Deepseek reasoning 对话格式（Reasoning Content）

POST

/v1/chat/completions

Deepseek-reasoner 是 DeepSeek 推出的推理模型。在输出最终回答之前，模型会先输出一段思维链内容，以提升最终答案的准确性。API 向用户开放 deepseek-reasoner 思维链的内容，以供用户查看、展示、蒸馏使用。

请求参数

Header 参数

Body 参数application/json

示例

基础文本对话流式响应

{
    "model": "deepseek-r1",
    "messages": [
        {
            "role": "user",
            "content": "9.11 and 9.8, which is greater?"
        }
    ],
    "max_tokens": 4096
}

请求示例代码

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

cURL

基础文本对话流式响应

curl --location -g --request POST '/v1/chat/completions' \
--header 'Authorization: Bearer ' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "deepseek-r1",
    "messages": [
        {
            "role": "user",
            "content": "9.11 and 9.8, which is greater?"
        }
    ],
    "max_tokens": 4096
}'

返回响应

🟢200成功

application/json

Body

示例

基础文本对话流式响应

{
    "id": "chatcmpl-123",
    "object": "chat.completion",
    "created": 1677652288,
    "model": "deepseek-r1",
    "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
    }
}

修改于 2025-07-27 14:15:31

Anthropic 对话格式（Messages）