对话补全

POST https://api.deepseek.com/chat/completions

根据输入的上下文，来让模型补全对话内容。

Request

application/json

Body

required

messages

object[]

required

model stringrequired

Possible values: [deepseek-chat, deepseek-reasoner]

使用的模型的 ID。您可以使用 deepseek-chat。

frequency_penalty numbernullable

Possible values: >= -2 and <= 2

Default value: 0

介于 -2.0 和 2.0 之间的数字。如果该值为正，那么新 token 会根据其在已有文本中的出现频率受到相应的惩罚，降低模型重复相同内容的可能性。

max_tokens integernullable

Possible values: > 1

介于 1 到 8192 间的整数，限制一次请求中模型生成 completion 的最大 token 数。输入 token 和输出 token 的总长度受模型的上下文长度的限制。

如未指定 max_tokens参数，默认使用 4096。

presence_penalty numbernullable

Possible values: >= -2 and <= 2

Default value: 0

介于 -2.0 和 2.0 之间的数字。如果该值为正，那么新 token 会根据其是否已在已有文本中出现受到相应的惩罚，从而增加模型谈论新主题的可能性。

response_format

object

nullable

stop

object

nullable

stream booleannullable

如果设置为 True，将会以 SSE（server-sent events）的形式以流式发送消息增量。消息流以 data: [DONE] 结尾。

stream_options

object

nullable

流式输出相关选项。只有在 stream 参数为 true 时，才可设置此参数。

include_usage boolean

如果设置为 true，在流式消息最后的 data: [DONE] 之前将会传输一个额外的块。此块上的 usage 字段显示整个请求的 token 使用统计信息，而 choices 字段将始终是一个空数组。所有其他块也将包含一个 usage 字段，但其值为 null。

temperature numbernullable

Possible values: <= 2

Default value: 1

采样温度，介于 0 和 2 之间。更高的值，如 0.8，会使输出更随机，而更低的值，如 0.2，会使其更加集中和确定。我们通常建议可以更改这个值或者更改 top_p，但不建议同时对两者进行修改。

top_p numbernullable

Possible values: <= 1

Default value: 1

作为调节采样温度的替代方案，模型会考虑前 top_p 概率的 token 的结果。所以 0.1 就意味着只有包括在最高 10% 概率中的 token 会被考虑。我们通常建议修改这个值或者更改 temperature，但不建议同时对两者进行修改。

tools

object[]

nullable

tool_choice

object

nullable

logprobs booleannullable

是否返回所输出 token 的对数概率。如果为 true，则在 message 的 content 中返回每个输出 token 的对数概率。

top_logprobs integernullable

Possible values: <= 20

一个介于 0 到 20 之间的整数 N，指定每个输出位置返回输出概率 top N 的 token，且返回这些 token 的对数概率。指定此参数时，logprobs 必须为 true。

Responses

200 (No streaming)
200 (Streaming)

OK, 返回一个 chat completion 对象。

application/json

Schema
Example (from schema)
Example

Schema

id stringrequired

该对话的唯一标识符。

choices

object[]

required

模型生成的 completion 的选择列表。

Array [

finish_reason stringrequired

Possible values: [stop, length, content_filter, tool_calls, insufficient_system_resource]

模型停止生成 token 的原因。

stop：模型自然停止生成，或遇到 stop 序列中列出的字符串。

length ：输出长度达到了模型上下文长度限制，或达到了 max_tokens 的限制。

content_filter：输出内容因触发过滤策略而被过滤。

insufficient_system_resource：系统推理资源不足，生成被打断。

index integerrequired

该 completion 在模型生成的 completion 的选择列表中的索引。

message

object

required

logprobs

object

nullable

required

]

created integerrequired

创建聊天完成时的 Unix 时间戳（以秒为单位）。

model stringrequired

生成该 completion 的模型名。

system_fingerprint stringrequired

This fingerprint represents the backend configuration that the model runs with.

object stringrequired

Possible values: [chat.completion]

对象的类型, 其值为 chat.completion。

usage

object

该对话补全请求的用量信息。

completion_tokens integerrequired

模型 completion 产生的 token 数。

prompt_tokens integerrequired

用户 prompt 所包含的 token 数。该值等于 prompt_cache_hit_tokens + prompt_cache_miss_tokens

prompt_cache_hit_tokens integerrequired

用户 prompt 中，命中上下文缓存的 token 数。

prompt_cache_miss_tokens integerrequired

用户 prompt 中，未命中上下文缓存的 token 数。

total_tokens integerrequired

该请求中，所有 token 的数量（prompt + completion）。

completion_tokens_details

object

{
  "id": "string",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "string",
        "reasoning_content": "string",
        "tool_calls": [
          {
            "id": "string",
            "type": "function",
            "function": {
              "name": "string",
              "arguments": "string"
            }
          }
        ],
        "role": "assistant"
      },
      "logprobs": {
        "content": [
          {
            "token": "string",
            "logprob": 0,
            "bytes": [
              0
            ],
            "top_logprobs": [
              {
                "token": "string",
                "logprob": 0,
                "bytes": [
                  0
                ]
              }
            ]
          }
        ]
      }
    }
  ],
  "created": 0,
  "model": "string",
  "system_fingerprint": "string",
  "object": "chat.completion",
  "usage": {
    "completion_tokens": 0,
    "prompt_tokens": 0,
    "prompt_cache_hit_tokens": 0,
    "prompt_cache_miss_tokens": 0,
    "total_tokens": 0,
    "completion_tokens_details": {
      "reasoning_tokens": 0
    }
  }
}

{
  "id": "930c60df-bf64-41c9-a88e-3ec75f81e00e",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "Hello! How can I help you today?",
        "role": "assistant"
      }
    }
  ],
  "created": 1705651092,
  "model": "deepseek-chat",
  "object": "chat.completion",
  "usage": {
    "completion_tokens": 10,
    "prompt_tokens": 16,
    "total_tokens": 26
  }
}

OK, 返回包含一系列 chat completion chunk 对象的流式输出。

text/event-stream

Schema
Example

Schema

Array [

id stringrequired

该对话的唯一标识符。

choices

object[]

required

模型生成的 completion 的选择列表。

Array [

delta

object

required

流式返回的一个 completion 增量。

content stringnullable

completion 增量的内容。

reasoning_content stringnullable

仅适用于 deepseek-reasoner 模型。内容为 assistant 消息中在最终答案之前的推理内容。

role string

Possible values: [assistant]

产生这条消息的角色。

finish_reason stringnullablerequired

Possible values: [stop, length, content_filter, tool_calls, insufficient_system_resource]

模型停止生成 token 的原因。

stop：模型自然停止生成，或遇到 stop 序列中列出的字符串。

length ：输出长度达到了模型上下文长度限制，或达到了 max_tokens 的限制。

content_filter：输出内容因触发过滤策略而被过滤。

insufficient_system_resource: 由于后端推理资源受限，请求被打断。

index integerrequired

该 completion 在模型生成的 completion 的选择列表中的索引。

]

created integerrequired

创建聊天完成时的 Unix 时间戳（以秒为单位）。流式响应的每个 chunk 的时间戳相同。

model stringrequired

生成该 completion 的模型名。

system_fingerprint stringrequired

This fingerprint represents the backend configuration that the model runs with.

object stringrequired

Possible values: [chat.completion.chunk]

对象的类型, 其值为 chat.completion.chunk。

]

data: {"id": "1f633d8bfc032625086f14113c411638", "choices": [{"index": 0, "delta": {"content": "", "role": "assistant"}, "finish_reason": null, "logprobs": null}], "created": 1718345013, "model": "deepseek-chat", "system_fingerprint": "fp_a49d71b8a1", "object": "chat.completion.chunk", "usage": null}

data: {"choices": [{"delta": {"content": "Hello", "role": "assistant"}, "finish_reason": null, "index": 0, "logprobs": null}], "created": 1718345013, "id": "1f633d8bfc032625086f14113c411638", "model": "deepseek-chat", "object": "chat.completion.chunk", "system_fingerprint": "fp_a49d71b8a1"}

data: {"choices": [{"delta": {"content": "!", "role": "assistant"}, "finish_reason": null, "index": 0, "logprobs": null}], "created": 1718345013, "id": "1f633d8bfc032625086f14113c411638", "model": "deepseek-chat", "object": "chat.completion.chunk", "system_fingerprint": "fp_a49d71b8a1"}

data: {"choices": [{"delta": {"content": " How", "role": "assistant"}, "finish_reason": null, "index": 0, "logprobs": null}], "created": 1718345013, "id": "1f633d8bfc032625086f14113c411638", "model": "deepseek-chat", "object": "chat.completion.chunk", "system_fingerprint": "fp_a49d71b8a1"}

data: {"choices": [{"delta": {"content": " can", "role": "assistant"}, "finish_reason": null, "index": 0, "logprobs": null}], "created": 1718345013, "id": "1f633d8bfc032625086f14113c411638", "model": "deepseek-chat", "object": "chat.completion.chunk", "system_fingerprint": "fp_a49d71b8a1"}

data: {"choices": [{"delta": {"content": " I", "role": "assistant"}, "finish_reason": null, "index": 0, "logprobs": null}], "created": 1718345013, "id": "1f633d8bfc032625086f14113c411638", "model": "deepseek-chat", "object": "chat.completion.chunk", "system_fingerprint": "fp_a49d71b8a1"}

data: {"choices": [{"delta": {"content": " assist", "role": "assistant"}, "finish_reason": null, "index": 0, "logprobs": null}], "created": 1718345013, "id": "1f633d8bfc032625086f14113c411638", "model": "deepseek-chat", "object": "chat.completion.chunk", "system_fingerprint": "fp_a49d71b8a1"}

data: {"choices": [{"delta": {"content": " you", "role": "assistant"}, "finish_reason": null, "index": 0, "logprobs": null}], "created": 1718345013, "id": "1f633d8bfc032625086f14113c411638", "model": "deepseek-chat", "object": "chat.completion.chunk", "system_fingerprint": "fp_a49d71b8a1"}

data: {"choices": [{"delta": {"content": " today", "role": "assistant"}, "finish_reason": null, "index": 0, "logprobs": null}], "created": 1718345013, "id": "1f633d8bfc032625086f14113c411638", "model": "deepseek-chat", "object": "chat.completion.chunk", "system_fingerprint": "fp_a49d71b8a1"}

data: {"choices": [{"delta": {"content": "?", "role": "assistant"}, "finish_reason": null, "index": 0, "logprobs": null}], "created": 1718345013, "id": "1f633d8bfc032625086f14113c411638", "model": "deepseek-chat", "object": "chat.completion.chunk", "system_fingerprint": "fp_a49d71b8a1"}

data: {"choices": [{"delta": {"content": "", "role": null}, "finish_reason": "stop", "index": 0, "logprobs": null}], "created": 1718345013, "id": "1f633d8bfc032625086f14113c411638", "model": "deepseek-chat", "object": "chat.completion.chunk", "system_fingerprint": "fp_a49d71b8a1", "usage": {"completion_tokens": 9, "prompt_tokens": 17, "total_tokens": 26}}

data: [DONE]

OpenAI SDK

from openai import OpenAI

# for backward compatibility, you can still use `https://api.deepseek.com/v1` as `base_url`.
client = OpenAI(api_key="<your API key>", base_url="https://api.deepseek.com")

response = client.chat.completions.create(
    model="deepseek-chat",
    messages=[
        {"role": "system", "content": "You are a helpful assistant"},
        {"role": "user", "content": "Hello"},
  ],
    max_tokens=1024,
    temperature=0.7,
    stream=False
)

print(response.choices[0].message.content)

REQUESTS
HTTP.CLIENT

import requests
import json

url = "https://api.deepseek.com/chat/completions"

payload = json.dumps({
  "messages": [
    {
      "content": "You are a helpful assistant",
      "role": "system"
    },
    {
      "content": "Hi",
      "role": "user"
    }
  ],
  "model": "deepseek-chat",
  "frequency_penalty": 0,
  "max_tokens": 2048,
  "presence_penalty": 0,
  "response_format": {
    "type": "text"
  },
  "stop": None,
  "stream": False,
  "stream_options": None,
  "temperature": 1,
  "top_p": 1,
  "tools": None,
  "tool_choice": "none",
  "logprobs": False,
  "top_logprobs": None
})
headers = {
  'Content-Type': 'application/json',
  'Accept': 'application/json',
  'Authorization': 'Bearer <TOKEN>'
}

response = requests.request("POST", url, headers=headers, data=payload)

print(response.text)

ResponseClear

Click the Send API Request button above and see the response here!

对话补全

https://api.deepseek.com/chat/completions

Request​

Body

Responses​

Request

Responses