快速入门：使用客户端库》中的 Python 设置说明进行操作。

如需向代理平台进行身份验证，请设置应用默认凭据。 如需了解详情，请参阅为本地开发环境设置身份验证。

在运行此示例之前，请务必设置 OPENAI_BASE_URL 环境变量或设置 OAuth 凭据。如需了解详情，请参阅身份验证和凭证。

from openai import OpenAI
client = OpenAI()
response = client.responses.create(
    model="MODEL",
    input="INPUT",
    max_output_tokens=MAX_OUTPUT_TOKENS,
    stream=False,
    store=False,
)
print(response)
  • MODEL：您要使用的模型名称，例如 xai/grok-4.20-reasoning。
  • INPUT：模型的提示或输入。
  • MAX_OUTPUT_TOKENS：回答中可生成的词元数量上限。词元约为 4 个字符。100 个词元对应大约 60-80 个单词。

    指定较低的值可获得较短的回答，指定较高的值可获得可能较长的回答。

REST

设置环境后，您可以使用 REST 测试文本提示。以下示例会向发布方模型端点发送请求。

在使用任何请求数据之前，请先进行以下替换：

  • PROJECT_ID：您的 Google Cloud 项目 ID。
  • MODEL：您要使用的模型名称，例如 xai/grok-4.20-reasoning。
  • INPUT：模型的提示或输入。
  • MAX_OUTPUT_TOKENS：回答中可生成的词元数量上限。词元约为 4 个字符。100 个词元对应大约 60-80 个单词。

    指定较低的值可获得较短的回答，指定较高的值可获得可能较长的回答。

HTTP 方法和网址：

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

请求 JSON 正文： 

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

如需发送请求，请选择以下方式之一：

curl

将请求正文保存在名为 request.json 的文件中，然后执行以下命令： 

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth 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

将请求正文保存在名为 request.json 的文件中，然后执行以下命令： 

$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://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/endpoints/openapi/responses" | Select-Object -Expand Content

以下示例展示了完整的 curl 请求：

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-4.20-reasoning",
    "input": "Explain black holes in one short sentence.",
    "max_output_tokens": 100,
    "stream": false,
    "store": false
  }'

根据 Responses API 定义，非流式传输响应将包含唯一 ID、模型元数据、使用情况统计信息以及包含生成的文本的输出数组。

{
  "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
}

向 Responses API 发出流式传输调用

以下示例展示了如何对 Responses API 进行流式调用：

Python

试用此示例之前，请按照《Agent Platform 快速入门：使用客户端库》中的 Python 设置说明进行操作。

如需向代理平台进行身份验证，请设置应用默认凭据。 如需了解详情，请参阅为本地开发环境设置身份验证。

在运行此示例之前，请务必设置 OPENAI_BASE_URL 环境变量或设置 OAuth 凭据。如需了解详情，请参阅身份验证和凭证。

from openai import OpenAI
client = OpenAI()
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="")
  • MODEL：您要使用的模型名称，例如 xai/grok-4.20-reasoning。
  • INPUT：模型的提示或输入。
  • MAX_OUTPUT_TOKENS：回答中可生成的词元数量上限。词元约为 4 个字符。100 个词元对应大约 60-80 个单词。

    指定较低的值可获得较短的回答，指定较高的值可获得可能较长的回答。

REST

设置环境后，您可以使用 REST 测试文本提示。以下示例会向发布方模型端点发送请求。

在使用任何请求数据之前，请先进行以下替换：

  • PROJECT_ID：您的 Google Cloud 项目 ID。
  • MODEL：您要使用的模型名称，例如 xai/grok-4.20-reasoning。
  • INPUT：模型的提示或输入。
  • MAX_OUTPUT_TOKENS：回答中可生成的词元数量上限。词元约为 4 个字符。100 个词元对应大约 60-80 个单词。

    指定较低的值可获得较短的回答，指定较高的值可获得可能较长的回答。

HTTP 方法和网址：

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

请求 JSON 正文： 

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

如需发送请求，请选择以下方式之一：

curl

将请求正文保存在名为 request.json 的文件中，然后执行以下命令： 

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth 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

将请求正文保存在名为 request.json 的文件中，然后执行以下命令： 

$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://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/endpoints/openapi/responses" | Select-Object -Expand Content
 

向 Responses API 发出有状态调用

如需使用有状态功能，您必须配置Organization Policy Service以允许使用这些功能。具体而言，请通过将 publishers/xai/models/MODEL_NAME:stateful_responses_api 添加到允许的值（例如 publishers/xai/models/grok-4.20-reasoning:stateful_responses_api）来更新限制 constraints/vertexai.allowedPartnerModelFeatures。如需了解详情，请参阅控制模型访问权限。

Responses API 通过有状态请求支持多轮对话。默认情况下，store 设置为 true，这会启用有状态的响应。在有状态的对话中，您可以在 previous_response_id 字段中提供之前回答的 id，以引用之前的回答。

以下示例展示了使用 Responses API 进行的两轮对话：

第 1 轮：初始请求

在第一个回合中，发出将 store 设置为 true 的请求。您还可以省略 store 参数，因为 true 是默认值。

Python

试用此示例之前，请按照《Agent Platform 快速入门：使用客户端库》中的 Python 设置说明进行操作。

如需向代理平台进行身份验证，请设置应用默认凭据。 如需了解详情，请参阅为本地开发环境设置身份验证。

在运行此示例之前，请务必设置 OPENAI_BASE_URL 环境变量或设置 OAuth 凭据。如需了解详情，请参阅身份验证和凭证。

from openai import OpenAI
client = OpenAI()
response = client.responses.create(
    model="MODEL",
    input="randomly pick 3 colors, just return the words of the colors",
)
print(response)
  • MODEL：您要使用的模型名称，例如 xai/grok-4.20-reasoning。

REST

设置环境后，您可以使用 REST 测试文本提示。以下示例会向发布方模型端点发送请求。

在使用任何请求数据之前，请先进行以下替换：

  • PROJECT_ID：您的 Google Cloud 项目 ID。
  • MODEL：您要使用的模型名称，例如 xai/grok-4.20-reasoning。

HTTP 方法和网址：

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

请求 JSON 正文： 

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

如需发送请求，请选择以下方式之一：

curl

将请求正文保存在名为 request.json 的文件中，然后执行以下命令： 

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth 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

将请求正文保存在名为 request.json 的文件中，然后执行以下命令： 

$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://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/endpoints/openapi/responses" | Select-Object -Expand Content

以下示例展示了完整的 curl 请求：

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-4.20-reasoning",
    "input": "randomly pick 3 colors, just return the words of the colors"
  }'

第 1 轮的回答示例：

{
  "background": false,
  "completed_at": 1780435592,
  "created_at": 1780435591,
  "error": null,
  "frequency_penalty": 0,
  "id": "hkofavjWJuaRifEPntCBiA8",
  "incomplete_details": null,
  "instructions": null,
  "max_output_tokens": null,
  "max_tool_calls": null,
  "metadata": {
    "system_fingerprint": "fp_39c5j0a3e9"
  },
  "model": "xai/grok-4.20-reasoning",
  "object": "response",
  "output": [
    {
      "content": [
        {
          "annotations": [],
          "logprobs": [],
          "text": "violet teal crimson",
          "type": "output_text"
        }
      ],
      "id": "msg_hkofavjWJuaRifEPntCBiA8",
      "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": true,
  "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": 343,
    "input_tokens_details": {
      "cached_tokens": 320
    },
    "num_server_side_tools_used": 0,
    "num_sources_used": 0,
    "output_tokens": 389,
    "output_tokens_details": {
      "reasoning_tokens": 386
    },
    "total_tokens": 732
  },
  "user": null
}

第 2 轮：跟进请求

在第二轮对话中，在 previous_response_id 参数中引用上一个回答中的 ID。

Python

试用此示例之前，请按照《Agent Platform 快速入门：使用客户端库》中的 Python 设置说明进行操作。

如需向代理平台进行身份验证，请设置应用默认凭据。 如需了解详情，请参阅为本地开发环境设置身份验证。

在运行此示例之前，请务必设置 OPENAI_BASE_URL 环境变量或设置 OAuth 凭据。如需了解详情，请参阅身份验证和凭证。

from openai import OpenAI
client = OpenAI()
response = client.responses.create(
    model="MODEL",
    input="What is the second color?",
    previous_response_id="PREVIOUS_RESPONSE_ID",
)
print(response)
  • MODEL：您要使用的模型名称，例如 xai/grok-4.20-reasoning。
  • PREVIOUS_RESPONSE_ID：用于继续对话的上一条响应的 ID。

REST

设置环境后，您可以使用 REST 测试文本提示。以下示例会向发布方模型端点发送请求。

在使用任何请求数据之前，请先进行以下替换：

  • PROJECT_ID：您的 Google Cloud 项目 ID。
  • MODEL：您要使用的模型名称，例如 xai/grok-4.20-reasoning。
  • PREVIOUS_RESPONSE_ID：上一个响应的 ID。

HTTP 方法和网址：

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

请求 JSON 正文： 

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

如需发送请求，请选择以下方式之一：

curl

将请求正文保存在名为 request.json 的文件中，然后执行以下命令： 

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth 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

将请求正文保存在名为 request.json 的文件中，然后执行以下命令： 

$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://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/endpoints/openapi/responses" | Select-Object -Expand Content

以下示例展示了完整的 curl 请求：

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-4.20-reasoning",
    "input": "What is the second color?",
    "previous_response_id": "hkofavjWJuaRifEPntCBiA8"
  }'

第 2 轮的回答示例：

{
  "background": false,
  "completed_at": 1780436062,
  "created_at": 1780436060,
  "error": null,
  "frequency_penalty": 0,
  "id": "VkwfatGAFY2CifEPvPu-iQM",
  "incomplete_details": null,
  "instructions": null,
  "max_output_tokens": null,
  "max_tool_calls": null,
  "metadata": {
    "system_fingerprint": "fp_39c5j0a3e9"
  },
  "model": "xai/grok-4.20-reasoning",
  "object": "response",
  "output": [
    {
      "content": [
        {
          "annotations": [],
          "logprobs": [],
          "text": "teal",
          "type": "output_text"
        }
      ],
      "id": "msg_VkwfatGAFY2CifEPvPu-iQM",
      "role": "assistant",
      "status": "completed",
      "type": "message"
    }
  ],
  "parallel_tool_calls": true,
  "presence_penalty": 0,
  "previous_response_id": "hkofavjWJuaRifEPntCBiA8",
  "prompt_cache_key": null,
  "reasoning": {
    "effort": "medium",
    "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": {
    "extra_properties": {
      "google": {
        "traffic_type": "ON_DEMAND"
      }
    },
    "input_tokens": 360,
    "input_tokens_details": {
      "cached_tokens": 320
    },
    "num_server_side_tools_used": 0,
    "num_sources_used": 0,
    "output_tokens": 314,
    "output_tokens_details": {
      "reasoning_tokens": 312
    },
    "total_tokens": 674
  },
  "user": null
}

获取回答

您可以按 ID 检索之前生成的回答。

Python

试用此示例之前，请按照《Agent Platform 快速入门：使用客户端库》中的 Python 设置说明进行操作。

如需向代理平台进行身份验证，请设置应用默认凭据。 如需了解详情，请参阅为本地开发环境设置身份验证。

在运行此示例之前，请务必设置 OPENAI_BASE_URL 环境变量或设置 OAuth 凭据。如需了解详情，请参阅身份验证和凭证。

import json
import openai
v1beta1_client = openai.OpenAI(
    base_url=f"https://aiplatform.googleapis.com/v1beta1/projects/{project_id}/locations/global/endpoints/openapi",
    api_key=credentials.token,
)



response_id = "RESPONSE_ID"
retrieved_response = v1beta1_client.responses.retrieve(response_id)



print(json.dumps(retrieved_response.model_dump(), indent=2))
  • RESPONSE_ID：要检索的回答的 ID。

示例响应：

{
  "id": "pfgxarvYI4C0hMIP-qns4AU",
  "created_at": 1781659813.0,
  "error": null,
  "incomplete_details": null,
  "instructions": null,
  "metadata": {
    "system_fingerprint": "fp_39c5j0a3e9"
  },
  "model": "xai/grok-4.20-reasoning",
  "object": "response",
  "output": [
    {
      "id": "msg_pfgxarvYI4C0hMIP-qns4AU",
      "content": [
        {
          "annotations": [],
          "text": "Once upon a twilight meadow, a gentle unicorn named Luna followed a trail of glowing fireflies to her mossy bed beneath the silver moon, where she dreamed of rainbow bridges and endless starlit gallops.",
          "type": "output_text",
          "logprobs": []
        }
      ],
      "role": "assistant",
      "status": "completed",
      "type": "message",
      "phase": null
    }
  ],
  "parallel_tool_calls": true,
  "temperature": 0.7,
  "tool_choice": "auto",
  "tools": [],
  "top_p": 0.95,
  "background": false,
  "completed_at": 1781659815.0,
  "conversation": null,
  "max_output_tokens": null,
  "max_tool_calls": null,
  "moderation": null,
  "previous_response_id": null,
  "prompt": null,
  "prompt_cache_key": null,
  "prompt_cache_retention": null,
  "reasoning": {
    "effort": "medium",
    "generate_summary": null,
    "summary": "detailed"
  },
  "safety_identifier": null,
  "service_tier": "default",
  "status": "completed",
  "text": {
    "format": {
      "type": "text"
    },
    "verbosity": null
  },
  "top_logprobs": 0,
  "truncation": "disabled",
  "usage": {
    "input_tokens": 340,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "output_tokens": 375,
    "output_tokens_details": {
      "reasoning_tokens": 334
    },
    "total_tokens": 715,
    "extra_properties": {
      "google": {
        "traffic_type": "ON_DEMAND"
      }
    },
    "num_server_side_tools_used": 0,
    "num_sources_used": 0
  },
  "user": null,
  "frequency_penalty": 0,
  "presence_penalty": 0,
  "store": true
}

REST

设置环境后，您可以使用 REST 测试文本提示。以下示例会向发布方模型端点发送请求。

在使用任何请求数据之前，请先进行以下替换：

  • PROJECT_ID：您的 Google Cloud 项目 ID。
  • RESPONSE_ID：要检索的回答的 ID。

HTTP 方法和网址：

GET https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/endpoints/openapi/responses/RESPONSE_ID

如需发送请求，请选择以下方式之一：

curl

执行以下命令：

curl -X GET \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     "https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/endpoints/openapi/responses/RESPONSE_ID"

PowerShell

执行以下命令：

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

Invoke-WebRequest `
    -Method GET `
    -Headers $headers `
    -Uri "https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/endpoints/openapi/responses/RESPONSE_ID" | Select-Object -Expand Content

以下示例展示了完整的 curl 请求：

curl -H "Authorization: Bearer $(gcloud auth application-default print-access-token)" \
  -H "Content-Type: application/json" \
  "https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/endpoints/openapi/responses/VkwfatGAFY2CifEPvPu-iQM"

示例响应：

{
  "background": false,
  "completed_at": 1780436062,
  "created_at": 1780436060,
  "error": null,
  "frequency_penalty": 0,
  "id": "VkwfatGAFY2CifEPvPu-iQM",
  "incomplete_details": null,
  "instructions": null,
  "max_output_tokens": null,
  "max_tool_calls": null,
  "metadata": {
    "system_fingerprint": "fp_39c5j0a3e9"
  },
  "model": "xai/grok-4.20-reasoning",
  "object": "response",
  "output": [
    {
      "content": [
        {
          "annotations": [],
          "logprobs": [],
          "text": "teal",
          "type": "output_text"
        }
      ],
      "id": "msg_VkwfatGAFY2CifEPvPu-iQM",
      "role": "assistant",
      "status": "completed",
      "type": "message"
    }
  ],
  "parallel_tool_calls": true,
  "presence_penalty": 0,
  "previous_response_id": "hkofavjWJuaRifEPntCBiA8",
  "prompt_cache_key": null,
  "reasoning": {
    "effort": "medium",
    "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": {
    "extra_properties": {
      "google": {
        "traffic_type": "ON_DEMAND"
      }
    },
    "input_tokens": 360,
    "input_tokens_details": {
      "cached_tokens": 320
    },
    "num_server_side_tools_used": 0,
    "num_sources_used": 0,
    "output_tokens": 314,
    "output_tokens_details": {
      "reasoning_tokens": 312
    },
    "total_tokens": 674
  },
  "user": null
}

删除回答

您可以按 ID 删除之前生成的回答。

Python

试用此示例之前，请按照《Agent Platform 快速入门：使用客户端库》中的 Python 设置说明进行操作。

如需向代理平台进行身份验证，请设置应用默认凭据。 如需了解详情，请参阅为本地开发环境设置身份验证。

在运行此示例之前，请务必设置 OPENAI_BASE_URL 环境变量或设置 OAuth 凭据。如需了解详情，请参阅身份验证和凭证。

import openai
v1beta1_client = openai.OpenAI(
    base_url=f"https://aiplatform.googleapis.com/v1beta1/projects/{project_id}/locations/global/endpoints/openapi",
    api_key=credentials.token,
)



response_id = "RESPONSE_ID"
delete_response = v1beta1_client.responses.delete(response_id)



print(delete_response)
  • RESPONSE_ID：要删除的回答的 ID。

示例响应：

{
  "deleted": true,
  "id": "TekCarmCCOPYyOgPnrWSgAY",
  "object": "response"
}

REST

设置环境后，您可以使用 REST 测试文本提示。以下示例会向发布方模型端点发送请求。

在使用任何请求数据之前，请先进行以下替换：

  • PROJECT_ID：您的 Google Cloud 项目 ID。
  • RESPONSE_ID：要删除的回答的 ID。

HTTP 方法和网址：

DELETE https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/endpoints/openapi/responses/RESPONSE_ID

如需发送请求，请选择以下方式之一：

curl

执行以下命令：

curl -X DELETE \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     "https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/endpoints/openapi/responses/RESPONSE_ID"

PowerShell

执行以下命令：

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

Invoke-WebRequest `
    -Method DELETE `
    -Headers $headers `
    -Uri "https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/endpoints/openapi/responses/RESPONSE_ID" | Select-Object -Expand Content

以下示例展示了完整的 curl 请求：

curl -X DELETE 

  -H "Authorization: Bearer $(gcloud auth application-default print-access-token)" 

  -H "Content-Type: application/json" 

  "https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/endpoints/openapi/responses/TekCarmCCOPYyOgPnrWSgAY"

示例响应：

{
  "deleted": true,
  "id": "TekCarmCCOPYyOgPnrWSgAY",
  "object": "response"
}

后续步骤