curl -N -X POST https://www.geeknow.top/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.5",
    "messages": [
      { "role": "system", "content": "你是一个简洁的技术助手。" },
      { "role": "user", "content": "用三点说明 API 网关的作用。" }
    ],
    "stream": true,
    "stream_options": {
      "include_usage": true
    }
  }'

data: {"id":"chatcmpl_abc123","object":"chat.completion.chunk","created":1735689600,"model":"gpt-5.5","choices":[{"index":0,"delta":{"role":"assistant","content":"API"},"finish_reason":null}]}

data: {"id":"chatcmpl_abc123","object":"chat.completion.chunk","created":1735689600,"model":"gpt-5.5","choices":[{"index":0,"delta":{"content":" 网关"},"finish_reason":null}]}

data: {"id":"chatcmpl_abc123","object":"chat.completion.chunk","created":1735689600,"model":"gpt-5.5","choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":{"prompt_tokens":26,"completion_tokens":38,"total_tokens":64}}

data: [DONE]

{
  "error": {
    "message": "field 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

chat

completions

curl -N -X POST https://www.geeknow.top/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.5",
    "messages": [
      { "role": "system", "content": "你是一个简洁的技术助手。" },
      { "role": "user", "content": "用三点说明 API 网关的作用。" }
    ],
    "stream": true,
    "stream_options": {
      "include_usage": true
    }
  }'

data: {"id":"chatcmpl_abc123","object":"chat.completion.chunk","created":1735689600,"model":"gpt-5.5","choices":[{"index":0,"delta":{"role":"assistant","content":"API"},"finish_reason":null}]}

data: {"id":"chatcmpl_abc123","object":"chat.completion.chunk","created":1735689600,"model":"gpt-5.5","choices":[{"index":0,"delta":{"content":" 网关"},"finish_reason":null}]}

data: {"id":"chatcmpl_abc123","object":"chat.completion.chunk","created":1735689600,"model":"gpt-5.5","choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":{"prompt_tokens":26,"completion_tokens":38,"total_tokens":64}}

data: [DONE]

{
  "error": {
    "message": "field 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"
  }
}

Chat Completions（流式）

使用统一对话格式调用 OpenAI、Claude、Gemini、DeepSeek、Qwen 等上游模型。本页展示流式写法，适合需要边生成边展示的聊天、Agent 和长文本生成场景。

如果未传 stream，接口默认按非流式返回。若希望固定获得流式响应，请显式传入 "stream": true。

请求体

model

string

required

模型名称。可通过模型列表查询当前 API Key 可用模型。

messages

array<object>

required

按时间顺序排列的对话消息。常见角色为 system、user、assistant、tool。

messages[].content

string | array

required

消息内容。字符串表示纯文本；数组表示多模态内容，支持 text、image_url、input_audio、file、video_url。

stream

boolean

required

设为 true 后响应为 text/event-stream，每个片段以 data: 推送，结束时返回 data: [DONE]。

stream_options.include_usage

boolean

在流式最后一条消息中携带 token 用量统计。仅部分上游模型支持。

max_tokens

integer

限制最大生成 token 数。部分推理模型建议改用 max_completion_tokens。

max_completion_tokens

integer

限制最大补全 token 数，包含推理 token。适合支持 reasoning 的模型。

temperature

number

采样温度，常用范围 0 到 2。较低值更稳定，较高值更多样。

top_p

number

核采样参数，常用范围 0 到 1。通常不建议同时大幅调整 temperature 和 top_p。

tools

array<object>

函数调用工具列表，格式兼容 OpenAI tools。

tool_choice

string | object

控制模型是否调用工具。常见值为 auto、none、required，也可指定某个函数。

response_format

object

指定输出格式，例如 { "type": "json_object" } 或 json_schema。

reasoning_effort

string

推理强度。常见值包括 none、minimal、low、medium、high、xhigh；是否生效取决于模型。高强度不一定更好，建议按业务评测选择。

请求示例

curl -N -X POST https://www.geeknow.top/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.5",
    "messages": [
      { "role": "system", "content": "你是一个简洁的技术助手。" },
      { "role": "user", "content": "用三点说明 API 网关的作用。" }
    ],
    "stream": true,
    "stream_options": {
      "include_usage": true
    }
  }'

多模态流式

图片 URL 需要能被上游模型公网下载；本地图片请先上传图床。base64 图片可使用 data:image/png;base64,... 形式放在 image_url.url。

curl -N -X POST https://www.geeknow.top/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.5",
    "messages": [
      {
        "role": "user",
        "content": [
          { "type": "text", "text": "概括这张图表的主要结论。" },
          { "type": "image_url", "image_url": { "url": "https://YOUR_IMAGE_HOST/path/chart.png", "detail": "high" } }
        ]
      }
    ],
    "stream": true
  }'

响应示例

data: {"id":"chatcmpl_abc123","object":"chat.completion.chunk","created":1735689600,"model":"gpt-5.5","choices":[{"index":0,"delta":{"role":"assistant","content":"API"},"finish_reason":null}]}

data: {"id":"chatcmpl_abc123","object":"chat.completion.chunk","created":1735689600,"model":"gpt-5.5","choices":[{"index":0,"delta":{"content":" 网关"},"finish_reason":null}]}

data: {"id":"chatcmpl_abc123","object":"chat.completion.chunk","created":1735689600,"model":"gpt-5.5","choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":{"prompt_tokens":26,"completion_tokens":38,"total_tokens":64}}

data: [DONE]

{
  "error": {
    "message": "field 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"
  }
}

响应字段

string

本次生成的响应 ID。

object

string

流式响应固定为 chat.completion.chunk。

choices[].delta

object

增量内容。可能包含 role、content、reasoning_content 或 tool_calls。

choices[].finish_reason

string

结束原因，常见值为 stop、length、tool_calls。

usage

object

用量统计。只有上游返回用量且启用 stream_options.include_usage 时才一定出现。

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

Chat Completions（流式）

Chat Completions（流式）

请求体

请求示例

多模态流式

响应示例

响应字段

相关接口

​Chat Completions（流式）

​请求体

​请求示例

​多模态流式

​响应示例

​响应字段

​相关接口

Chat Completions（流式）

请求体

请求示例

多模态流式

响应示例

响应字段

相关接口