curl -X POST https://www.geeknow.top/v1/responses \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.5",
    "instructions": "你是一个简洁的技术助手。",
    "input": "用三句话解释 Responses API 适合什么场景。",
    "reasoning": { "effort": "low" }
  }'

{
  "id": "resp_abc123",
  "object": "response",
  "created_at": 1735689600,
  "status": "completed",
  "model": "gpt-5.5",
  "output": [
    {
      "type": "message",
      "id": "msg_abc123",
      "status": "completed",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "Responses API 适合多模态输入、工具调用和需要上下文续接的任务。它把输出拆成结构化 item，便于程序读取。通过统一网关可以复用同一套认证、计费和渠道分发能力。",
          "annotations": []
        }
      ]
    }
  ],
  "usage": {
    "prompt_tokens": 26,
    "completion_tokens": 62,
    "total_tokens": 88
  }
}

event: response.created
data: {"type":"response.created","response":{"id":"resp_abc123","object":"response","status":"in_progress","model":"gpt-5.5"}}

event: response.output_text.delta
data: {"type":"response.output_text.delta","delta":"Responses"}

event: response.output_text.delta
data: {"type":"response.output_text.delta","delta":" API"}

event: response.completed
data: {"type":"response.completed","response":{"id":"resp_abc123","status":"completed","usage":{"prompt_tokens":26,"completion_tokens":62,"total_tokens":88}}}

{
  "error": {
    "message": "model is required",
    "type": "invalid_request_error",
    "param": "",
    "code": "invalid_request"
  }
}

{
  "error": {
    "message": "Invalid API key provided",
    "type": "invalid_request_error",
    "param": "",
    "code": "invalid_api_key"
  }
}

{
  "error": {
    "message": "用户额度不足",
    "type": "new_api_error",
    "param": "",
    "code": "insufficient_user_quota"
  }
}

{
  "error": {
    "message": "当前请求频率过高，请稍后再试",
    "type": "new_api_error",
    "param": "",
    "code": "too_many_requests"
  }
}

{
  "error": {
    "message": "bad response body",
    "type": "new_api_error",
    "param": "",
    "code": "bad_response_body"
  }
}

POST

https://www.geeknow.top

responses

curl -X POST https://www.geeknow.top/v1/responses \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.5",
    "instructions": "你是一个简洁的技术助手。",
    "input": "用三句话解释 Responses API 适合什么场景。",
    "reasoning": { "effort": "low" }
  }'

{
  "id": "resp_abc123",
  "object": "response",
  "created_at": 1735689600,
  "status": "completed",
  "model": "gpt-5.5",
  "output": [
    {
      "type": "message",
      "id": "msg_abc123",
      "status": "completed",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "Responses API 适合多模态输入、工具调用和需要上下文续接的任务。它把输出拆成结构化 item，便于程序读取。通过统一网关可以复用同一套认证、计费和渠道分发能力。",
          "annotations": []
        }
      ]
    }
  ],
  "usage": {
    "prompt_tokens": 26,
    "completion_tokens": 62,
    "total_tokens": 88
  }
}

event: response.created
data: {"type":"response.created","response":{"id":"resp_abc123","object":"response","status":"in_progress","model":"gpt-5.5"}}

event: response.output_text.delta
data: {"type":"response.output_text.delta","delta":"Responses"}

event: response.output_text.delta
data: {"type":"response.output_text.delta","delta":" API"}

event: response.completed
data: {"type":"response.completed","response":{"id":"resp_abc123","status":"completed","usage":{"prompt_tokens":26,"completion_tokens":62,"total_tokens":88}}}

{
  "error": {
    "message": "model is required",
    "type": "invalid_request_error",
    "param": "",
    "code": "invalid_request"
  }
}

{
  "error": {
    "message": "Invalid API key provided",
    "type": "invalid_request_error",
    "param": "",
    "code": "invalid_api_key"
  }
}

{
  "error": {
    "message": "用户额度不足",
    "type": "new_api_error",
    "param": "",
    "code": "insufficient_user_quota"
  }
}

{
  "error": {
    "message": "当前请求频率过高，请稍后再试",
    "type": "new_api_error",
    "param": "",
    "code": "too_many_requests"
  }
}

{
  "error": {
    "message": "bad response body",
    "type": "new_api_error",
    "param": "",
    "code": "bad_response_body"
  }
}

OpenAI Responses 接口

Responses API 是面向多模态、工具调用和结构化输出的统一响应接口。相比 Chat Completions，它的输入、输出和工具调用结构更适合复杂任务编排。新项目如果没有强依赖旧 Chat Completions 请求体，建议优先评估该接口。

请求体

model

string

required

模型名称。

input

string | array<object>

用户输入。可以是字符串，也可以是结构化消息数组；部分上游能力组合会要求使用结构化数组。

instructions

string

开发者或系统级指令。

previous_response_id

string

上一轮响应 ID。仅在上游和当前通道支持 Responses 会话续接时可用；当前 HTTP 路径不应依赖该字段做通用上下文管理。

tools

array<object>

工具列表。支持函数工具，也可转发上游兼容的内置工具。

tool_choice

string | object

工具选择策略。

max_output_tokens

integer

最大输出 token 数。不同模型和通道对该字段支持程度不同；如果返回空文本或上游报不支持，请调高限制或去掉该字段后重试。

reasoning

object

推理配置，例如 { "effort": "low" }、{ "effort": "medium" }、{ "effort": "high" }、{ "effort": "xhigh" }。官方支持值还包括 none 和 minimal，但具体可用范围取决于模型。

text

object

文本输出配置，常用于 JSON Schema 结构化输出，也可包含支持模型的输出风格字段，例如 verbosity。

stream

boolean

是否启用 SSE 流式输出。

stream_options.include_obfuscation

boolean

OpenAI Responses 原生流式选项，用于控制流式事件中的 obfuscation 字段。不要把 Chat Completions 的 stream_options.include_usage 直接套到 Responses；用量通常随 response.completed 等事件返回，是否出现取决于上游。

store

boolean

控制上游是否存储请求和响应。该字段默认允许转发，可由渠道设置禁用。

metadata

object

业务侧附加元数据。

include

array<string>

请求响应中额外包含的字段，具体取值取决于上游实现。

请求示例

curl -X POST https://www.geeknow.top/v1/responses \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.5",
    "instructions": "你是一个简洁的技术助手。",
    "input": "用三句话解释 Responses API 适合什么场景。",
    "reasoning": { "effort": "low" }
  }'

多模态输入

图片 URL 放在 input_image.image_url。如果传 base64，使用 data:image/png;base64,... 形式；具体是否支持取决于模型和通道，生产前请用当前 API Key 验证。

curl -X POST https://www.geeknow.top/v1/responses \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.5",
    "input": [
      {
        "role": "user",
        "content": [
          { "type": "input_text", "text": "提取这张截图中的异常指标。" },
          { "type": "input_image", "image_url": "https://YOUR_IMAGE_HOST/path/dashboard.png", "detail": "high" }
        ]
      }
    ]
  }'

工具调用

curl -X POST https://www.geeknow.top/v1/responses \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.5",
    "input": "北京今天适合户外跑步吗？",
    "tools": [
      {
        "type": "function",
        "name": "get_weather",
        "description": "获取城市天气",
        "parameters": {
          "type": "object",
          "properties": {
            "city": { "type": "string" }
          },
          "required": ["city"]
        }
      }
    ],
    "tool_choice": "auto"
  }'

流式输出

curl -N -X POST https://www.geeknow.top/v1/responses \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.5",
    "input": "写一个 5 行以内的产品发布公告。",
    "stream": true
  }'

base64 写法：

{
  "type": "input_image",
  "image_url": "data:image/png;base64,BASE64_IMAGE_DATA"
}

响应示例

{
  "id": "resp_abc123",
  "object": "response",
  "created_at": 1735689600,
  "status": "completed",
  "model": "gpt-5.5",
  "output": [
    {
      "type": "message",
      "id": "msg_abc123",
      "status": "completed",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "Responses API 适合多模态输入、工具调用和需要上下文续接的任务。它把输出拆成结构化 item，便于程序读取。通过统一网关可以复用同一套认证、计费和渠道分发能力。",
          "annotations": []
        }
      ]
    }
  ],
  "usage": {
    "prompt_tokens": 26,
    "completion_tokens": 62,
    "total_tokens": 88
  }
}

event: response.created
data: {"type":"response.created","response":{"id":"resp_abc123","object":"response","status":"in_progress","model":"gpt-5.5"}}

event: response.output_text.delta
data: {"type":"response.output_text.delta","delta":"Responses"}

event: response.output_text.delta
data: {"type":"response.output_text.delta","delta":" API"}

event: response.completed
data: {"type":"response.completed","response":{"id":"resp_abc123","status":"completed","usage":{"prompt_tokens":26,"completion_tokens":62,"total_tokens":88}}}

{
  "error": {
    "message": "model is required",
    "type": "invalid_request_error",
    "param": "",
    "code": "invalid_request"
  }
}

{
  "error": {
    "message": "Invalid API key provided",
    "type": "invalid_request_error",
    "param": "",
    "code": "invalid_api_key"
  }
}

{
  "error": {
    "message": "用户额度不足",
    "type": "new_api_error",
    "param": "",
    "code": "insufficient_user_quota"
  }
}

{
  "error": {
    "message": "当前请求频率过高，请稍后再试",
    "type": "new_api_error",
    "param": "",
    "code": "too_many_requests"
  }
}

{
  "error": {
    "message": "bad response body",
    "type": "new_api_error",
    "param": "",
    "code": "bad_response_body"
  }
}

上下文压缩

POST /v1/responses/compact

用于把较长上下文压缩成适合后续继续对话的摘要。请求结构与 /v1/responses 接近，常用字段为 model、input、instructions、previous_response_id。

curl -X POST https://www.geeknow.top/v1/responses/compact \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.5",
    "instructions": "压缩成后续对话可继续使用的上下文，保留决策、约束和待办。",
    "input": [
      { "role": "user", "content": "第一轮需求..." },
      { "role": "assistant", "content": "第一轮方案..." }
    ]
  }'

概览

文本系列

图像系列

视频系列

上传管理

任务管理

账户管理

OpenAI Responses 接口

OpenAI Responses 接口

请求体

请求示例

多模态输入

工具调用

流式输出

响应示例

上下文压缩

相关接口

​OpenAI Responses 接口

​请求体

​请求示例

​多模态输入

​工具调用

​流式输出

​响应示例

​上下文压缩

​相关接口

OpenAI Responses 接口

请求体

请求示例

多模态输入

工具调用

流式输出

响应示例

上下文压缩

相关接口