导航|地址|刷新
思考模式 | DeepSeek API Docs







跳到主要内容




DeepSeek API 文档


中文（中国）
English

中文（中国）

DeepSeek Platform














快速开始

首次调用 API

模型 & 价格

Token 用量计算

限速与隔离

错误码


接入 Agent 工具




API 指南

思考模式

多轮对话

对话前缀续写（Beta）

FIM 补全（Beta）

JSON Output

Tool Calls

上下文硬盘缓存

使用 Responses API

使用 Anthropic API



API 文档



新闻



其它资源


常见问题

更新日志










API 指南

思考模式

本页总览




思考模式

DeepSeek 模型支持思考模式：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。

思考模式开关与思考强度控制​

	控制参数（OpenAI 格式）	控制参数（Anthropic 格式）	控制参数（Responses API 格式）
思考模式开关(1)	{"thinking": {"type": "enabled/disabled"}}	{"reasoning": {"effort": "none/low/high/max"}} (none 表示关闭思考模式)
思考强度控制(2)	{"reasoning_effort": "low/high/max"}	{"output_config": {"effort": "low/high/max"}}

(1) 思考模式默认打开，且 effort 默认为 high
(2) 用户设置的 effort 与模型推理 effort 映射表如下：

请求传入 effort	deepseek-v4-flash 实际映射 effort	deepseek-v4-pro 实际映射 effort(3)
low	low	high
high	high	high
xhigh	high	max
max	max	max

(3) 我们将于 2026 年 8 月初，更新 deepseek-v4-pro 的实际映射


您在 OpenAI SDK 中使用 Chat Completion 设置 thinking 参数时，需要将 thinking 参数传入 extra_body 中：


response = client.chat.completions.create(
model="deepseek-v4-pro",
# ...
reasoning_effort="high",
extra_body={"thinking":{"type":"enabled"}}
)





输入输出参数​

思考模式不支持 temperature、top_p、presence_penalty、frequency_penalty 参数。请注意，为了兼容已有软件，设置参数不会报错，但也不会生效。

在思考模式下，思维链内容通过 reasoning_content 参数返回，与 content 同级。在后续的轮次的拼接中，可以选择性地返回 reasoning_content 给 API：

在两个 user 消息之间，如果模型未进行工具调用，则中间 assistant 的 reasoning_content 无需参与上下文拼接，在后续轮次中将其传入 API 会被忽略。详见多轮对话拼接。

在两个 user 消息之间，如果模型进行了工具调用，则中间 assistant 的 reasoning_content 需参与上下文拼接，在后续所有 user 交互轮次中必须回传给 API。详见工具调用。

多轮对话拼接​

在每一轮对话过程中，模型会输出思维链内容（reasoning_content）和最终回答（content）。如果没有工具调用，则在下一轮对话中，之前轮输出的思维链内容不会被拼接到上下文中，如下图所示：



样例代码​

下面的代码以 Python 语言为例，展示了如何访问思维链和最终回答，以及如何在多轮对话中进行上下文拼接。


非流式

流式




from openai import OpenAI
client = OpenAI(api_key="<DeepSeek API Key>", base_url="https://api.deepseek.com")

# Turn 1
messages =[{"role":"user","content":"9.11 and 9.8, which is greater?"}]
response = client.chat.completions.create(
model="deepseek-v4-pro",
messages=messages,
reasoning_effort="high"
extra_body={"thinking":{"type":"enabled"}},
)

reasoning_content = response.choices[0].message.reasoning_content
content = response.choices[0].message.content

# Turn 2
# The reasoning_content will be ignored by the API
messages.append(response.choices[0].message)
messages.append({'role':'user','content':"How many Rs are there in the word 'strawberry'?"})
response = client.chat.completions.create(
model="deepseek-v4-pro",
messages=messages,
reasoning_effort="high"
extra_body={"thinking":{"type":"enabled"}},
)
# ...








from openai import OpenAI
client = OpenAI(api_key="<DeepSeek API Key>", base_url="https://api.deepseek.com")

# Turn 1
messages =[{"role":"user","content":"9.11 and 9.8, which is greater?"}]
response = client.chat.completions.create(
model="deepseek-v4-pro",
messages=messages,
stream=True,
reasoning_effort="high"
extra_body={"thinking":{"type":"enabled"}},
)

reasoning_content =""
content =""

for chunk in response:
if chunk.choices[0].delta.reasoning_content:
reasoning_content += chunk.choices[0].delta.reasoning_content
else:
content += chunk.choices[0].delta.content

# Turn 2
# The reasoning_content will be ignored by the API
messages.append({"role":"assistant","reasoning_content": reasoning_content,"content": content})
messages.append({'role':'user','content':"How many Rs are there in the word 'strawberry'?"})
response = client.chat.completions.create(
model="deepseek-v4-pro",
messages=messages,
stream=True,
reasoning_effort="high"
extra_body={"thinking":{"type":"enabled"}},
)
# ...








工具调用​

DeepSeek 模型的思考模式支持工具调用功能。模型在输出最终答案之前，可以进行多轮的思考与工具调用，以提升答案的质量。其调用模式如下图所示：



请注意，携带了 tools 参数的请求，在后续所有请求中，必须完整回传 reasoning_content 给 API。若您的代码中未正确回传 reasoning_content，API 会返回 400 报错。正确回传方法请您参考下面的样例代码。

样例代码​

下面是一个简单的在思考模式下进行工具调用的样例代码：


import os
import json
from openai import OpenAI
from datetime import datetime

# The definition of the tools
tools =[
{
"type":"function",
"function":{
"name":"get_date",
"description":"Get the current date",
"parameters":{"type":"object","properties":{}},
}
},
{
"type":"function",
"function":{
"name":"get_weather",
"description":"Get weather of a location, the user should supply the location and date.",
"parameters":{
"type":"object",
"properties":{
"location":{"type":"string","description":"The city name"},
"date":{"type":"string","description":"The date in format YYYY-mm-dd"},
},
"required":["location","date"]
},
}
},
]

# The mocked version of the tool calls
defget_date_mock():
return datetime.now().strftime("%Y-%m-%d")

defget_weather_mock(location, date):
return"Cloudy 7~13°C"

TOOL_CALL_MAP ={
"get_date": get_date_mock,
"get_weather": get_weather_mock
}

defrun_turn(turn, messages):
sub_turn =1
whileTrue:
response = client.chat.completions.create(
model='deepseek-v4-pro',
messages=messages,
tools=tools,
reasoning_effort="high",
extra_body={"thinking":{"type":"enabled"}},
)
messages.append(response.choices[0].message)
reasoning_content = response.choices[0].message.reasoning_content
content = response.choices[0].message.content
tool_calls = response.choices[0].message.tool_calls
print(f"Turn {turn}.{sub_turn}\n{reasoning_content=}\n{content=}\n{tool_calls=}")
# If there is no tool calls, then the model should get a final answer and we need to stop the loop
if tool_calls isNone:
break
for tool in tool_calls:
tool_function = TOOL_CALL_MAP[tool.function.name]
tool_result = tool_function(**json.loads(tool.function.arguments))
print(f"tool result for {tool.function.name}: {tool_result}\n")
messages.append({
"role":"tool",
"tool_call_id": tool.id,
"content": tool_result,
})
sub_turn +=1
print()

client = OpenAI(
api_key=os.environ.get('DEEPSEEK_API_KEY'),
base_url=os.environ.get('DEEPSEEK_BASE_URL'),
)

# The user starts a question
turn =1
messages =[{
"role":"user",
"content":"How's the weather in Hangzhou Tomorrow"
}]
run_turn(turn, messages)

# The user starts a new question
turn =2
messages.append({
"role":"user",
"content":"How's the weather in Guangzhou Tomorrow"
})
run_turn(turn, messages)





在 Turn 1 的每个子请求中，都携带了该 Turn 下产生的 reasoning_content 给 API，从而让模型继续之前的思考。response.choices[0].message 携带了 assistant 消息的所有必要字段，包括 content、reasoning_content、tool_calls。简单起见，可以直接用如下代码将消息 append 到 messages 结尾：


messages.append(response.choices[0].message)





这行代码等价于：


messages.append({
'role': 'assistant',
'content': response.choices[0].message.content,
'reasoning_content': response.choices[0].message.reasoning_content,
'tool_calls': response.choices[0].message.tool_calls,
})





且在 Turn 2 的请求中，我们仍然携带着 Turn1 所产生的 reasoning_content 给 API。

该代码的样例输出如下：


Turn 1.1
reasoning_content="The user is asking about the weather in Hangzhou tomorrow. I need to get tomorrow's date first, then call the weather function."
content="Let me check tomorrow's weather in Hangzhou for you. First, let me get tomorrow's date."
tool_calls=[ChatCompletionMessageFunctionToolCall(id='call_00_kw66qNnNto11bSfJVIdlV5Oo', function=Function(arguments='{}', name='get_date'), type='function', index=0)]
tool result for get_date: 2026-04-19

Turn 1.2
reasoning_content="Today is 2026-04-19, so tomorrow is 2026-04-20. Now I'll call the weather function for Hangzhou."
content=''
tool_calls=[ChatCompletionMessageFunctionToolCall(id='call_00_H2SCW6136vWJGq9SQlBuhVt4', function=Function(arguments='{"location": "Hangzhou", "date": "2026-04-20"}', name='get_weather'), type='function', index=0)]
tool result for get_weather: Cloudy 7~13°C

Turn 1.3
reasoning_content='The weather result is in. Let me share this with the user.'
content="Here's the weather forecast for **Hangzhou tomorrow (April 20, 2026)**:\n\n- 🌤 **Condition:** Cloudy \n- 🌡 **Temperature:** 7°C ~ 13°C (45°F ~ 55°F)\n\nIt'll be on the cooler side, so you might want to bring a light jacket if you're heading out! Let me know if you need anything else."
tool_calls=None

Turn 2.1
reasoning_content='The user is asking about the weather in Guangzhou tomorrow. Today is 2026-04-19, so tomorrow is 2026-04-20. I can directly call the weather function.'
content=''
tool_calls=[ChatCompletionMessageFunctionToolCall(id='call_00_8URkLt5NjmNkVKhDmMcNq9Mo', function=Function(arguments='{"location": "Guangzhou", "date": "2026-04-20"}', name='get_weather'), type='function', index=0)]
tool result for get_weather: Cloudy 7~13°C

Turn 2.2
reasoning_content='The weather result for Guangzhou is the same as Hangzhou. Let me share this with the user.'
content="Here's the weather forecast for **Guangzhou tomorrow (April 20, 2026)**:\n\n- 🌤 **Condition:** Cloudy \n- 🌡 **Temperature:** 7°C ~ 13°C (45°F ~ 55°F)\n\nIt'll be cool and cloudy, so a light jacket would be a good idea if you're going out. Let me know if there's anything else you'd like to know!"
tool_calls=None












上一页

Reasonix

下一页

多轮对话






思考模式开关与思考强度控制

输入输出参数

多轮对话拼接
样例代码


工具调用
样例代码












微信公众号





社区

邮箱

Discord

Twitter



更多

GitHub




Copyright © 2026 DeepSeek, Inc.




------
导航页 打开网址