openapi.yaml

openapi: 3.0.0
info:
  title: SiliconFlow API
  description: The SiliconFlow REST API
  version: "1.0.0"
  contact:
    name: SiliconFlow Support
    url: https://www.siliconflow.cn/
  license:
    name: MIT
    url: https://github.com/siliconflow/siliconcloud/blob/main/LICENSE
servers:
  - url: https://api.siliconflow.cn/v1
security:
  - bearerAuth: [ ]

paths:
  /user/info:
    get:
      summary: 获取用户信息
      operationId: user-info
      description: 获取用户信息，包括余额和状态
      tags:
        - UserInfo
      responses:
        '200':
          description: Successful response
          content:
            application/json:
              schema:
                type: object
                properties:
                  code:
                    type: integer
                    example: 20000
                  message:
                    type: string
                    example: OK
                  status:
                    type: boolean
                    example: true
                  data:
                    type: object
                    properties:
                      id:
                        type: string
                        example: "userid"
                      name:
                        type: string
                        example: "username"
                      image:
                        type: string
                        example: "user_avatar_image_url"
                      email:
                        type: string
                        example: "user_email_address"
                      isAdmin:
                        type: boolean
                        example: false
                      balance:
                        type: string
                        example: "0.88"
                      status:
                        type: string
                        example: "normal"
                      introduction:
                        type: string
                        example: "user_introduction"
                      role:
                        type: string
                        example: "user_role"
                      chargeBalance:
                        type: string
                        example: "88.00"
                      totalBalance:
                        type: string
                        example: "88.88"
        '400':
          description: 'BadRequest'
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/StringData"
        '401':
          description: 'Unauthorized'
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/StringData"
        '404':
          description: 'NotFound'
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/StringData"
        '429':
          description: 'RateLimit'
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/StringData"
        '503':
          description: 'Overloaded'
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/StringData"
        '504':
          description: 'Timeout'
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/StringData"
      deprecated: false

  /models:
    get:
      summary: Get Model List
      operationId: Retrieve a list of models.
      description: Retrieve models information.
      parameters:
        - name: type
          in: query
          description: The type of models
          required: false
          schema:
            type: string
            enum: [ text, image, audio, video ]
        - name: sub_type
          in: query
          description: The sub type of models. You can use it to filter models individually without setting type.
          required: false
          schema:
            type: string
            enum: [ chat, embedding, reranker, text-to-image, image-to-image,  speech-to-text, text-to-video ]
      tags:
        - Models
      responses:
        '200':
          description: Successful response
          content:
            application/json:
              schema:
                type: object
                properties:
                  object:
                    type: string
                    example: list
                  data:
                    type: array
                    items:
                      type: object
                      properties:
                        id:
                          type: string
                          example: stabilityai/stable-diffusion-xl-base-1.0
                        object:
                          type: string
                          example: model
                        created:
                          type: integer
                          example: 0
                        owned_by:
                          type: string
                          example: ""
        '400':
          description: 'BadRequest'
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/StringData"
        '401':
          description: 'Unauthorized'
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/StringData"
        '404':
          description: 'NotFound'
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/StringData"
        '429':
          description: 'RateLimit'
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/StringData"
        '503':
          description: 'Overloaded'
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/StringData"
        '504':
          description: 'Timeout'
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/StringData"
      deprecated: false

  /uploads/audio/voice:
    post:
      summary: Upload Voice
      description: 上传用户预置音色，支持以 base64 编码或者文件形式上传，参考https://docs.siliconflow.cn/capabilities/text-to-speech#2-2)
      operationId: uploadAudioVoice
      parameters: []
      requestBody:
        content:
          multipart/form-data:
            schema:
              type: object
              properties:
                model:
                  type: string
                  example: "fishaudio/fish-speech-1.4"
                  enum: ["fishaudio/fish-speech-1.4"]
                  description: "预置音色的模型名称"
                customName:
                  type: string
                  example: "your-voice-name"
                  description: "用户自定义的音色名称"
                  default: "硅基流动音色模型"
                text:
                  type: string
                  example: "在一无所知中, 梦里的一天结束了，一个新的轮回便会开始"
                  description: "音频对应的文字内容"
                  default: "在一无所知中, 梦里的一天结束了，一个新的轮回便会开始"
              required:
                - model
                - customName
                - text
              oneOf:
                - properties:
                    audio:
                      title: base64 编码音频
                      type: string
                      example: "data:audio/mpeg;base64,aGVsbG93b3JsZA=="
                      description: "使用 base64 编码的音频文件，头部为：`data:audio/mpeg;base64,`格式"
                - properties:
                    file:
                      title: 文件上传音频
                      type: string
                      format: binary
                      example: /path/to/audio.mp3
                      description: "待上传的文件"
         
      responses:
        '200':
          description: Successful response
          content:
            application/json:
              schema:
                type: object
                properties:
                  uri:
                    type: string
                    example: 'speech:your-voice-name:cm04pf7az00061413w7kz5qxs:mjtkgbyuunvtybnsvbxd'

        '400':
          description: 'BadRequest'
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/StringData"
        '401':
          description: 'Unauthorized'
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/StringData"
        '404':
          description: 'NotFound'
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/StringData"
        '429':
          description: 'RateLimit'
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/StringData"
        '503':
          description: 'Overloaded'
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/StringData"
        '504':
          description: 'Timeout'
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/StringData"
      deprecated: false

  /chat/completions:
    post:
      summary: Chat Completions
      operationId: chat-completions
      description: Creates a model response for the given chat conversation.
      tags:
        - Chat Completions
      requestBody:
        content:
          application/json:
            schema:
              $ref: "#/components/schemas/ChatCompletionRequest"
      responses:
        '200':
          description: '200'
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/ChatCompletionResponse"
            text/event-stream:
              schema:
                $ref: "#/components/schemas/ChatCompletionStream"
        '400':
          description: 'BadRequest'
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/StringData"
        '401':
          description: 'Unauthorized'
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/StringData"
        '404':
          description: 'NotFound'
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/StringData"
        '429':
          description: 'RateLimit'
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/StringData"
        '503':
          description: 'Overloaded'
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/StringData"
        '504':
          description: 'Timeout'
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/StringData"
      deprecated: false

  /embeddings:
    post:
      summary: Create Embeddings
      description: Creates an embedding vector representing the input text.
      operationId: createEmbedding
      tags:
        - Embeddings
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/EmbeddingsRequest'
      responses:
        '200':
          description: '200'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/EmbeddingsResponse'
        '400':
          description: 'BadRequest'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/StringData'
        '401':
          description: 'Unauthorized'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/StringData'
        '404':
          description: 'NotFound'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/StringData'
        '429':
          description: 'RateLimit'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/StringData'
        '503':
          description: 'Overloaded'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/StringData'
        '504':
          description: 'Timeout'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/StringData'
      deprecated: false

  /audio/speech:
    post:
      operationId: createSpeech
      tags:
          - Audio
      summary: Create Speech
      description: 从输入文本生成音频。根据输入的文本生成音频。接口生成的数据为音频的二进制数据，需要使用者自行处理。参考：https://docs.siliconflow.cn/capabilities/text-to-speech#5
      requestBody:
          required: true
          content:
              application/json:
                  schema:
                      $ref: "#/components/schemas/CreateSpeechRequest"
      responses:
          "200":
              description: 根据输入的文本生成音频。接口生成的数据为音频的二进制数据，需要使用者自行处理。参考：https://docs.siliconflow.cn/capabilities/text-to-speech#5
              headers:
                  Transfer-Encoding:
                      schema:
                          type: string
                      description: chunked
              content:
                  application/octet-stream:
                      schema:
                          type: string
                          format: binary

  /audio/transcriptions:
    post:
      summary: Create Audio Transcriptions
      description: Creates an audio transcription.
      operationId: createAudioTranscriptions
      tags:
        - Audio
      requestBody:
        content:
          multipart/form-data:
            schema:
              $ref: '#/components/schemas/AudioRequest'
      responses:
        '200':
          description: '200'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/AudioResponse'
        '400':
          description: 'BadRequest'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/StringData'
        '401':
          description: 'Unauthorized'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/StringData'
        '404':
          description: 'NotFound'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/StringData'
        '429':
          description: 'RateLimit'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/StringData'
        '503':
          description: 'Overloaded'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/StringData'
        '504':
          description: 'Timeout'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/StringData'
      deprecated: false

  /rerank:
    post:
      summary: Create Rerank
      description: Creates a rerank request.
      operationId: createRerank
      tags:
        - Rerank
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/RerankRequest'
      responses:
        '200':
          description: '200'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/RerankResponse'
        '400':
          description: 'BadRequest'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/StringData'
        '401':
          description: 'Unauthorized'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/StringData'
        '404':
          description: 'NotFound'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/StringData'
        '429':
          description: 'RateLimit'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/StringData'
        '503':
          description: 'Overloaded'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/StringData'
        '504':
          description: 'Timeout'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/StringData'
      deprecated: false

  /images/generations:
    post:
      summary: Image Generation
      operationId: ImageGeneration
      description: Creates an image response for the given prompt.
      tags:
        - Image
      requestBody:
        content:
          application/json:
            schema:
              oneOf:
                - $ref: "#/components/schemas/stable-diffusion-3-5-large"
                - $ref: "#/components/schemas/FLUX.1-schnell"
                - $ref: "#/components/schemas/Pro-FLUX.1-schnell"
                - $ref: "#/components/schemas/FLUX.1-dev"
                - $ref: "#/components/schemas/stable-diffusion-3-medium"
                - $ref: "#/components/schemas/stable-diffusion-xl-base-1.0"
                - $ref: "#/components/schemas/stable-diffusion-2-1"

      responses:
        '200':
          description: '200'
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/ImagesGenerationResponse"
        '400':
          description: 'BadRequest'
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/StringData"
        '401':
          description: 'Unauthorized'
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/StringData"
        '404':
          description: 'NotFound'
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/StringData"
        '429':
          description: 'RateLimit'
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/StringData"
        '503':
          description: 'Overloaded'
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/StringData"
        '504':
          description: 'Timeout'
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/StringData"
      deprecated: false

components:
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer

  schemas:
    EmbeddingsRequest:
      type: object
      required:
        - model
        - input
      properties:
        model:
          type: string
          description: The name of the embedding model to use.要使用的 embedding 模型名称。
          example: BAAI/bge-large-zh-v1.5
          enum:
            - BAAI/bge-large-zh-v1.5
            - BAAI/bge-large-en-v1.5
            - netease-youdao/bce-embedding-base_v1
            - BAAI/bge-m3
            - Pro/BAAI/bge-m3
        input:
          description: |
            Input text to embed, encoded as a string or array of tokens. To embed multiple inputs in a single request, pass an array of strings or array of token arrays. The input must not exceed the max input tokens for the model (512 tokens for all models except BAAI/bge-m3 which is 8192), cannot be an empty string.
            输入的文本将被编码为字符串或 tokens 数组。要在单个请求中嵌入多个输入，请传递字符串数组或字符串数组。每个字符串不得超过模型的最大 tokens 限制（BAAI/bge-m3模型为8192tokens，其余模型为512tokens），且不能为空字符串。
          default: "硅基流动embedding上线，多快好省的 embedding 服务，快来试试吧"

          oneOf:
            - type: string
              title: string
              description: The string that will be turned into an embedding. the item must not exceed the max models tokens limitation.
                将字符串数组转换为嵌入，string 长度不得超过模型的最大 tokens 限制。当前输入长度不得超过当前模型的 512 个 tokens。
              default: "硅基流动embedding上线，多快好省的 embedding 服务，快来试试吧"
              example: "硅基流动embedding上线，多快好省的 embedding 服务，快来试试吧"
            - type: array
              title: array
              description: |
                The array of strings that will be turned into an embedding. The array length must not exceed the max size, and the item must not exceed the max models tokens limitation.
                Current, the maximum array size is 32 , At the same time every item must not exceed 512 tokens for current models.
                将字符串数组转换为嵌入。数组长度不得超过最大限制，且每项不得超过模型的最大 tokens 限制。目前，最大数组大小为 32，同时每项不得超过当前模型的 512 个 tokens。
              minItems: 1
              maxItems: 32
              items:
                type: string
                default: "['大语言模型', 'LLM', 'Embedding', 'RAG']"
                example: "['大语言模型', 'LLM', 'Embedding', 'RAG']"
        encoding_format:
          description: |
            "The format to return the embeddings in. Can be either `float` or [`base64`](https://pypi.org/project/pybase64/). 返回嵌入的格式。可以是 float 或 [`base64`](https://pypi.org/project/pybase64/)."
          example: "float"
          default: "float"
          type: string
          enum: [ "float", "base64" ]

    EmbeddingsResponse:
      type: object
      required:
        - object
        - model
        - data
        - usage
      properties:
        object:
          type: string
          description: The object type, which is always "list".
          enum:
            - [ list ]
        model:
          description: The name of the model used to generate the embedding.
          type: string
        data:
          type: array
          description: The list of embeddings generated by the model.
          items:
            type: object
            required: [ index, object, embedding ]
            properties:
              object:
                type: string
                enum:
                  - embedding
              embedding:
                type: array
                items:
                  type: number
              index:
                type: integer
        usage:
          type: object
          description: The usage information for the request.
          properties:
            prompt_tokens:
              type: integer
              description: The number of tokens used by the prompt.
            completion_tokens:
              type: integer
              description: The number of tokens used by the completion.
            total_tokens:
              type: integer
              description: The total number of tokens used by the request.
          required:
            - prompt_tokens
            - total_tokens
            - completion_tokens

    RerankRequest:
      type: object
      required:
        - model
        - query
        - documents
      properties:
        model:
          type: string
          description: Specifies the model to be used.
          example: BAAI/bge-reranker-v2-m3
          enum:
            - BAAI/bge-reranker-v2-m3
            - netease-youdao/bce-reranker-base_v1
        query:
          type: string
          description: Required. The search query.
          example: Apple
          default: Apple
        documents:
          type: array
          minItems: 1
          items:
            type: string
          description: Required. List of documents to be reordered. If document objects are provided, the 'text' field is mandatory, and other fields will be preserved in the response.
          example: [ "苹果", "香蕉", "水果", "蔬菜" ]
          default: [ "苹果", "香蕉", "水果", "蔬菜" ]
        top_n:
          type: integer
          example: 4
          description: Number of most relevant documents or indices to return.
        return_documents:
          type: boolean
          default: false
          description: If false, the response does not include document text; if true, it includes the input document text.
        max_chunks_per_doc:
          type: integer
          default: 1024
          description: Maximum number of chunks generated from within a document. Long documents are divided into multiple chunks for calculation, and the highest score among the chunks is taken as the document's score.
        overlap_tokens:
          type: integer
          default: 80
          maximum: 80
          description: Number of token overlaps between adjacent chunks when documents are chunked.


    RerankResponse:
      type: object
      required:
        - id
        - results
        - tokens
      properties:
        id:
          type: string
        results:
          type: array
          items:
            type: object
            properties:
              document:
                type: object
                properties:
                  text:
                    type: string
                description: Original document content.
              index:
                type: integer
                description: The index value of the position in the input candidate doc array.
              relevance_score:
                type: number
                description: Similarity score.
        tokens:
          type: object
          properties:
            input_tokens:
              type: integer
            output_tokens:
              type: integer

    CreateSpeechRequest:
      type: object
      additionalProperties: false
      properties:
        model:
            description: |
              Current available TTS models: `fishaudio/fish-speech-1.4`
            type: string
            example: "fishaudio/fish-speech-1.4"
            enum: ["fishaudio/fish-speech-1.4"]

        input:
            type: string
            description: The text to generate audio for.
            maxLength: 128000
            minLength: 1
        voice:
            description: The voice to use when generating the audio. Supported voices are `fishaudio/fish-speech-1.4:alex`, `fishaudio/fish-speech-1.4:anna`, `fishaudio/fish-speech-1.4:bella`, `fishaudio/fish-speech-1.4:benjamin`, `fishaudio/fish-speech-1.4:charles`, `fishaudio/fish-speech-1.4:claire`, `fishaudio/fish-speech-1.4:david`, `fishaudio/fish-speech-1.4:diana`. Previews of the voices are available in the [Text to speech guide](/capabilities/text-to-speech).
            type: string
            enum: [
                  "fishaudio/fish-speech-1.4:alex",
                  "fishaudio/fish-speech-1.4:anna",
                  "fishaudio/fish-speech-1.4:bella",
                  "fishaudio/fish-speech-1.4:benjamin",
                  "fishaudio/fish-speech-1.4:charles",
                  "fishaudio/fish-speech-1.4:claire",
                  "fishaudio/fish-speech-1.4:david",
                  "fishaudio/fish-speech-1.4:diana"
            ]
        response_format:
            description: "The format to audio in. Supported formats are `mp3`, `opus`, `wav`, `pcm`"
            default: "mp3"
            type: string
            enum: ["mp3", "opus", "wav", "pcm"]

      required:
        - model
        - input
        - voice

    AudioRequest:
      type: object
      required:
        - model
        - file
      properties:
        file:
          type: string
          description: The audio file object (not file name) to transcribe
          example: /path/to/audio.mp3
          format: binary
        model:
          type: string
          description: The name of the audio model to use.
          example: FunAudioLLM/SenseVoiceSmall
          enum:
            - FunAudioLLM/SenseVoiceSmall

    AudioResponse:
      type: object
      description: Represents a transcription response returned by model, based on the provided input.
      required:
        - text
      properties:
        text:
          description: The transcribed text.
          type: string


    StringData:
      type: string
    ErrorData:
      type: object
      required:
        - error
      properties:
        error:
          type: object
          properties:
            message:
              type: string
              nullable: false
            type:
              type: string
              nullable: false
            param:
              type: string
              nullable: true
              default: null
            code:
              type: string
              nullable: true
              default: null
          required:
            - type
            - message
            - param
            - code

    FinishReason:
      type: string
      enum:
        - stop
        - eos
        - length
        - tool_calls

    LogprobsPart:
      type: object
      properties:
        tokens:
          type: array
          items:
            type: string
          description: List of token strings
        token_logprobs:
          type: array
          items:
            type: number
            format: float
          description: List of token log probabilities

    PromptPart:
      type: array
      items:
        type: object
        properties:
          text:
            type: string
            example: <s>[INST] What is the capital of France? [/INST]
            default: <s>[INST] What is the capital of France? [/INST]
          logprobs:
            $ref: "#/components/schemas/LogprobsPart"

    UsageData:
      type: object
      properties:
        prompt_tokens:
          type: integer
        completion_tokens:
          type: integer
        total_tokens:
          type: integer

    CompletionChoicesData:
      type: array
      items:
        type: object
        properties:
          text:
            type: string
          finish_reason:
            $ref: "#/components/schemas/FinishReason"
          logprobs:
            allOf:
              - $ref: "#/components/schemas/LogprobsPart"
              - nullable: true

    CompletionResponse:
      type: object
      properties:
        id:
          type: string
        choices:
          $ref: "#/components/schemas/CompletionChoicesData"
        prompt:
          $ref: "#/components/schemas/PromptPart"
        usage:
          $ref: "#/components/schemas/UsageData"
        created:
          type: integer
        model:
          type: string
        object:
          type: string
          enum:
            - text_completion
      required:
        - id
        - choices
        - usage
        - created
        - model
        - object

    CompletionStream:
      oneOf:
        - $ref: "#/components/schemas/CompletionEvent"

    CompletionEvent:
      type: object
      required: [ data ]
      properties:
        data:
          $ref: "#/components/schemas/CompletionChunk"

    CompletionChunk:
      type: object
      required: [ id, token, choices, usage, finish_reason ]
      properties:
        id:
          type: string
        token:
          $ref: "#/components/schemas/CompletionToken"
        choices:
          title: CompletionChoices
          type: array
          items:
            $ref: "#/components/schemas/CompletionChoice"
        usage:
          allOf:
            - $ref: "#/components/schemas/UsageData"
            - nullable: true
        finish_reason:
          allOf:
            - $ref: "#/components/schemas/FinishReason"
            - nullable: true

    CompletionChoice:
      type: object
      required: [ index ]
      properties:
        text:
          type: string

    CompletionToken:
      type: object
      required: [ id, text, logprob, special ]
      properties:
        id:
          type: integer
        text:
          type: string
        logprob:
          type: number
          format: float
        special:
          type: boolean

    ChatCompletionChoicesData:
      type: array
      items:
        type: object
        properties:
          message:
            type: object
            properties:
              role:
                type: string
                example: assistant
              content:
                type: string
          finish_reason:
            $ref: "#/components/schemas/FinishReason"

    ChatCompletionRequestMessageContentPartText:
      type: object
      title: Text content part
      properties:
        type:
          type: string
          enum: [ "text" ]
          description: The type of the content part.
          default: "text"
        text:
          type: string
          description: The text content.
          default: "描述这张图片"
      required:
        - type
        - text

    ChatCompletionRequestMessageContentPartImage:
      type: object
      title: Image content part
      properties:
        type:
          type: string
          enum: [ "image_url" ]
          description: The type of the content part.
          default: "image_url"
        image_url:
          type: object
          properties:
            url:
              type: string
              description: Either a URL of the image or the base64 encoded image data.
              default: "https://sf-maas-uat-prod.oss-cn-shanghai.aliyuncs.com/dog.png"
            detail:
              type: string
              description: Specifies the detail level of the image.
              enum: [ "auto", "low", "high" ]
              default: "auto"
          required:
            - url
      required:
        - type
        - image_url

    ChatCompletionRequestUserMessageContentPart:
      oneOf:
        - $ref: "#/components/schemas/ChatCompletionRequestMessageContentPartText"
        - $ref: "#/components/schemas/ChatCompletionRequestMessageContentPartImage"
      x-oaiExpandable: true

    ChatCompletionRequest:
      type: object
      required:
        - model
        - messages
      properties:
        model:
          type: string
          description: The name of the model to query.
          example: deepseek-ai/DeepSeek-V2.5
          default: deepseek-ai/DeepSeek-V2.5
          enum:
            - deepseek-ai/DeepSeek-V2.5
            - deepseek-ai/DeepSeek-V2-Chat
            - deepseek-ai/DeepSeek-Coder-V2-Instruct
            - Qwen/Qwen2.5-72B-Instruct-128K
            - Qwen/Qwen2.5-72B-Instruct
            - Qwen/Qwen2-VL-72B-Instruct
            - Qwen/Qwen2.5-32B-Instruct
            - Qwen/Qwen2.5-14B-Instruct
            - Qwen/Qwen2.5-7B-Instruct
            - Qwen/Qwen2.5-Math-72B-Instruct
            - Qwen/Qwen2.5-Coder-7B-Instruct
            - Qwen/Qwen2-72B-Instruct
            - Qwen/Qwen2-7B-Instruct
            - Qwen/Qwen2-1.5B-Instruct
            - Qwen/Qwen2-57B-A14B-Instruct
            - TeleAI/TeleChat2
            - 01-ai/Yi-1.5-34B-Chat-16K
            - 01-ai/Yi-1.5-9B-Chat-16K
            - 01-ai/Yi-1.5-6B-Chat
            - THUDM/chatglm3-6b
            - THUDM/glm-4-9b-chat
            - Vendor-A/Qwen/Qwen2-72B-Instruct
            - Vendor-A/Qwen/Qwen2.5-72B-Instruct
            - internlm/internlm2_5-7b-chat
            - internlm/internlm2_5-20b-chat
            - OpenGVLab/InternVL2-Llama3-76B
            - OpenGVLab/InternVL2-26B
            - nvidia/Llama-3.1-Nemotron-70B-Instruct
            - meta-llama/Meta-Llama-3.1-405B-Instruct
            - meta-llama/Meta-Llama-3.1-70B-Instruct
            - meta-llama/Meta-Llama-3.1-8B-Instruct
            - meta-llama/Meta-Llama-3-8B-Instruct
            - meta-llama/Meta-Llama-3-70B-Instruct
            - google/gemma-2-27b-it
            - google/gemma-2-9b-it
            - Pro/Qwen/Qwen2.5-7B-Instruct
            - Pro/Qwen/Qwen2-7B-Instruct
            - Pro/Qwen/Qwen2-1.5B-Instruct
            - Pro/Qwen/Qwen2-VL-7B-Instruct
            - Pro/01-ai/Yi-1.5-9B-Chat-16K
            - Pro/01-ai/Yi-1.5-6B-Chat
            - Pro/THUDM/chatglm3-6b
            - Pro/THUDM/glm-4-9b-chat
            - Pro/internlm/internlm2_5-7b-chat
            - Pro/OpenGVLab/InternVL2-8B
            - Pro/meta-llama/Meta-Llama-3-8B-Instruct
            - Pro/meta-llama/Meta-Llama-3.1-8B-Instruct
            - Pro/google/gemma-2-9b-it

        messages:
          type: array
          description: A list of messages comprising the conversation so far.
          items:
            type: object
            properties:
              role:
                type: string
                description: 'The role of the messages author. Choice between: system, user, or assistant.'
                example: user
                default: user
                enum:
                  - user
                  - assistant
                  - system
              content:
                oneOf:
                  - type: string
                    description: The contents of the message.
                    example: SiliconCloud推出分层速率方案与免费模型RPM提升10倍，对于整个大模型应用领域带来哪些改变？
                    default: SiliconCloud推出分层速率方案与免费模型RPM提升10倍，对于整个大模型应用领域带来哪些改变？
                  - type: array
                    description: An array of content parts with a defined type, each can be of type `text` or `image_url` when passing in images. You can pass multiple images by adding multiple `image_url` content parts. Image input is only supported when using the `gpt-4o` model.
                    items:
                      $ref: "#/components/schemas/ChatCompletionRequestUserMessageContentPart"
                    minItems: 1
            required:
              - role
              - content
          minItems: 1
          maxItems: 10
        stream:
          type: boolean
          description: "If set, tokens are returned as Server-Sent Events as they are made available. Stream terminates with `data: [DONE]`"
          example: false
          default: false
        max_tokens:
          type: integer
          description: The maximum number of tokens to generate.
          example: 512
          default: 512
          minimum: 1
          maximum: 4096
        stop:
          description: >
            Up to 4 sequences where the API will stop generating further tokens.
            The returned text will not contain the stop sequence.
          default: null
          nullable: true
          oneOf:
            - type: string
              default: <|endoftext|>
              example: "\n"
              nullable: true
            - type: array
              minItems: 1
              maxItems: 4
              items:
                type: string
                example: '["\n"]'
        temperature:
          type: number
          description: Determines the degree of randomness in the response.
          format: float
          example: 0.7
          default: 0.7
        top_p:
          type: number
          description: The `top_p` (nucleus) parameter is used to dynamically adjust the number of choices for each predicted token based on the cumulative probabilities.
          format: float
          example: 0.7
          default: 0.7
        top_k:
          type: number
          format: float
          example: 50
          default: 50
        frequency_penalty:
          type: number
          format: float
          example: 0.5
          default: 0.5
        n:
          type: integer
          description: Number of generations to return
          example: 1
          default: 1
        response_format:
          type: object
          description: 'An object specifying the format that the model must output.'
          properties:
            type:
              type: string
              description: 'The type of the response format.'
              example: text

    ChatCompletionResponse:
      type: object
      properties:
        id:
          type: string
        choices:
          $ref: "#/components/schemas/ChatCompletionChoicesData"
        usage:
          $ref: "#/components/schemas/UsageData"
        created:
          type: integer
        model:
          type: string
        object:
          type: string
          enum:
            - chat.completion

    ChatCompletionStream:
      type: object
      properties:
        id:
          type: string
        choices:
          $ref: "#/components/schemas/ChatCompletionChoicesData"
        created:
          type: integer
        model:
          type: string
        object:
          type: string
          enum:
            - chat.completion.chunk

    ChatCompletionEvent:
      type: object
      required: [ data ]
      properties:
        data:
          $ref: "#/components/schemas/ChatCompletionChunk"

    ChatCompletionChunk:
      type: object
      required: [ id, object, created, token, choices ]
      properties:
        id:
          type: string
        object:
          type: string
          enum:
            - chat.completion.chunk
        created:
          type: integer
        token:
          $ref: "#/components/schemas/ChatCompletionToken"
        choices:
          title: ChatCompletionChoices
          type: array
          items:
            $ref: "#/components/schemas/ChatCompletionChoice"
        usage:
          allOf:
            - $ref: "#/components/schemas/UsageData"
            - nullable: true
        finish_reason:
          allOf:
            - $ref: "#/components/schemas/FinishReason"
            - nullable: true

    ChatCompletionToken:
      type: object
      required: [ id, text, logprob, special ]
      properties:
        id:
          type: integer
        text:
          type: string
        logprob:
          type: number
          format: float
        special:
          type: boolean

    ChatCompletionChoice:
      type: object
      required: [ index, delta ]
      properties:
        index:
          type: integer
        delta:
          title: ChatCompletionChoiceDelta
          type: object
          required: [ content ]
          properties:
            content:
              type: string

    upload_image:
      title: Upload Image
      type: string
      default: data:image/webp;base64, XXX
    stable-diffusion-3-5-large:
      title: stable-diffusion-3-5-large
      type: object
      required:
        - model
        - prompt
        - image_size
        - batch_size
        - num_inference_steps
        - guidance_scale
      properties:
        model:
          type: string
          default: stabilityai/stable-diffusion-3-5-large
          enum:
            - stabilityai/stable-diffusion-3-5-large
        prompt:
          type: string
          default: an island near sea, with seagulls, moon shining over the sea, light house, boats int he background, fish flying over the sea
        negative_prompt:
          title: Negative Prompt
          type: string
        image_size:
          title: Image Size
          enum:
            - 1024x1024
            - 512x1024
            - 768x512
            - 768x1024
            - 1024x576
            - 576x1024
          default: 1024x1024
        batch_size:
          title: Number Images
          type: integer
          minimum: 1
          maximum: 4
          default: 1
        seed:
          title: Seed
          type: integer
          minimum: 0
          maximum: 9999999999
        num_inference_steps:
          title: Number Inference Steps
          type: integer
          minimum: 1
          maximum: 100
          default: 20
        guidance_scale:
          title: Guidance Scale
          type: number
          minimum: 0
          maximum: 100
          default: 7.5
    
    FLUX.1-schnell:
      title: FLUX.1-schnell
      type: object
      required:
        - model
        - prompt
        - image_size
      properties:
        model:
          type: string
          default: black-forest-labs/FLUX.1-schnell
          enum:
            - black-forest-labs/FLUX.1-schnell
        prompt:
          type: string
          default: an island near sea, with seagulls, moon shining over the sea, light house, boats int he background, fish flying over the sea
        image_size:
          title: Image Size
          enum:
            - 1024x1024
            - 512x1024
            - 768x512
            - 768x1024
            - 1024x576
            - 576x1024
          default: 1024x1024
        seed:
          title: Seed
          type: integer
          minimum: 0
          maximum: 9999999999
    
    Pro-FLUX.1-schnell:
      title: Pro-FLUX.1-schnell
      type: object
      required:
        - model
        - prompt
        - image_size
      properties:
        model:
          type: string
          default: Pro/black-forest-labs/FLUX.1-schnell
          enum:
            - Pro/black-forest-labs/FLUX.1-schnell
        prompt:
          type: string
          default: an island near sea, with seagulls, moon shining over the sea, light house, boats int he background, fish flying over the sea
        image_size:
          title: Image Size, format:"[width]x[height]", the maximum pixel size is 2359296.
          enum:
            - 1024x1024
            - 960x1280
            - 768x1024
            - 720x1440
            - 720x1280
            - others
          default: 1024x1024
        seed:
          title: Seed
          type: integer
          minimum: 0
          maximum: 9999999999
    
    FLUX.1-dev:
      title: FLUX.1-dev
      type: object
      required:
        - model
        - prompt
        - image_size
        - num_inference_steps
      properties:
        model:
          type: string
          description: The name of the model to query.
          default: black-forest-labs/FLUX.1-dev
          enum:
            - black-forest-labs/FLUX.1-dev
        prompt:
          type: string
          default: a man
        image_size:
          title: Image Size, format:"[width]x[height]", the maximum pixel size is 2359296.
          enum:
            - 1024x1024
            - 960x1280
            - 768x1024
            - 720x1440
            - 720x1280
            - others
          default: 1024x1024
        seed:
          title: Seed
          type: integer
          minimum: 0
          maximum: 9999999999
        num_inference_steps:
          title: Number Inference Steps
          type: integer
          minimum: 1
          maximum: 30
          default: 20

    stable-diffusion-3-medium:
      title: stable-diffusion-3-medium
      type: object
      required:
        - model
        - prompt
        - image_size
        - batch_size
        - num_inference_steps
        - guidance_scale
      properties:
        model:
          type: string
          default: stabilityai/stable-diffusion-3-medium
          enum:
            - stabilityai/stable-diffusion-3-medium
        prompt:
          type: string
          default: an island near sea, with seagulls, moon shining over the sea, light house, boats int he background, fish flying over the sea
        negative_prompt:
          title: Negative Prompt
          type: string
        image_size:
          title: Image Size
          enum:
            - 1024x1024
            - 960x1280
            - 768x1024
            - 720x1440
            - 720x1280
            - others
          default: 1024x1024
        batch_size:
          title: Number Images
          type: integer
          minimum: 1
          maximum: 4
          default: 1
        seed:
          title: Seed
          type: integer
          minimum: 0
          maximum: 9999999999
        num_inference_steps:
          title: Number Inference Steps
          type: integer
          minimum: 1
          maximum: 100
          default: 20
        guidance_scale:
          title: Guidance Scale
          type: number
          minimum: 0
          maximum: 100
          default: 7.5

    stable-diffusion-xl-base-1.0:
      title: stable-diffusion-xl-base-1.0
      type: object
      required:
        - model
        - prompt
        - image_size
        - batch_size
        - num_inference_steps
        - guidance_scale
      properties:
        model:
          type: string
          default: stabilityai/stable-diffusion-xl-base-1.0
          enum:
            - stabilityai/stable-diffusion-xl-base-1.0
        prompt:
          type: string
          default: an island near sea, with seagulls, moon shining over the sea, light house, boats int he background, fish flying over the sea
        negative_prompt:
          title: Negative Prompt
          type: string
        image_size:
          title: Image Size
          enum:
            - 1024x1024
            - 960x1280
            - 768x1024
            - 720x1440
            - 720x1280
            - others
          default: 1024x1024
        batch_size:
          title: Number Images
          type: integer
          minimum: 1
          maximum: 4
          default: 1
        seed:
          title: Seed
          type: integer
          minimum: 0
          maximum: 9999999999
        num_inference_steps:
          title: Number Inference Steps
          type: integer
          minimum: 1
          maximum: 100
          default: 20
        guidance_scale:
          title: Guidance Scale
          type: number
          minimum: 0
          maximum: 100
          default: 7.5
        image:
          $ref: "#/components/schemas/upload_image"

    stable-diffusion-2-1:
      title: stable-diffusion-2-1
      type: object
      required:
        - model
        - prompt
        - image_size
        - batch_size
        - num_inference_steps
        - guidance_scale
      properties:
        model:
          type: string
          default: stabilityai/stable-diffusion-2-1
          enum:
            - stabilityai/stable-diffusion-2-1
        prompt:
          type: string
          default: an island near sea, with seagulls, moon shining over the sea, light house, boats int he background, fish flying over the sea
        negative_prompt:
          title: Negative Prompt
          type: string
        image_size:
          title: Image Size
          enum:
            - 512x512
            - 512x1024
            - 768x512
            - 768x1024
            - 1024x576
            - 576x1024
          default: 512x512
        batch_size:
          title: Number Images
          type: integer
          minimum: 1
          maximum: 4
          default: 1
        seed:
          title: Seed
          type: integer
          minimum: 0
          maximum: 9999999999
        num_inference_steps:
          title: Number Inference Steps
          type: integer
          minimum: 1
          maximum: 100
          default: 20
        guidance_scale:
          title: Guidance Scale
          type: number
          minimum: 0
          maximum: 100
          default: 7.5
        image:
          $ref: "#/components/schemas/upload_image"


    ImagesGenerationResponse:
      type: object
      properties:
        images:
          type: array
          items:
            type: object
            properties:
              url:
                type: string
        timings:
          type: object
          properties:
            inference:
              type: number
              format: float
        seed:
          type: integer