更新时间:2025-07-28 GMT+08:00

DeepSeek

功能介绍

DeepSeek API是基于DeepSeek大模型推出的接口服务,它支持多场景文本交互,能够快速生成高质量对话、文案、故事等内容,可用于文本摘要、智能问答、内容创作等场景。

URI

NLP推理服务支持使用盘古推理接口(V1推理接口)调用,也支持使用业界通用的OpenAi格式接口(V2推理接口)调用。

V1接口、V2接口的鉴权方式不同,请求体和返回体略有差异。

表1 NLP服务推理接口

API分类

API访问路径(URI)

V1推理接口

POST /v1/{project_id}/deployments/{deployment_id}/chat/completions

V2推理接口

POST /api/v2/chat/completions

表2 V1推理接口路径参数

参数

是否必选

参数类型

描述

project_id

String

项目ID,获取方法请参见获取项目ID

deployment_id

String

模型的部署ID,获取方法请参见获取模型部署ID

请求参数

V1、V2推理接口的鉴权方式不同,请求参数与响应参数也有不同,说明如下:

Header参数

  1. V1接口支持Token鉴权方式,也支持API Key鉴权方式。两种鉴权方式请求Header参数说明如下:
表3 请求Header参数(Token认证)

参数

是否必选

参数类型

描述

X-Auth-Token

String

用户Token。

用于获取操作API的权限。获取Token接口响应消息头中X-Subject-Token的值即为Token。

Content-Type

String

发送的实体的MIME类型,参数值为“application/json”。

表4 请求Header参数(API Key认证)

参数

是否必选

参数类型

描述

X-Apig-AppCode

String

API Key值。

用于获取操作API的权限。API Key认证响应消息头中X-Apig-AppCode的值即为API Key。

Content-Type

String

发送的实体的MIME类型,参数值为“application/json”。

  1. V2接口只支持API Key鉴权方式。请求Header参数见表5 V2接口请求Header参数
表5 V2接口请求Header参数(OpenAI格式的API Key认证)

参数

是否必选

参数类型

描述

Authorization

String

用户创建应用接入获取的API Key,拼接“Bearer ”后的字符串。示例:Bearer d59******9C3

Content-Type

String

发送的实体的MIME类型,参数值为“application/json”。

请求Body参数

V1、V2推理接口请求Body参数一致,如表6

表6 请求Body参数

参数

是否必选

参数类型

描述

messages

Array of ChatCompletionMessageParam objects

多轮对话问答对,包含两个属性:role和content。

  • role表示对话的角色,取值是system或user。

    如果需要模型以某个人设形象回答问题,可以将role参数设置为system。不使用人设时,可设置为user。在一次会话请求中,人设只需要设置一次。

  • content表示对话的内容,可以是任意文本。

messages参数可以帮助模型根据对话的上下文生成合适的回复。

model

String

使用的模型ID,根据所部署的模型填写,填写DeepSeek-R1或DeepSeek-V3。

stream

boolean

流式开关。流式输出协议为SSE(Server-Sent Events)协议。

如果开启流式,请赋值true。开启流式开关后,API会在生成文本的过程中,实时地将生成的文本发送给客户端,而不是等到生成完成后一次性将所有文本发送给客户端。

缺省值:false

temperature

Float

用于控制生成文本的多样性和创造力。

控制采样随机性的浮点数。一般来说,temperature越低,适合完成确定性的任务。temperature越高,如0.9,适合完成创造性的任务。值为 0 意味着贪婪采样。当取值超过1,会大概率出现效果不可用问题。

temperature参数可以影响语言模型输出的质量和多样性,但也不是唯一的因素。还有其他一些参数,如top_p参数也可以用来调整语言模型的行为和偏好,但不建议同时更改这两temperature和top_p。

最小值:0,建议不要低于1e-5

最大值:1.0

缺省值:1.0

top_p

Float

核采样参数。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。0.1 就意味着只有包括在最高 10% 概率中的 token 会被考虑。 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。

取值范围:(0.0, 1.0]

缺省值:0.8

说明:

token是指模型处理和生成文本的基本单位。token可以是词或者字符的片段。模型的输入和输出的文本都会被转换成token,然后根据模型的概率分布进行采样或者计算。

max_tokens

Integer

生成文本的最大输出token数量。

输入的文本加上生成的文本总量不能超过模型所能处理的最大长度。

最小值:1

最大值:8192

缺省值:4096

presence_penalty

Float

用于调整模型对新Token的处理方式。即如果一个Token已经在之前的文本中出现过,那么模型在生成这个Token时会受到一定的惩罚。当presence_penalty的值为正数时,模型会更倾向于生成新的、未出现过的Token,即模型会更倾向于谈论新的话题。

最小值:-2

最大值:2

缺省值:0 (表示该参数未生效)

frequency_penalty

Float

用于调整模型对频繁出现的Token的处理方式。即如果一个Token在训练集中出现的频率较高,那么模型在生成这个Token时会受到一定的惩罚。当frequency_penalty的值为正数时,模型会更倾向于生成出现频率较低的Token,即模型会更倾向于使用不常见的词汇。

最小值:-2

最大值:2

缺省值:0 (表示该参数未生效)

表7 ChatCompletionMessageParam

参数

是否必选

参数类型

描述

role

String

对话的角色,默认取值范围:system、user、assistant、tool、function。支持自定义。

如果需要模型以某个人设形象回答问题,可以将role参数设置为system。不使用人设时,可设置为user。

返回参数时,为固定值:assistant

在一次会话请求中,人设只需要设置一次。

content

String

对话的内容,可以是任意文本,单位token。

设置多轮对话时,message中content个数不能超过20。

最小长度:1

最大长度:不同模型支持的token长度。

缺省值:None

响应参数

非流式

状态码: 200

表8 响应Body参数

参数

参数类型

描述

id

String

用来标识每个响应的唯一字符串。形式为:"chatcmpl-{random_uuid()}"

object

String

固定为"chat.completion"

created

Integer

响应生成的时间,单位:s。

model

String

请求模型ID。

choices

Array ofChatCompletionResponseChoice objects

生成的文本列表。

usage

UsageInfo object

该对话请求的token用量信息。该参数可以帮助用户了解和控制模型的使用情况,避免超出Tokens限制。

prompt_logprobs

Object

输入文本以及对应token的对数概率信息。

缺省值:null

表9 ChatCompletionResponseChoice

参数

参数类型

描述

message

ChatMessage object

生成的文本内容。

index

Integer

生成的文本在列表中的索引,从0开始。

finish_reason

String

模型停止生成 token 的原因。

取值范围:[stop, length, content_filter, tool_calls, insufficient_system_resource]

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。

tool_calls:模型决定调用外部工具(函数/API)来完成任务。

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

缺省值:stop

logprobs

Object

评估指标,表示推理输出的置信度。

缺省值:null

stop_reason

Union[Integer, String]

导致生成停止的token id或者字符串。如果是遇到EOS token则返回默认值。如果是因为用户请求参数参数中指定的stop参数中的字符串或者token id,则返回对应的字符串或者token id。不是openai接口标准字段,但vllm接口支持。

缺省值:None

表10 UsageInfo

参数

参数类型

描述

prompt_tokens

Number

用户prompt中所包含的token数。

total_tokens

Number

该次对话请求中,所有token的数量。

completion_tokens

Number

推理模型所产生的答案的token数量。

表11 ChatMessage

参数

参数类型

描述

role

String

生成这条消息的角色。固定为:assistant。

content

String

对话的内容。

最小长度:1

最大长度:不同模型支持的token长度。

reasoning_content

String

内容为在最终答案之前的推理内容(模型的思考过程)。

说明:

仅适用于 DeepSeek-R1 模型。

流式(stream参数为true)

状态码: 200

表12 流式输出的数据单元

参数

参数类型

描述

data

CompletionStreamResponse object

stream=true时,模型生成的消息以流式形式返回。生成的内容以增量的方式逐步发送回来,每个data字段均包含一部分生成的内容,直到所有data返回,响应结束。

表13 CompletionStreamResponse

参数

参数类型

描述

id

String

该对话的唯一标识符。

created

Integer

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

String

生成该 completion 的模型名。

object

String

对象的类型, 其值为 chat.completion.chunk。

choices

ChatCompletionResponseStreamChoice

模型生成的 completion 的选择列表。

表14 ChatCompletionResponseStreamChoice

参数

参数类型

描述

index

Integer

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

finish_reason

String

模型停止生成 token 的原因。

取值范围:[stop, length, content_filter, tool_calls, insufficient_system_resource]

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。

tool_calls:模型决定调用外部工具(函数/API)来完成任务。

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

状态码: 400

表15 响应Body参数

参数

参数类型

描述

error_code

String

错误码。

error_msg

String

错误信息。

请求示例

  • 非流式
    V1推理接口:
    POST https://{endpoint}/v1/{project_id}/alg-infer/3rdnlp/service/{deployment_id}/v1/chat/completions
    
    Request Header:   
    Content-Type: application/json   
    X-Auth-Token: MIINRwYJKoZIhvcNAQcCoIINODCCDTQCAQExDTALBglghkgBZQMEAgEwgguVBgkqhkiG...      
    
    Request Body:
    {
      "model":"DeepSeek-V3",
      "messages":[
        {
          "role":"user",
          "content":"你好"
        }]
    }
    V2推理接口:
    POST https://{endpoint}/api/v2/chat/completions
    
    Request Header:   
    Content-Type: application/json   
    Authorization: Bearer 201ca68f-45f9-4e19-8fa4-831e...  
    
    Request Body:
    {
      "model":"DeepSeek-V3",
      "messages":[
        {
          "role":"user",
          "content":"你好"
        }]
    }
  • 流式(stream参数为true)
    V1推理接口:
    POST https://{endpoint}/v1/{project_id}/alg-infer/3rdnlp/service/{deployment_id}/v1/chat/completions
    
    Request Header:   
    Content-Type: application/json   
    X-Auth-Token: MIINRwYJKoZIhvcNAQcCoIINODCCDTQCAQExDTALBglghkgBZQMEAgEwgguVBgkqhkiG...      
    
    Request Body:
    {
      "model":"DeepSeek-V3",
      "messages":[
        {
          "role":"user",
          "content":"你好"
        }],
      "stream":true
    }
    V2推理接口:
    POST https://{endpoint}/api/v2/chat/completions
    
    Request Header:   
    Content-Type: application/json   
    Authorization: Bearer 201ca68f-45f9-4e19-8fa4-831e...  
    
    Request Body:
    {
      "model":"DeepSeek-V3",
      "messages":[
        {
          "role":"user",
          "content":"你好"
        }],
      "stream":true
    }

响应示例

状态码: 200

OK

  • 非流式问答响应
     {
        "id": "chat-9a75fc02e45d48db94f94ce38277beef",
        "object": "chat.completion",
        "created": 1743403365,
        "model": "DeepSeek-V3",
        "choices": [
            {
                "index": 0,
                "message": {
                    "role": "assistant",
                    "content": "你好!有什么我可以帮助你的吗?",
                    "tool_calls": []
                },
                "finish_reason": "stop"
            }
        ],
        "usage": {
            "prompt_tokens": 64,
            "total_tokens": 73,
            "completion_tokens": 9
        }
    }
  • 带有思维链的非流式问答响应
    {
        "id": "81c34733-0e7c-4b4b-a044-1e1fcd54b8db",
        "model": "deepseek-r1_32k",
        "created": 1747485310,
        "choices": [
            {
                "index": 0,
                "message": {
                    "role": "assistant",
                    "content": "\n\n你好!很高兴见到你,有什么我可以帮忙的吗?",
                    "reasoning_content": "嗯,用户刚刚发了一个简短的“你好”,这是在用中文打招呼。首先我需要确认他们的需求是什么,可能只是想测试一下回复,或者有具体的问题要问。另外,我需要考虑是否需要用英文回应,但用户用了中文,用中文回复更合适吧。\n\n然后,我要确保回复友好且符合指南,不能涉及敏感内容。用户可能期待进一步的对话或者有问题需要帮助。这时候应该保持开放式的回答,邀请他们提出具体的问题或需求。比如,可以说“你好!很高兴见到你,有什么我可以帮忙的吗?”这样既礼貌又主动提供帮助。\n\n另外,注意避免使用任何格式或markdown,保持自然简洁。可能存在用户刚接触这个平台,不熟悉如何提问的情况,所以用鼓励的语气可能会更好。检查有没有任何拼写或语法错误,确保回复正确无误。\n",
                    "tool_calls": [
                    ]
                },
                "finish_reason": "stop"
            }
        ],
        "usage": {
            "completion_tokens": 184,
            "prompt_tokens": 6,
            "total_tokens": 190
        }
    }
  • 流式问答响应
    V1推理接口返回体:
    data:{"id":"chat-97313a4bc0a342558364345de0380291","object":"chat.completion.chunk","created":1743404317,"model":"DeepSeek-V3","choices":[{"index":0,"message":{"role":"assistant"},"logprobs":null,"finish_reason":null}]
    
    data:{"id":"chat-97313a4bc0a342558364345de0380291","object":"chat.completion.chunk","created":1743404317,"model":"DeepSeek-V3","choices":[{"index":0,"message":{"content":"你好"},"logprobs":null,"finish_reason":null}]}
    
    data:{"id":"chat-97313a4bc0a342558364345de0380291","object":"chat.completion.chunk","created":1743404317,"model":"DeepSeek-V3","choices":[{"index":0,"message":{"content":",有什么我能帮您的吗?"},"logprobs":null,"finish_reason":"stop","stop_reason":null}]}
    
    data:[DONE]
    V2推理接口返回体:
    data:{"id":"chat-97313a4bc0a342558364345de0380291","object":"chat.completion.chunk","created":1743404317,"model":"DeepSeek-V3","choices":[{"index":0,"delta":{"role":"assistant"},"logprobs":null,"finish_reason":null}]
    
    data:{"id":"chat-97313a4bc0a342558364345de0380291","object":"chat.completion.chunk","created":1743404317,"model":"DeepSeek-V3","choices":[{"index":0,"delta":{"content":"你好"},"logprobs":null,"finish_reason":null}]}
    
    data:{"id":"chat-97313a4bc0a342558364345de0380291","object":"chat.completion.chunk","created":1743404317,"model":"DeepSeek-V3","choices":[{"index":0,"delta":{"content":",有什么我能帮您的吗?"},"logprobs":null,"finish_reason":"stop","stop_reason":null}]}
    
    data:[DONE]
  • 带有思维链的流式问答响应
    V1推理接口返回体:
    data:{"id":"chat-cc897cfa872a4fc993a803bbddf9268a","object":"chat.completion.chunk","created":1747485542,"model":"DeepSeek-R1","choices":[{"index":0,"message":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}],"usage":{"prompt_tokens":6,"total_tokens":6,"completion_tokens":0}}
    
    data:{"id":"chat-cc897cfa872a4fc993a803bbddf9268a","object":"chat.completion.chunk","created":1747485542,"model":"DeepSeek-R1","choices":[{"index":0,"message":{"reasoning_content":"嗯"},"logprobs":null,"finish_reason":null}],"usage":{"prompt_tokens":6,"total_tokens":7,"completion_tokens":1}}
    
    data:{"id":"chat-cc897cfa872a4fc993a803bbddf9268a","object":"chat.completion.chunk","created":1747485542,"model":"DeepSeek-R1","choices":[{"index":0,"message":{"reasoning_content":","},"logprobs":null,"finish_reason":null}],"usage":{"prompt_tokens":6,"total_tokens":8,"completion_tokens":2}}
    
    data:{"id":"chat-cc897cfa872a4fc993a803bbddf9268a","object":"chat.completion.chunk","created":1747485542,"model":"DeepSeek-R1","choices":[{"index":0,"message":{"reasoning_content":"用户发"},"logprobs":null,"finish_reason":null}],"usage":{"prompt_tokens":6,"total_tokens":10,"completion_tokens":4}}
    
    ...
    
    
    data:{"id":"chat-cc897cfa872a4fc993a803bbddf9268a","object":"chat.completion.chunk","created":1747485542,"model":"DeepSeek-R1","choices":[{"index":0,"message":{"reasoning_content":"生成"},"logprobs":null,"finish_reason":null}],"usage":{"prompt_tokens":6,"total_tokens":185,"completion_tokens":179}}
    
    data:{"id":"chat-cc897cfa872a4fc993a803bbddf9268a","object":"chat.completion.chunk","created":1747485542,"model":"DeepSeek-R1","choices":[{"index":0,"message":{"reasoning_content":"最终的"},"logprobs":null,"finish_reason":null}],"usage":{"prompt_tokens":6,"total_tokens":186,"completion_tokens":180}}
    
    data:{"id":"chat-cc897cfa872a4fc993a803bbddf9268a","object":"chat.completion.chunk","created":1747485542,"model":"DeepSeek-R1","choices":[{"index":0,"message":{"reasoning_content":"回复。\n"},"logprobs":null,"finish_reason":null}],"usage":{"prompt_tokens":6,"total_tokens":188,"completion_tokens":182}}
    
    data:{"id":"chat-cc897cfa872a4fc993a803bbddf9268a","object":"chat.completion.chunk","created":1747485542,"model":"DeepSeek-R1","choices":[{"index":0,"message":{"content":"\n\n你好"},"logprobs":null,"finish_reason":null}],"usage":{"prompt_tokens":6,"total_tokens":191,"completion_tokens":185}}
    
    data:{"id":"chat-cc897cfa872a4fc993a803bbddf9268a","object":"chat.completion.chunk","created":1747485542,"model":"DeepSeek-R1","choices":[{"index":0,"message":{"content":"!很高兴"},"logprobs":null,"finish_reason":null}],"usage":{"prompt_tokens":6,"total_tokens":193,"completion_tokens":187}}
    
    data:{"id":"chat-cc897cfa872a4fc993a803bbddf9268a","object":"chat.completion.chunk","created":1747485542,"model":"DeepSeek-R1","choices":[{"index":0,"message":{"content":"见到"},"logprobs":null,"finish_reason":null}],"usage":{"prompt_tokens":6,"total_tokens":194,"completion_tokens":188}}
    
    data:{"id":"chat-cc897cfa872a4fc993a803bbddf9268a","object":"chat.completion.chunk","created":1747485542,"model":"DeepSeek-R1","choices":[{"index":0,"message":{"content":"你"},"logprobs":null,"finish_reason":null}],"usage":{"prompt_tokens":6,"total_tokens":195,"completion_tokens":189}}
    
    data:{"id":"chat-cc897cfa872a4fc993a803bbddf9268a","object":"chat.completion.chunk","created":1747485542,"model":"DeepSeek-R1","choices":[{"index":0,"message":{"content":",有什么"},"logprobs":null,"finish_reason":null}],"usage":{"prompt_tokens":6,"total_tokens":197,"completion_tokens":191}}
    
    data:{"id":"chat-cc897cfa872a4fc993a803bbddf9268a","object":"chat.completion.chunk","created":1747485542,"model":"DeepSeek-R1","choices":[{"index":0,"message":{"content":"我可以帮"},"logprobs":null,"finish_reason":null}],"usage":{"prompt_tokens":6,"total_tokens":199,"completion_tokens":193}}
    
    data:{"id":"chat-cc897cfa872a4fc993a803bbddf9268a","object":"chat.completion.chunk","created":1747485542,"model":"DeepSeek-R1","choices":[{"index":0,"message":{"content":"您的吗"},"logprobs":null,"finish_reason":null}],"usage":{"prompt_tokens":6,"total_tokens":201,"completion_tokens":195}}
    
    data:{"id":"chat-cc897cfa872a4fc993a803bbddf9268a","object":"chat.completion.chunk","created":1747485542,"model":"DeepSeek-R1","choices":[{"index":0,"message":{"content":"?"},"logprobs":null,"finish_reason":"stop","stop_reason":null}],"usage":{"prompt_tokens":6,"total_tokens":203,"completion_tokens":197}}
    
    data:{"id":"chat-cc897cfa872a4fc993a803bbddf9268a","object":"chat.completion.chunk","created":1747485542,"model":"DeepSeek-R1","choices":[],"usage":{"prompt_tokens":6,"total_tokens":203,"completion_tokens":197}}
    
    data:[DONE]
    V2推理接口返回体:
    data:{"id":"chat-cc897cfa872a4fc993a803bbddf9268a","object":"chat.completion.chunk","created":1747485542,"model":"DeepSeek-R1","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}],"usage":{"prompt_tokens":6,"total_tokens":6,"completion_tokens":0}}
    
    data:{"id":"chat-cc897cfa872a4fc993a803bbddf9268a","object":"chat.completion.chunk","created":1747485542,"model":"DeepSeek-R1","choices":[{"index":0,"delta":{"reasoning_content":"嗯"},"logprobs":null,"finish_reason":null}],"usage":{"prompt_tokens":6,"total_tokens":7,"completion_tokens":1}}
    
    data:{"id":"chat-cc897cfa872a4fc993a803bbddf9268a","object":"chat.completion.chunk","created":1747485542,"model":"DeepSeek-R1","choices":[{"index":0,"delta":{"reasoning_content":","},"logprobs":null,"finish_reason":null}],"usage":{"prompt_tokens":6,"total_tokens":8,"completion_tokens":2}}
    
    data:{"id":"chat-cc897cfa872a4fc993a803bbddf9268a","object":"chat.completion.chunk","created":1747485542,"model":"DeepSeek-R1","choices":[{"index":0,"delta":{"reasoning_content":"用户发"},"logprobs":null,"finish_reason":null}],"usage":{"prompt_tokens":6,"total_tokens":10,"completion_tokens":4}}
    
    ...
    
    
    data:{"id":"chat-cc897cfa872a4fc993a803bbddf9268a","object":"chat.completion.chunk","created":1747485542,"model":"DeepSeek-R1","choices":[{"index":0,"delta":{"reasoning_content":"生成"},"logprobs":null,"finish_reason":null}],"usage":{"prompt_tokens":6,"total_tokens":185,"completion_tokens":179}}
    
    data:{"id":"chat-cc897cfa872a4fc993a803bbddf9268a","object":"chat.completion.chunk","created":1747485542,"model":"DeepSeek-R1","choices":[{"index":0,"delta":{"reasoning_content":"最终的"},"logprobs":null,"finish_reason":null}],"usage":{"prompt_tokens":6,"total_tokens":186,"completion_tokens":180}}
    
    data:{"id":"chat-cc897cfa872a4fc993a803bbddf9268a","object":"chat.completion.chunk","created":1747485542,"model":"DeepSeek-R1","choices":[{"index":0,"delta":{"reasoning_content":"回复。\n"},"logprobs":null,"finish_reason":null}],"usage":{"prompt_tokens":6,"total_tokens":188,"completion_tokens":182}}
    
    data:{"id":"chat-cc897cfa872a4fc993a803bbddf9268a","object":"chat.completion.chunk","created":1747485542,"model":"DeepSeek-R1","choices":[{"index":0,"delta":{"content":"\n\n你好"},"logprobs":null,"finish_reason":null}],"usage":{"prompt_tokens":6,"total_tokens":191,"completion_tokens":185}}
    
    data:{"id":"chat-cc897cfa872a4fc993a803bbddf9268a","object":"chat.completion.chunk","created":1747485542,"model":"DeepSeek-R1","choices":[{"index":0,"delta":{"content":"!很高兴"},"logprobs":null,"finish_reason":null}],"usage":{"prompt_tokens":6,"total_tokens":193,"completion_tokens":187}}
    
    data:{"id":"chat-cc897cfa872a4fc993a803bbddf9268a","object":"chat.completion.chunk","created":1747485542,"model":"DeepSeek-R1","choices":[{"index":0,"delta":{"content":"见到"},"logprobs":null,"finish_reason":null}],"usage":{"prompt_tokens":6,"total_tokens":194,"completion_tokens":188}}
    
    data:{"id":"chat-cc897cfa872a4fc993a803bbddf9268a","object":"chat.completion.chunk","created":1747485542,"model":"DeepSeek-R1","choices":[{"index":0,"delta":{"content":"你"},"logprobs":null,"finish_reason":null}],"usage":{"prompt_tokens":6,"total_tokens":195,"completion_tokens":189}}
    
    data:{"id":"chat-cc897cfa872a4fc993a803bbddf9268a","object":"chat.completion.chunk","created":1747485542,"model":"DeepSeek-R1","choices":[{"index":0,"delta":{"content":",有什么"},"logprobs":null,"finish_reason":null}],"usage":{"prompt_tokens":6,"total_tokens":197,"completion_tokens":191}}
    
    data:{"id":"chat-cc897cfa872a4fc993a803bbddf9268a","object":"chat.completion.chunk","created":1747485542,"model":"DeepSeek-R1","choices":[{"index":0,"delta":{"content":"我可以帮"},"logprobs":null,"finish_reason":null}],"usage":{"prompt_tokens":6,"total_tokens":199,"completion_tokens":193}}
    
    data:{"id":"chat-cc897cfa872a4fc993a803bbddf9268a","object":"chat.completion.chunk","created":1747485542,"model":"DeepSeek-R1","choices":[{"index":0,"delta":{"content":"您的吗"},"logprobs":null,"finish_reason":null}],"usage":{"prompt_tokens":6,"total_tokens":201,"completion_tokens":195}}
    
    data:{"id":"chat-cc897cfa872a4fc993a803bbddf9268a","object":"chat.completion.chunk","created":1747485542,"model":"DeepSeek-R1","choices":[{"index":0,"delta":{"content":"?"},"logprobs":null,"finish_reason":"stop","stop_reason":null}],"usage":{"prompt_tokens":6,"total_tokens":203,"completion_tokens":197}}
    
    data:{"id":"chat-cc897cfa872a4fc993a803bbddf9268a","object":"chat.completion.chunk","created":1747485542,"model":"DeepSeek-R1","choices":[],"usage":{"prompt_tokens":6,"total_tokens":203,"completion_tokens":197}}
    
    data:[DONE]
  • 流式问答,内容审核不通过时的响应
    event:moderation data:{"suggestion":"block","reply":"作为AI语言模型,我的目标是以积极、正向和安全的方式提供帮助和信息,您的问题超出了我的回答范围。"}
    
    data:[DONE]

状态码

请参见状态码

错误码

请参见错误码