对话补全 - DeepSeek API

根据输入的上下文，来让模型补全对话内容。

curl --location --request POST 'https://api.deepseek.com/chat/completions' \ --header 'Authorization: Bearer ' \ --header 'Content-Type: application/json' \ --data-raw '{ "messages": [ { "content": "You are a helpful assistant", "role": "system" }, { "content": "你是谁？", "role": "user" } ], "model": "deepseek-chat", "frequency_penalty": 0, "max_tokens": 2048, "presence_penalty": 0, "response_format": { "type": "text" }, "stop": null, "stream": false, "stream_options": null, "temperature": 1, "top_p": 1, "tools": null, "tool_choice": "none", "logprobs": false, "top_logprobs": null }'

{ "id": "e137bb42-7580-4cb8-88ba-825209cf966b", "choices": [ { "index": 0, "message": { "role": "assistant", "content": "Hello! How can I assist you today? 😊" }, "logprobs": null, "finish_reason": "stop" } ], "created": 1739112811, "model": "deepseek-chat", "system_fingerprint": "fp_3a5790e1b4", "object": "chat.completion", "usage": { "prompt_tokens": 9, "completion_tokens": 11, "total_tokens": 20, "prompt_tokens_details": { "cached_tokens": 0 }, "prompt_cache_hit_tokens": 0, "prompt_cache_miss_tokens": 9 } }

请求参数

Authorization

在 Header 添加参数

Authorization

，其值为在 Bearer 之后拼接 Token

示例：

Authorization: Bearer ********************

Header 参数

Content-Type

string

必需

示例值:

application/json

Authorization

string

必需

示例值:

Bearer {{API_KEY}}

Body 参数application/json

messages

array [oneOf]

对话的消息列表

必需

>= 1 items

object

System message

可选

object

User message

可选

object

Assistant message

可选

object

Tool message

可选

model

enum<string>

使用的 AI 模型

必需

枚举值:

deepseek-chatdeepseek-reasoner

frequency_penalty

number | null

可选

max_tokens

integer | null

可选

presence_penalty

number | null

可选

response_format

object | null

可选

type

string | null

可选

stop

可选

One of

string | null

array[string] | null

stream

boolean | null

是否启用流式传输

可选

stream_options

object | null

可选

include_usage

boolean

可选

temperature

number | null

可选

top_p

number | null

可选

tools

null

可选

tool_choice

可选

One of

string

object

logprobs

boolean | null

可选

top_logprobs

integer | null

可选

示例

返回响应

🟢200No streaming

application/json

OK, 返回一个 chat completion 对象。

Body

string

必需

choices

array [object {4}]

必需

finish_reason

string

可选

index

integer

可选

message

object

可选

logprobs

object | null

必需

created

integer

必需

model

string

必需

system_fingerprint

string

必需

object

string

必需

usage

object

可选

completion_tokens

integer

必需

prompt_tokens

integer

必需

prompt_cache_hit_tokens

integer

必需

prompt_cache_miss_tokens

integer

必需

total_tokens

integer

必需

completion_tokens_details

object

可选

🟢200Streaming