# 实时 ChatGPT LLM 响应

**API:** Data API

**Endpoint:** `POST /v1/beta/dataforseo/ai_optimization/chat_gpt/llm_responses/live`

**Tags:** DataForSEO

向 ChatGPT 模型发送 `user_prompt` 并同步返回其回复。`model_name` 用于选择模型——参见 `get_dataforseo_ai_chat_gpt_llm_responses_models`，未列出的名称会被直接拒绝。`max_output_tokens`、`temperature` 和 `top_p` 的行为与供应商自有 API 一致，`web_search` 或 `force_web_search` 可让它浏览网页。返回 `model_name`、`input_tokens`、`output_tokens`、`reasoning_tokens`、`web_search`、`money_spent`、`datetime`、`items` 和 `fan_out_queries`。读取响应中的 `money_spent` 即可知道一次提示词的实际成本。采用 DataForSEO 的信封结构：数据位于 `tasks[0].result`，结果状态位于 `tasks[0].status_code`——被拒绝的请求仍会返回 HTTP 200。⚠️ 这是通过数据提供方路由的通用 LLM 调用，不是 SEO 测量。如果你想了解 ChatGPT 如何向用户描述某个品牌，请改用 `post_dataforseo_ai_chat_gpt_llm_scraper_live` 复现消费者体验。

### 计费参考

- 计量方式：按上报的响应成本计量。
- 参考请求估算：0.0695 美元。
- 参考客户倍率：1.0。不得对已结算的客户金额再次应用。

仅供参考的元数据，不是账户报价、保证价格或消费上限。资源额度不同于 Felo 额度。最终扣费以 Felo 计费记录为准。

## Base URL

- `https://openapi.felo.ai`

## Authentication

- `FeloBearerAuth` (http bearer, bearer format Felo API Key)
- `FeloApiKey` (apiKey in header `X-API-Key`)

## Request body

Required: **no**

### application/json

Schema:

```json
{
  "type": "array",
  "items": {
    "type": [
      "object",
      "null"
    ],
    "oneOf": [
      {
        "type": "object",
        "properties": {
          "user_prompt": {
            "type": "string",
            "description": "<em>AI 模型的提示词</em><br><strong>必填字段</strong><br>要发送给 AI 模型的问题或任务；<br>在 <code>user_prompt</code> 字段中最多可指定 <strong>500 个字符</strong>"
          },
          "model_name": {
            "type": "string",
            "description": "<em>AI 模型名称</em><br><strong>必填字段</strong><br><code>model_name</code > 由实际模型名称和版本名称组成；<br>如果只指定基础模型名称，将默认设置其最新版本；<br>例如，指定 <code>gpt-4.1</code> 时，会自动将 <code>gpt-4.1-2025-04-14</code> 设为 <code>model_name</code>；<br>可单独向 <code>https://api.dataforseo.com/v3/ai_optimization/chat_gpt/llm_responses/models</code> 发起请求，获取可用 LLM 模型列表"
          },
          "max_output_tokens": {
            "type": [
              "integer",
              "null"
            ],
            "description": "<em>AI 响应中的最大 token 数</em><br>可选字段<br>推理模型（例如 <a href=\"/v3/ai_optimization/chat_gpt/llm_responses/models/\" target=\"_blank\">Models 端点</a>中 <code>reasoning</code> 为 <code>true</code>）的最小值：<code>1024</code>；<br>非推理模型的最小值：<code>16</code>；<br>最大值：<code>4096</code>；<br>默认值：<code>2048</code><br><strong>注意：</strong>如果将 <code>web_search</code> 设为 <code>true</code>，或请求中指定的是推理模型，输出 token 数可能超过指定的 <code>max_output_tokens</code> 上限"
          },
          "temperature": {
            "type": [
              "number",
              "null"
            ],
            "description": "<em>AI 响应的随机性</em><br>可选字段<br>值越高，输出越多样；<br>值越低，输出越集中；<br>最小值：<code>0</code><br>最大值：<code>2</code><br>默认值：<code>0.94</code><br><strong>注意：</strong>推理模型不支持"
          },
          "top_p": {
            "type": [
              "number",
              "null"
            ],
            "description": "<em>AI 响应的多样性</em><br>可选字段 <br>通过限制 token 选择来控制响应的多样性；<br>最小值：<code>0</code><br>最大值：<code>1</code> <br>默认值：<code>0.92</code><p><strong>注意：</strong>同一请求中 <code>top_p</code> 不能与 <code>temperature</code> 同时使用"
          },
          "web_search": {
            "type": [
              "boolean",
              "null"
            ],
            "description": "<em>启用网络搜索</em><br>可选字段<br>启用后，AI 模型可以访问并引用当前网络信息；<br>默认值：<code>false</code>；<br><strong>注意：</strong>支持 <code>web_search</code> 的模型列表请参阅 <a href=\"https://docs.dataforseo.com/v3/ai_optimization/chat_gpt/llm_responses/models/\">Models 端点</a>；"
          },
          "force_web_search": {
            "type": [
              "boolean",
              "null"
            ],
            "description": "<em>强制 AI 智能体使用网络搜索</em><br>可选字段<br>要启用此参数，还必须启用 <code>web_search</code>；<br>启用后，AI 模型会被强制访问并引用当前网络信息；<br>默认值：<code>false</code>；<br><strong>注意：</strong>即使参数设为 <code>true</code>，也不能保证响应中会引用网络来源 <br><strong>注意 2：</strong>推理模型不支持"
          },
          "web_search_country_iso_code": {
            "type": [
              "string",
              "null"
            ],
            "description": "<em>地点的 ISO 国家代码</em><br>可选字段<br>要启用此参数，还必须启用 <code>web_search</code>；<br>启用后，AI 模型将从你指定的国家/地区搜索网络；<br><strong>注意：</strong><code>o3-mini</code>、<code>o1-pro</code>、<code>o1</code> 模型不支持"
          },
          "web_search_city": {
            "type": [
              "string",
              "null"
            ],
            "description": "<em>地点的城市名称</em><br>可选字段<br><strong>注意：</strong><code>o3-mini</code>、<code>o1-pro</code>、<code>o1</code> 模型不支持"
          },
          "system_message": {
            "type": [
              "string",
              "null"
            ],
            "description": "<em>AI 行为指令</em><br>可选字段<br>定义 AI 的角色、语气或特定行为 <br>在 <code>system_message</code> 字段中最多可指定 <strong>500 个字符</strong>"
          },
          "message_chain": {
            "type": [
              "array",
              "null"
            ],
            "items": {
              "type": [
                "object",
                "null"
              ],
              "oneOf": [
                {
                  "type": "object",
                  "properties": {
                    "role": {
                      "type": [
                        "string",
                        "null"
                      ],
                      "description": "消息来源用户的角色"
                    },
                    "message": {
                      "type": [
                        "string",
                        "null"
                      ],
                      "description": "消息文本"
                    }
                  }
                }
              ]
            },
            "description": "对话历史\n可选字段\n表示此前对话轮次的消息对象数组；\n每个对象必须包含：\nrole 字符串，值为 user 或 ai 角色；\nmessage 字符串，包含消息内容（最多 500 个字符）；\n数组中最多可指定 10 个消息对象；\n注意：对于 Perplexity 模型，消息必须严格在 user 与 AI 角色之间交替（user → ai）；\n示例：\n\"message_chain\": [{\"role\":\"user\",\"message\":\"Hello, what’s up?\"},{\"role\":\"ai\",\"message\":\"Hello! I’m doing well, thank you. How can I assist you today?\"}]"
          },
          "tag": {
            "type": [
              "string",
              "null"
            ],
            "description": "<em>用户自定义任务标识符</em><br>可选字段<br><em>字符数上限为 255</em><br>可使用此参数标识任务，并将其与结果对应<br>可在响应的 <code>data</code> 对象中找到指定的 <code>tag</code> 值"
          }
        },
        "example": [
          {
            "system_message": "communicate as if we are in a business meeting",
            "message_chain": [
              {
                "role": "user",
                "message": "Hello, what’s up?"
              },
              {
                "role": "ai",
                "message": "Hello! I’m doing well, thank you. How can I assist you today? Are there any specific topics or projects you’d like to discuss in our meeting?"
              }
            ],
            "max_output_tokens": 200,
            "temperature": 0.3,
            "top_p": 0.5,
            "model_name": "gpt-4.1-mini",
            "web_search": true,
            "web_search_country_iso_code": "FR",
            "web_search_city": "Paris",
            "user_prompt": "provide information on how relevant the amusement park business is in France now"
          }
        ]
      }
    ]
  },
  "example": [
    {
      "system_message": "communicate as if we are in a business meeting",
      "message_chain": [
        {
          "role": "user",
          "message": "Hello, what’s up?"
        },
        {
          "role": "ai",
          "message": "Hello! I’m doing well, thank you. How can I assist you today? Are there any specific topics or projects you’d like to discuss in our meeting?"
        }
      ],
      "max_output_tokens": 200,
      "temperature": 0.3,
      "top_p": 0.5,
      "model_name": "gpt-4.1-mini",
      "web_search": true,
      "web_search_country_iso_code": "FR",
      "web_search_city": "Paris",
      "user_prompt": "provide information on how relevant the amusement park business is in France now"
    }
  ]
}
```

## Responses

### 200 — 操作成功

Headers:
- `X-Request-Id` (string) — 联系 Felo 支持时需提供的请求标识符。

**application/json**

Schema: object | null

```json
{
  "type": [
    "object",
    "null"
  ],
  "oneOf": [
    {
      "$ref": "#/components/schemas/Response36Afe1097B20_AiOptimizationChatGptLlmResponsesLiveResponseInfo"
    }
  ]
}
```

### 400 — 无法处理该请求。请检查请求参数。

### 401 — 需要有效的 Felo API 密钥。

### 402 — 由于未满足计费要求，请求无法继续。

### 403 — 该账户无权执行此操作。

### 429 — 已达到请求或支出限额。

### 502 — 服务无法完成该请求。

### 503 — API 或计费服务暂时不可用。

### 504 — 服务在处理请求时超时。

### default — 错误响应；上游透传响应可能采用提供方格式

**application/json**

Schema:

```json
{}
```

## Schema definitions

### Response36Afe1097B20_AiOptimizationChatGptLlmResponsesLiveResponseInfo

`#/components/schemas/Response36Afe1097B20_AiOptimizationChatGptLlmResponsesLiveResponseInfo`

```json
{
  "type": "object",
  "allOf": [
    {
      "$ref": "#/components/schemas/Response36Afe1097B20_BaseResponseInfo"
    },
    {
      "type": "object",
      "properties": {
        "tasks": {
          "type": [
            "array",
            "null"
          ],
          "items": {
            "type": [
              "object",
              "null"
            ],
            "oneOf": [
              {
                "$ref": "#/components/schemas/Response36Afe1097B20_AiOptimizationChatGptLlmResponsesLiveTaskInfo"
              }
            ]
          },
          "description": "<em>任务数组</em>"
        }
      }
    }
  ]
}
```

### Response36Afe1097B20_AiOptimizationChatGptLlmResponsesLiveResultInfo

`#/components/schemas/Response36Afe1097B20_AiOptimizationChatGptLlmResponsesLiveResultInfo`

```json
{
  "type": "object",
  "properties": {
    "model_name": {
      "type": [
        "string",
        "null"
      ],
      "description": "<em>所用 AI 模型的名称</em>"
    },
    "input_tokens": {
      "type": [
        "integer",
        "null"
      ],
      "description": "<em>输入中的 token 数</em><br>处理的 token 总数"
    },
    "output_tokens": {
      "type": [
        "integer",
        "null"
      ],
      "description": "<em>输出中的 token 数</em><br>AI 响应中生成的 token 总数"
    },
    "reasoning_tokens": {
      "type": [
        "integer",
        "null"
      ],
      "description": "<em>推理 token 数</em><br>用于生成推理内容的 token 总数"
    },
    "web_search": {
      "type": [
        "boolean",
        "null"
      ],
      "description": "<em>表示是否使用了网络搜索</em>"
    },
    "money_spent": {
      "type": [
        "number",
        "null"
      ],
      "description": "<em>AI token 成本（美元）</em><br>第三方 AI 模型提供商按其<a href=\"https://platform.openai.com/docs/pricing\" target=\"_blank\">定价</a>收取的费用"
    },
    "datetime": {
      "type": [
        "string",
        "null"
      ],
      "description": "<em>收到结果的日期和时间</em><br>采用 UTC 格式：“yyyy-mm-dd hh-mm-ss +00:00”<br>示例：<br><code class=\"long-string\">2019-11-15 12:57:46 +00:00</code>"
    },
    "items": {
      "type": [
        "array",
        "null"
      ],
      "items": {
        "type": [
          "object",
          "null"
        ],
        "oneOf": [
          {
            "$ref": "#/components/schemas/Response36Afe1097B20_BaseAiOptimizationLlmResponseElementItem"
          }
        ]
      },
      "description": "<em>响应条目数组</em><br>包含结构化的 AI 响应数据"
    },
    "fan_out_queries": {
      "type": [
        "array",
        "null"
      ],
      "items": {
        "type": [
          "string",
          "null"
        ]
      },
      "description": "<em>扇出查询数组</em><br>包含从主查询派生出的相关搜索查询，以提供更全面的回答"
    }
  }
}
```

### Response36Afe1097B20_AiOptimizationChatGptLlmResponsesLiveTaskInfo

`#/components/schemas/Response36Afe1097B20_AiOptimizationChatGptLlmResponsesLiveTaskInfo`

```json
{
  "type": "object",
  "allOf": [
    {
      "$ref": "#/components/schemas/Response36Afe1097B20_BaseResponseTaskInfo"
    },
    {
      "type": "object",
      "properties": {
        "result": {
          "type": [
            "array",
            "null"
          ],
          "items": {
            "type": [
              "object",
              "null"
            ],
            "oneOf": [
              {
                "$ref": "#/components/schemas/Response36Afe1097B20_AiOptimizationChatGptLlmResponsesLiveResultInfo"
              }
            ]
          },
          "description": "<em>结果数组</em>"
        }
      }
    }
  ]
}
```

### Response36Afe1097B20_BaseAiOptimizationLlmResponseElementItem

`#/components/schemas/Response36Afe1097B20_BaseAiOptimizationLlmResponseElementItem`

```json
{
  "type": "object",
  "properties": {
    "type": {
      "type": [
        "string",
        "null"
      ],
      "description": "元素类型"
    }
  },
  "additionalProperties": false,
  "discriminator": {
    "propertyName": "type",
    "mapping": {
      "reasoning": "#/components/schemas/Response36Afe1097B20_ReasoningAiOptimizationLlmResponseElementItem",
      "message": "#/components/schemas/Response36Afe1097B20_MessageAiOptimizationLlmResponseElementItem"
    }
  }
}
```

### Response36Afe1097B20_BaseResponseInfo

`#/components/schemas/Response36Afe1097B20_BaseResponseInfo`

```json
{
  "properties": {
    "version": {
      "type": [
        "string",
        "null"
      ],
      "description": "API 的当前版本"
    },
    "status_code": {
      "type": [
        "integer",
        "null"
      ],
      "description": "通用状态码\n完整响应码列表见此处"
    },
    "status_message": {
      "type": [
        "string",
        "null"
      ],
      "description": "通用信息性消息\n完整的一般信息性消息列表见此处"
    },
    "time": {
      "type": [
        "string",
        "null"
      ],
      "description": "总执行时间，秒"
    },
    "cost": {
      "type": [
        "number",
        "null"
      ],
      "description": "任务总费用，美元",
      "format": "double"
    },
    "tasks_count": {
      "type": [
        "integer",
        "null"
      ],
      "description": "tasks 数组中的任务数",
      "format": "int64"
    },
    "tasks_error": {
      "type": [
        "integer",
        "null"
      ],
      "description": "tasks 数组中返回错误的任务数",
      "format": "int64"
    }
  }
}
```

### Response36Afe1097B20_BaseResponseTaskInfo

`#/components/schemas/Response36Afe1097B20_BaseResponseTaskInfo`

```json
{
  "properties": {
    "id": {
      "type": [
        "string",
        "null"
      ],
      "description": "任务标识符\n我们系统中 UUID 格式的唯一任务标识符"
    },
    "status_code": {
      "type": [
        "integer",
        "null"
      ],
      "description": "任务的状态码\n由 DataForSEO 生成，范围如下：10000-60000\n完整响应码列表见此处"
    },
    "status_message": {
      "type": [
        "string",
        "null"
      ],
      "description": "任务的信息性消息\n完整的一般信息性消息列表见此处"
    },
    "time": {
      "type": [
        "string",
        "null"
      ],
      "description": "执行时间，秒"
    },
    "cost": {
      "type": [
        "number",
        "null"
      ],
      "description": "任务总费用，美元",
      "format": "double"
    },
    "result_count": {
      "type": [
        "integer",
        "null"
      ],
      "description": "result 数组中的元素数",
      "format": "int64"
    },
    "path": {
      "type": [
        "array",
        "null"
      ],
      "items": {
        "type": [
          "string",
          "null"
        ]
      },
      "description": "URL 路径"
    },
    "data": {
      "type": [
        "object",
        "null"
      ],
      "additionalProperties": {
        "type": [
          "object",
          "null"
        ]
      },
      "description": "包含你在 POST 请求中指定的相同参数"
    }
  }
}
```