Deepseek Reasoning - RootAPI.ai API文档

🔗 接口端点

POST/v1/chat/completions

使用 deepseek-reasoner 模型创建带有推理过程的对话补全。

📝 请求参数

参数名	类型	必需	默认值	说明
model	string	是	-	必须设置为 "deepseek-reasoner"
messages	array	是	-	对话消息数组
max_tokens	integer	否	4096	最大生成token数
temperature	number	否	1.0	随机性控制 (0-2)
stream	boolean	否	false	是否流式输出
top_p	number	否	1.0	核采样参数

🎯 模型特殊说明

deepseek-reasoner 模型的响应包含两个关键字段：

reasoning_content - 模型的思维链推理过程
content - 基于推理得出的最终答案

💡 请求示例

🧠 基础推理对话 ✅

curl https://rootapiai.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $ROOTAPI_API_KEY" \
  -d '{
    "model": "deepseek-reasoner",
    "messages": [
      {
        "role": "user",
        "content": "9.11 and 9.8, which is greater?"
      }
    ],
    "max_tokens": 4096
  }'

📥 响应示例：

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "deepseek-reasoner",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "reasoning_content": "让我一步步思考:\n1. 我们需要比较9.11和9.8的大小\n2. 两个数都是小数,我们可以直接比较\n3. 9.8 = 9.80\n4. 9.11 < 9.80\n5. 所以9.8更大",
      "content": "9.8 is greater than 9.11."
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 15,
    "total_tokens": 25
  }
}

🔍 响应字段说明

reasoning_content - 模型的完整推理过程，展示了思考步骤
content - 基于推理得出的简洁最终答案
finish_reason - 生成结束的原因（通常为 "stop"）

📡 流式推理响应 ✅

curl https://rootapiai.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $ROOTAPI_API_KEY" \
  -d '{
    "model": "deepseek-reasoner",
    "messages": [
      {
        "role": "user",
        "content": "9.11 and 9.8, which is greater?"
      }
    ],
    "stream": true
  }'

📥 流式响应示例：

{"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"deepseek-reasoner","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"让我"},"finish_reason":null}]}

{"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"deepseek-reasoner","choices":[{"index":0,"delta":{"reasoning_content":"一步步"},"finish_reason":null}]}

{"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"deepseek-reasoner","choices":[{"index":0,"delta":{"reasoning_content":"思考:"},"finish_reason":null}]}

// ... 更多思维链内容 ...

{"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"deepseek-reasoner","choices":[{"index":0,"delta":{"content":"9.8"},"finish_reason":null}]}

{"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"deepseek-reasoner","choices":[{"index":0,"delta":{"content":" is greater"},"finish_reason":null}]}

// ... 更多最终答案内容 ...

{"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"deepseek-reasoner","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}

📡 流式响应特点

在流式模式下，推理内容和最终答案会分别逐步输出：

推理阶段 - 先输出 reasoning_content 字段的内容
答案阶段 - 然后输出 content 字段的最终答案
实时展示 - 用户可以实时看到模型的思考过程

🧠 Deepseek Reasoning

📝 简介

🔬 推理模型特点

🔗 接口端点

POST/v1/chat/completions

📝 请求参数

🎯 模型特殊说明

💡 请求示例

🧠 基础推理对话 ✅

📥 响应示例：

🔍 响应字段说明

📡 流式推理响应 ✅

📥 流式响应示例：

📡 流式响应特点

🚀 使用建议