Skip to main content
POST
/
v1
/
responses
Responses API
curl --request POST \
  --url https://api.chenyu.cn/v1/responses \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "input": {},
  "stream": true,
  "temperature": 123,
  "max_output_tokens": 123,
  "reasoning": {}
}
'
{
  "id": "<string>",
  "object": "<string>",
  "status": "<string>",
  "model": "<string>",
  "output": [
    {}
  ],
  "usage": {}
}

​
Responses API

使用 OpenAI Responses 兼容格式调用文本模型。适合使用 input 组织请求，或需要携带模型专属参数的场景。

​
请求参数

​
model
string
required
模型 ID。可通过 模型列表 查询
​
input
string | array
required
输入内容。可以是字符串，也可以是 Responses 格式的输入数组
​
stream
boolean
是否使用流式响应
​
temperature
number
采样温度
​
max_output_tokens
integer
最大输出 token 数
​
reasoning
object
推理相关参数，具体支持范围以模型为准

​
响应参数

​
id
string
响应 ID
​
object
string
响应类型，通常为 response
​
status
string
响应状态，如 completed
​
model
string
实际调用的模型 ID
​
output
array
输出内容数组
​
usage
object
token 用量

​
代码示例

import requests

url = "https://api.chenyu.cn/v1/responses"
headers = {
    "Authorization": "Bearer your_api_key",
    "Content-Type": "application/json"
}
payload = {
    "model": "doubao-seed-2-0-lite-260428",
    "input": "用三句话说明 GPU 云服务适合哪些场景"
}

response = requests.post(url, headers=headers, json=payload)
print(response.json())

​
模型专属参数

{
  "model": "doubao-seed-2-0-lite-260428",
  "input": "分析这个问题",
  "thinking": {"type": "enabled"},
  "reasoning": {"effort": "low"}
}

​
响应示例

{
  "id": "resp_xxx",
  "object": "response",
  "status": "completed",
  "model": "doubao-seed-2-0-lite-260428",
  "output": [
    {
      "type": "message",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "GPU 云服务适合模型训练、推理部署和批量数据处理。"
        }
      ]
    }
  ],
  "usage": {
    "input_tokens": 18,
    "output_tokens": 16,
    "total_tokens": 34
  }
}