Skip to main content
POST
https://www.geeknow.top
/
v1
/
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-4o",
    "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-4o","choices":[{"index":0,"delta":{"role":"assistant","content":"API"},"finish_reason":null}]}

data: {"id":"chatcmpl_abc123","object":"chat.completion.chunk","created":1735689600,"model":"gpt-4o","choices":[{"index":0,"delta":{"content":" 网关"},"finish_reason":null}]}

data: {"id":"chatcmpl_abc123","object":"chat.completion.chunk","created":1735689600,"model":"gpt-4o","choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":{"prompt_tokens":26,"completion_tokens":38,"total_tokens":64}}

data: [DONE]

Documentation Index

Fetch the complete documentation index at: https://docs.geeknow.top/llms.txt

Use this file to discover all available pages before exploring further.

​
通用对话接口（默认流式）

使用统一对话格式调用 OpenAI、Claude、Gemini、DeepSeek、Qwen 等上游模型。本文档以流式输出为默认写法，适合需要边生成边展示的聊天、Agent 和长文本生成场景。
本项目路由中 stream 未传时按非流式处理。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。常见值为 low、medium、high，是否生效取决于模型。

​
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-4o",
    "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

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-4o",
    "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://.../chart.png", "detail": "high" } }
        ]
      }
    ],
    "stream": true
  }'

​
响应示例

data: {"id":"chatcmpl_abc123","object":"chat.completion.chunk","created":1735689600,"model":"gpt-4o","choices":[{"index":0,"delta":{"role":"assistant","content":"API"},"finish_reason":null}]}

data: {"id":"chatcmpl_abc123","object":"chat.completion.chunk","created":1735689600,"model":"gpt-4o","choices":[{"index":0,"delta":{"content":" 网关"},"finish_reason":null}]}

data: {"id":"chatcmpl_abc123","object":"chat.completion.chunk","created":1735689600,"model":"gpt-4o","choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":{"prompt_tokens":26,"completion_tokens":38,"total_tokens":64}}

data: [DONE]

​
响应字段

​
id
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。

​
相关接口