deepseek/openapi/deepseek-chat-completion-api-openapi.yml at main · api-evangelist/deepseek · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
openapi: 3.1.0
info:
  title: DeepSeek Chat Completion API
  description: Creates a model response for the given chat conversation.
  version: 1.0.0
servers:
  - url: https://api.deepseek.com
paths:
  /chat/completions:
    post:
      summary: DeepSeek Create Chat Completion
      description: Creates a model response for the given chat conversation.
      operationId: createChatCompletion
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
                - messages
                - model
              properties:
                messages:
                  type: array
                  items:
                    type: object
                    required:
                      - content
                      - role
                    properties:
                      content:
                        type: string
                        description: The content of the message.
                      role:
                        type: string
                        enum:
                          - system
                          - user
                          - assistant
                        description: The role of the message sender.
                model:
                  type: string
                  enum:
                    - deepseek-chat
                    - deepseek-reasoner
                  description: ID of the model to use.
                frequency_penalty:
                  type: number
                  nullable: true
                  minimum: -2
                  maximum: 2
                  default: 0
                  description: >
                    Positive values penalize new tokens based on their
                    frequency  in the text, reducing repetition.
                max_tokens:
                  type: integer
                  nullable: true
                  minimum: 1
                  maximum: 8192
                  default: 4096
                  description: The maximum number of tokens to generate.
                presence_penalty:
                  type: number
                  nullable: true
                  minimum: -2
                  maximum: 2
                  default: 0
                  description: >
                    Positive values penalize new tokens that appear in the text,
                    encouraging discussion of new topics.
                response_format:
                  type: object
                  nullable: true
                  description: Format of the response.
                  properties:
                    type:
                      type: string
                      description: The format of the response, e.g., text.
                stop:
                  type: object
                  nullable: true
                  description: Sequence where the model stops generating tokens.
                stream:
                  type: boolean
                  nullable: true
                  description: Whether to stream responses as they are generated.
                stream_options:
                  type: object
                  nullable: true
                  description: Options for streaming responses.
                temperature:
                  type: number
                  nullable: true
                  maximum: 2
                  default: 1
                  description: >-
                    Controls randomness in generation (higher values = more
                    random).
                top_p:
                  type: number
                  nullable: true
                  maximum: 1
                  default: 1
                  description: >
                    Nucleus sampling parameter. Tokens are selected from the  top_p probability mass.
                tools:
                  type: array
                  nullable: true
                  items:
                    type: object
                  description: Tools available for the model to use.
                tool_choice:
                  type: object
                  nullable: true
                  description: Configuration for tool selection.
                logprobs:
                  type: boolean
                  nullable: true
                  description: Whether to return log probabilities of output tokens.
                top_logprobs:
                  type: integer
                  nullable: true
                  maximum: 20
                  description: >
                    Number of most likely tokens to return with log
                    probabilities. Requires logprobs to be true.
      responses:
        '200':
          description: Successful response.
          content:
            application/json:
              schema:
                type: object
                required:
                  - id
                  - choices
                  - created
                  - model
                  - system_fingerprint
                  - object
                properties:
                  id:
                    type: string
                    description: Unique identifier for the chat completion.
                  choices:
                    type: array
                    items:
                      type: object
                      description: Array of generated responses.
                  created:
                    type: integer
                    format: int64
                    description: Unix timestamp when the response was created.
                  model:
                    type: string
                    description: Model used for the response.
                  system_fingerprint:
                    type: string
                    description: Backend configuration fingerprint.
                  object:
                    type: string
                    enum:
                      - chat.completion
                    description: Object type.
                  usage:
                    type: object
                    description: Token usage details.
      tags:
        - Chat
tags:
  - name: Chat