# 实时 Perplexity LLM 响应
**API:** Data API
**Endpoint:** `POST /v1/beta/dataforseo/ai_optimization/perplexity/llm_responses/live`
**Tags:** DataForSEO
向 Perplexity 模型发送 `user_prompt` 并同步返回其回复。`model_name` 必须来自 `get_dataforseo_ai_perplexity_llm_responses_models`——`sonar`、`sonar-pro` 和 `sonar-reasoning-pro`。`web_search_country_iso_code` 可限定搜索范围，其他三家供应商不提供此功能。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。
### 计费参考
- 计量方式：按上报的响应成本计量。
- 参考请求估算：0.0163 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": "AI 模型的提示词
必填字段
要发送给 AI 模型的问题或任务；
在 user_prompt 字段中最多可指定 500 个字符"
},
"model_name": {
"type": "string",
"description": "AI 模型名称
必填字段
model_name 由实际模型名称和版本名称组成；
如果只指定基础模型名称，将默认设置其最新版本；
可单独向以下端点发起请求，获取可用 LLM 模型列表：https://api.dataforseo.com/v3/ai_optimization/perplexity/llm_responses/models"
},
"max_output_tokens": {
"type": [
"integer",
"null"
],
"description": "AI 响应中的最大 token 数
可选字段
最小值：1
最大值：4096；
默认值：2048；
注意：如果请求中指定的是推理模型，输出 token 数可能超过指定的 max_output_tokens 上限"
},
"temperature": {
"type": [
"number",
"null"
],
"description": "AI 响应的随机性
可选字段
值越高，输出越多样
值越低，输出越集中
最小值：0
最大值：1.9
默认值：0.77"
},
"top_p": {
"type": [
"number",
"null"
],
"description": "AI 响应的多样性
可选字段
通过限制 token 选择来控制响应的多样性
最小值：0
最大值：1
默认值：0.9"
},
"web_search_country_iso_code": {
"type": [
"string",
"null"
],
"description": "用于网络搜索本地化的国家代码
可选字段
指定国家 ISO 代码以获取本地化的网络搜索结果
注意：仅适用于 Perplexity Sonar 模型
示例：US"
},
"system_message": {
"type": [
"string",
"null"
],
"description": "AI 行为指令
可选字段
定义 AI 的角色、语气或特定行为
在 system_message 字段中最多可指定 500 个字符"
},
"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": "用户自定义任务标识符
可选字段
字符数上限为 255
可使用此参数标识任务，并将其与结果对应
可在响应的 data 对象中找到指定的 tag 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,
"web_search_country_iso_code": "FR",
"model_name": "sonar",
"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,
"web_search_country_iso_code": "FR",
"model_name": "sonar",
"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": [
{
"$ref": "#/components/schemas/Response36Afe1097B20_AiOptimizationPerplexityLlmResponsesLiveResponseInfo"
}
]
}
```
### 400 — 无法处理该请求。请检查请求参数。
### 401 — 需要有效的 Felo API 密钥。
### 402 — 由于未满足计费要求，请求无法继续。
### 403 — 该账户无权执行此操作。
### 429 — 已达到请求或支出限额。
### 502 — 服务无法完成该请求。
### 503 — API 或计费服务暂时不可用。
### 504 — 服务在处理请求时超时。
### default — 错误响应；上游透传响应可能采用提供方格式
**application/json**
Schema:
```json
{}
```
## Schema definitions
### Response36Afe1097B20_AiOptimizationPerplexityLlmResponsesLiveResponseInfo
`#/components/schemas/Response36Afe1097B20_AiOptimizationPerplexityLlmResponsesLiveResponseInfo`
```json
{
"type": "object",
"allOf": [
{
"$ref": "#/components/schemas/Response36Afe1097B20_BaseResponseInfo"
},
{
"type": "object",
"properties": {
"tasks": {
"type": [
"array",
"null"
],
"items": {
"type": [
"object",
"null"
],
"oneOf": [
{
"$ref": "#/components/schemas/Response36Afe1097B20_AiOptimizationPerplexityLlmResponsesLiveTaskInfo"
}
]
},
"description": "任务数组"
}
}
}
]
}
```
### Response36Afe1097B20_AiOptimizationPerplexityLlmResponsesLiveResultInfo
`#/components/schemas/Response36Afe1097B20_AiOptimizationPerplexityLlmResponsesLiveResultInfo`
```json
{
"type": "object",
"properties": {
"model_name": {
"type": [
"string",
"null"
],
"description": "所用 AI 模型的名称"
},
"input_tokens": {
"type": [
"integer",
"null"
],
"description": "输入中的 token 数
处理的 token 总数"
},
"output_tokens": {
"type": [
"integer",
"null"
],
"description": "输出中的 token 数
AI 响应中生成的 token 总数"
},
"reasoning_tokens": {
"type": [
"integer",
"null"
]
},
"web_search": {
"type": [
"boolean",
"null"
],
"description": "表示是否使用了网络搜索
注意：在 Perplexity Sonar 模型中，网络搜索默认启用"
},
"money_spent": {
"type": [
"number",
"null"
],
"description": "AI token 成本（美元）
第三方 AI 模型提供商按其定价收取的费用"
},
"datetime": {
"type": [
"string",
"null"
],
"description": "收到结果的日期和时间
采用 UTC 格式：“yyyy-mm-dd hh-mm-ss +00:00”
示例：
2019-11-15 12:57:46 +00:00"
},
"items": {
"type": [
"array",
"null"
],
"items": {
"type": [
"object",
"null"
],
"oneOf": [
{
"$ref": "#/components/schemas/Response36Afe1097B20_MessageAiOptimizationLlmResponseElementItem"
}
]
},
"description": "响应条目数组
包含结构化的 AI 响应数据"
},
"fan_out_queries": {
"type": [
"object",
"null"
],
"description": "扇出查询数组
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_AiOptimizationPerplexityLlmResponsesLiveTaskInfo
`#/components/schemas/Response36Afe1097B20_AiOptimizationPerplexityLlmResponsesLiveTaskInfo`
```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_AiOptimizationPerplexityLlmResponsesLiveResultInfo"
}
]
},
"description": "结果数组"
}
}
}
]
}
```
### Response36Afe1097B20_AnnotationInfo
`#/components/schemas/Response36Afe1097B20_AnnotationInfo`
```json
{
"type": "object",
"properties": {
"title": {
"type": [
"string",
"null"
],
"description": "引用来源的域名或标题"
},
"url": {
"type": [
"string",
"null"
],
"description": "指向引用来源的重定向 URL
包含指向原始来源的 Vertex AI 重定向"
},
"direct_url": {
"type": [
"string",
"null"
],
"description": "引用来源的直接 URL
包含 `url` 字段中的 Vertex AI 重定向所指向的原始来源 URL"
},
"start_index": {
"type": [
"integer",
"null"
],
"description": "注释索引的起始位置"
},
"end_index": {
"type": [
"integer",
"null"
],
"description": "注释索引的结束位置"
},
"text": {
"type": [
"string",
"null"
],
"description": "推理链章节的文本
概述模型思考过程的推理链章节文本"
}
}
}
```
### 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"
}
}
}
```
### Response36Afe1097B20_LlmMessageSectionInfo
`#/components/schemas/Response36Afe1097B20_LlmMessageSectionInfo`
```json
{
"type": "object",
"properties": {
"type": {
"type": [
"string",
"null"
],
"description": "元素类型"
},
"text": {
"type": [
"string",
"null"
],
"description": "推理链章节的文本
概述模型思考过程的推理链章节文本"
},
"annotations": {
"type": [
"array",
"null"
],
"items": {
"type": [
"object",
"null"
],
"oneOf": [
{
"$ref": "#/components/schemas/Response36Afe1097B20_AnnotationInfo"
}
]
},
"description": "用于生成响应的引用数组
如果 web_search 参数未设为 true，则为 null
注意：即使 web_search 为 true，annotations 也可能返回空，因为 AI 会尝试检索网络信息，但可能找不到相关结果"
}
}
}
```
### Response36Afe1097B20_MessageAiOptimizationLlmResponseElementItem
`#/components/schemas/Response36Afe1097B20_MessageAiOptimizationLlmResponseElementItem`
```json
{
"type": "object",
"allOf": [
{
"$ref": "#/components/schemas/Response36Afe1097B20_BaseAiOptimizationLlmResponseElementItem"
},
{
"type": "object",
"properties": {
"sections": {
"type": [
"array",
"null"
],
"items": {
"type": [
"object",
"null"
],
"oneOf": [
{
"$ref": "#/components/schemas/Response36Afe1097B20_LlmMessageSectionInfo"
}
]
},
"description": "推理链章节
包含 LLM 生成的推理链章节的对象数组"
}
}
}
]
}
```