openapi: 3.1.0
info:
  title: NVIDIA NIM for VLMs
  summary: Accelerated VLM inference for NVIDIA GPUs.
  version: 1.1.2
paths:
  /v1/chat/completions:
    post:
      summary: OpenAI-compatible chat endpoint
      operationId: create_chat_completion_v1_chat_completions_post
      parameters:
      - name: content-type
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          title: Content-Type
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/NIMLLMChatCompletionRequest'
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                anyOf:
                - $ref: '#/components/schemas/NIMLLMChatCompletionResponse'
                - $ref: '#/components/schemas/NIMLLMChatCompletionStreamResponse'
                title: Response Create Chat Completion V1 Chat Completions Post
        '400':
          description: Received an invalid request possibly containing unsupported
            or out-of-range parameter values.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '404':
          description: The requested model does not exist.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '500':
          description: Internal Server Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '415':
          description: Unsupported Media Type
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
components:
  schemas:
    BaseModel:
      properties: {}
      type: object
      title: BaseModel
    ChatCompletionLogProb:
      properties:
        token:
          type: string
          title: Token
        logprob:
          type: number
          title: Logprob
          default: -9999.0
        bytes:
          anyOf:
          - items:
              type: integer
            type: array
          - type: 'null'
          title: Bytes
      additionalProperties: false
      type: object
      required:
      - token
      title: ChatCompletionLogProb
    ChatCompletionLogProbs:
      properties:
        content:
          anyOf:
          - items:
              $ref: '#/components/schemas/ChatCompletionLogProbsContent'
            type: array
          - type: 'null'
          title: Content
      additionalProperties: false
      type: object
      title: ChatCompletionLogProbs
    ChatCompletionLogProbsContent:
      properties:
        token:
          type: string
          title: Token
        logprob:
          type: number
          title: Logprob
          default: -9999.0
        bytes:
          anyOf:
          - items:
              type: integer
            type: array
          - type: 'null'
          title: Bytes
        top_logprobs:
          items:
            $ref: '#/components/schemas/ChatCompletionLogProb'
          type: array
          title: Top Logprobs
      additionalProperties: false
      type: object
      required:
      - token
      title: ChatCompletionLogProbsContent
    ChatCompletionNamedFunction:
      properties:
        name:
          type: string
          title: Name
      additionalProperties: false
      type: object
      required:
      - name
      title: ChatCompletionNamedFunction
    ChatCompletionNamedToolChoiceParam:
      properties:
        function:
          $ref: '#/components/schemas/ChatCompletionNamedFunction'
        type:
          type: string
          const: function
          title: Type
          default: function
      additionalProperties: false
      type: object
      required:
      - function
      title: ChatCompletionNamedToolChoiceParam
    ChatCompletionResponseChoice:
      properties:
        index:
          type: integer
          title: Index
        message:
          $ref: '#/components/schemas/ChatMessage'
        logprobs:
          anyOf:
          - $ref: '#/components/schemas/ChatCompletionLogProbs'
          - type: 'null'
        finish_reason:
          anyOf:
          - type: string
            enum:
            - stop
            - length
            - tool_calls
          - type: 'null'
          title: Finish Reason
          default: stop
        stop_reason:
          anyOf:
          - type: integer
          - type: string
          - type: 'null'
          title: Stop Reason
      additionalProperties: false
      type: object
      required:
      - index
      - message
      title: ChatCompletionResponseChoice
    ChatCompletionResponseStreamChoice:
      properties:
        index:
          type: integer
          title: Index
        delta:
          $ref: '#/components/schemas/DeltaMessage'
        logprobs:
          anyOf:
          - $ref: '#/components/schemas/ChatCompletionLogProbs'
          - type: 'null'
        finish_reason:
          anyOf:
          - type: string
            enum:
            - stop
            - length
            - tool_calls
          - type: 'null'
          title: Finish Reason
        stop_reason:
          anyOf:
          - type: integer
          - type: string
          - type: 'null'
          title: Stop Reason
      additionalProperties: false
      type: object
      required:
      - index
      - delta
      title: ChatCompletionResponseStreamChoice
    ChatCompletionToolsParam:
      properties:
        type:
          type: string
          const: function
          title: Type
          default: function
        function:
          $ref: '#/components/schemas/FunctionDefinition'
      additionalProperties: false
      type: object
      required:
      - function
      title: ChatCompletionToolsParam
    ChatMessage:
      properties:
        role:
          type: string
          title: Role
        content:
          anyOf:
          - type: string
          - type: 'null'
          title: Content
        tool_calls:
          anyOf:
          - items:
              $ref: '#/components/schemas/ToolCall'
            type: array
          - type: 'null'
          title: Tool Calls
      additionalProperties: false
      type: object
      required:
      - role
      title: ChatMessage
    DeltaMessage:
      properties:
        role:
          anyOf:
          - type: string
          - type: 'null'
          title: Role
        content:
          anyOf:
          - type: string
          - type: 'null'
          title: Content
        tool_calls:
          anyOf:
          - items:
              $ref: '#/components/schemas/ToolCall'
            type: array
          - type: 'null'
          title: Tool Calls
      additionalProperties: false
      type: object
      title: DeltaMessage
    ErrorResponse:
      properties:
        object:
          type: string
          title: Object
          default: error
        message:
          type: string
          title: Message
        type:
          type: string
          title: Type
        param:
          anyOf:
          - type: string
          - type: 'null'
          title: Param
        code:
          type: integer
          title: Code
      additionalProperties: false
      type: object
      required:
      - message
      - type
      - code
      title: ErrorResponse
    FunctionCall:
      properties:
        name:
          anyOf:
          - type: string
          - type: 'null'
          title: Name
          default: ''
        arguments:
          anyOf:
          - type: string
          - type: 'null'
          title: Arguments
          default: ''
      additionalProperties: false
      type: object
      title: FunctionCall
    FunctionDefinition:
      properties:
        name:
          type: string
          title: Name
        description:
          anyOf:
          - type: string
          - type: 'null'
          title: Description
        parameters:
          anyOf:
          - type: object
          - type: 'null'
          title: Parameters
      additionalProperties: false
      type: object
      required:
      - name
      title: FunctionDefinition
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    ImageURL:
      properties:
        url:
          type: string
          title: Url
      type: object
      required:
      - url
      title: ImageURL
    Logprob:
      properties:
        logprob:
          type: number
          title: Logprob
        rank:
          anyOf:
          - type: integer
          - type: 'null'
          title: Rank
        decoded_token:
          anyOf:
          - type: string
          - type: 'null'
          title: Decoded Token
      type: object
      required:
      - logprob
      title: Logprob
    NIMLLMChatCompletionMessage:
      properties:
        role:
          $ref: '#/components/schemas/Role'
          description: The role of the message's author.
        content:
          anyOf:
          - type: string
            minLength: 1
          - items:
              anyOf:
              - $ref: '#/components/schemas/NIMVLMChatCompletionContentPartImage'
              - $ref: '#/components/schemas/NIMVLMChatCompletionContentPartText'
              - $ref: '#/components/schemas/NIMVLMChatCompletionContentPartVideo'
              - $ref: '#/components/schemas/NIMVLMChatCompletionContentPartVideoStreaming'
            type: array
          title: Content
          description: "The contents of the message.\n        <br>To pass images (only\
            \ with role=`user`):\n        <br>    - When content is a string, image\
            \ can be passed together with the text with `img` HTML tags that wraps\n\
            \        an image URL (`<img src=\"{url}\" />`),\n        base64 encoded\
            \ image data (`<img src=\"data:image/{format};base64,{base64encodedimage}\"\
            \ />`),\n        or an NVCF asset ID (`<img src=\"data:image/{format};asset_id,{asset_id}\"\
            \ />`)\n        when the container is hosted in NVCF and the payload exceeds\
            \ 200KB.\n        or http link (`https:{image_link}`)\n        <br>  \
            \  - When content is a list of objects, images can be passed as objects\
            \ with type=`image_url`.\n        <br>    - In both cases, images can\
            \ be PNG, JPG or JPEG.\n        <br>To pass videos (only with role=`user`):\n\
            \        <br>    - When content is a string, video can be passed together\
            \ with the text with `video` HTML tags that wraps\n        a video URL\
            \ (`<video src=\"{url}\" />`),\n        base64 encoded video data (`video\
            \ src=\"data:video/{format};base64,{base64encodedvideo}\" />`),\n    \
            \    or an NVCF asset ID (`<video src=\"data:video/{format};asset_id,{asset_id}\"\
            \ />`),\n        or http link (`https:{video_link}`)\n        when the\
            \ container is hosted in NVCF and the payload exceeds 200KB.\n       \
            \ <br>    - When content is a list of objects, images can be passed as\
            \ objects with type=`video_url` or `rtsp`.\n        For rtsp streams,\
            \ an extra parameter `duration` needs to be set as the length of the stream\
            \ in seconds to be\n        sampled.\n        <br>    - In both cases,\
            \ videos can be H.264, H.265, AV1, JPEG and MJPEG formats.\n        <br>For\
            \ `system` and `assistant` roles, the object list format is not supported.\n\
            \        "
        tool_call_id:
          anyOf:
          - type: string
          - type: 'null'
          title: Tool Call Id
          description: The id of the tool call.
        name:
          anyOf:
          - type: string
          - type: 'null'
          title: Name
          description: The name of the tool called.
        tool_calls:
          anyOf:
          - items:
              $ref: '#/components/schemas/ToolCall'
            type: array
          - type: 'null'
          title: Tool Calls
          description: The tool(s) called by the model.
      type: object
      required:
      - role
      - content
      title: NIMLLMChatCompletionMessage
    NIMLLMChatCompletionRequest:
      properties:
        messages:
          items:
            $ref: '#/components/schemas/NIMLLMChatCompletionMessage'
          type: array
          minItems: 1
          title: Messages
          description: A list of messages comprising the conversation so far.
        model:
          type: string
          title: Model
          description: The model to use.
        frequency_penalty:
          anyOf:
          - type: number
            maximum: 2.0
            minimum: -2.0
          - type: 'null'
          title: Frequency Penalty
          description: Number between -2.0 and 2.0. Positive values penalize new tokens
            based on their existing frequency in the text so far, decreasing the model's
            likelihood to repeat the same line verbatim.
          default: 0.0
        logit_bias:
          anyOf:
          - additionalProperties:
              type: number
            type: object
          - type: 'null'
          title: Logit Bias
          description: Modify the likelihood of specified tokens appearing in the
            completion. Accepts a JSON object that maps tokens (specified by their
            token ID in the tokenizer) to an associated bias value from -100 to 100.
            Mathematically, the bias is added to the logits generated by the model
            prior to sampling. The exact effect varies based on the model, but values
            between -1 and 1 should decrease or increase likelihood of selection;
            values at the ends of the range, such as -100 or 100 should result in
            a ban or exclusive selection of the relevant token.
        logprobs:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Logprobs
          description: Whether to return log probabilities of the output tokens or
            not. If true, returns the log probabilities of each output token returned
            in the `content` of `message`.
          default: false
        top_logprobs:
          anyOf:
          - type: integer
            maximum: 20.0
            minimum: 1.0
          - type: 'null'
          title: Top Logprobs
          description: An integer specifying the number of most likely tokens to return
            at each token position, each with an associated log probability. `logprobs`
            must be set to `true` if this parameter is used.
        max_tokens:
          anyOf:
          - type: integer
            minimum: 1.0
          - type: 'null'
          title: Max Tokens
          description: The maximum number of tokens that can be generated.
        n:
          anyOf:
          - type: integer
            maximum: 128.0
            minimum: 1.0
          - type: 'null'
          title: N
          description: How many completions to generate for each prompt.
          default: 1
        presence_penalty:
          anyOf:
          - type: number
            maximum: 2.0
            minimum: -2.0
          - type: 'null'
          title: Presence Penalty
          description: Number between -2.0 and 2.0. Positive values penalize new tokens
            based on whether they appear in the text so far, increasing the model's
            likelihood to talk about new topics.
          default: 0.0
        response_format:
          anyOf:
          - $ref: '#/components/schemas/ResponseFormat'
          - type: 'null'
          description: 'An object specifying the format that the model must output.
            Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees
            the message the model generates is valid JSON.'
        seed:
          anyOf:
          - type: integer
            maximum: 9.223372036854776e+18
            minimum: -9.223372036854776e+18
          - type: 'null'
          title: Seed
          description: Changing the seed produces a different response with similar
            characteristics. Fixing the seed reproduces the same results if all other
            parameters are also kept constant.
        stop:
          anyOf:
          - type: string
          - items:
              type: string
            type: array
          - type: 'null'
          title: Stop
          description: Sequences where the API will stop generating further tokens.
        stream:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Stream
          description: 'If set, partial message deltas are sent, like in ChatGPT.
            Tokens are sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format)
            as they become available, with the stream terminated by a `data: [DONE]`'
          default: false
        stream_options:
          anyOf:
          - $ref: '#/components/schemas/StreamOptions'
          - type: 'null'
        temperature:
          anyOf:
          - type: number
            maximum: 2.0
            minimum: 0.0
          - type: 'null'
          title: Temperature
          description: What sampling temperature to use, between 0 and 2. Higher values
            such as 0.8 make the output more random, while lower values such as 0.2
            make it more focused and deterministic.
          default: 0.5
        top_p:
          anyOf:
          - type: number
            maximum: 1.0
            exclusiveMinimum: 0.0
          - type: 'null'
          title: Top P
          description: An alternative to sampling with temperature, called nucleus
            sampling, where the model considers the results of the tokens with `top_p`
            probability mass. So 0.1 means only the tokens comprising the top 10%
            probability mass are considered. NVIDIA recommends that you alter this
            option or `temperature` but not both.
          default: 1.0
        tools:
          anyOf:
          - items:
              $ref: '#/components/schemas/ChatCompletionToolsParam'
            type: array
          - type: 'null'
          title: Tools
        tool_choice:
          anyOf:
          - type: string
            enum:
            - none
            - auto
            - required
          - $ref: '#/components/schemas/ChatCompletionNamedToolChoiceParam'
          - type: 'null'
          title: Tool Choice
          description: Controls which (if any) tool is called by the model.
          default: none
        parallel_tool_calls:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Parallel Tool Calls
          default: false
        user:
          anyOf:
          - type: string
          - type: 'null'
          title: User
        min_p:
          type: number
          title: Min P
          default: 0.0
        prompt_logprobs:
          anyOf:
          - type: integer
          - type: 'null'
          title: Prompt Logprobs
        echo:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Echo
          description: This is currently unsupported. If true, the previous message
            is emitted again before the current message if they belong to the same
            role.
          default: false
        add_special_tokens:
          type: boolean
          title: Add Special Tokens
          description: If true, special tokens (e.g. BOS) will be added to the prompt
            on top of what is added by the chat template. For most models, the chat
            template takes care of adding the special tokens so this should be set
            to false (as is the default).
          default: false
        documents:
          anyOf:
          - items:
              additionalProperties:
                type: string
              type: object
            type: array
          - type: 'null'
          title: Documents
          description: A list of dicts representing documents that will be accessible
            to the model if it is performing RAG (retrieval-augmented generation).
            If the template does not support RAG, this argument will have no effect.
            We recommend that each document should be a dict containing "title" and
            "text" keys.
        chat_template:
          anyOf:
          - type: string
          - type: 'null'
          title: Chat Template
          description: A Jinja template to use for this conversion. As of transformers
            v4.44, default chat template is no longer allowed, so you must provide
            a chat template if the tokenizer does not define one.
        chat_template_kwargs:
          anyOf:
          - type: object
          - type: 'null'
          title: Chat Template Kwargs
          description: Additional kwargs to pass to the template renderer. Will be
            accessible by the chat template.
        guided_whitespace_pattern:
          anyOf:
          - type: string
          - type: 'null'
          title: Guided Whitespace Pattern
          description: If specified, will override the default whitespace pattern
            for guided json decoding.
        image:
          anyOf:
          - type: string
          - type: 'null'
          title: Image
          description: The image as a string or null.
        nvext:
          anyOf:
          - $ref: '#/components/schemas/NVExt'
          - type: 'null'
          description: Extension dictionary for NIM API.
        num_frames_per_inference:
          anyOf:
          - type: integer
            maximum: 32.0
            minimum: 1.0
          - type: 'null'
          title: Num Frames Per Inference
          description: Number of frames to sample from the video or stream. They will
            be the input to model.
          default: 8
        media_response_type:
          anyOf:
          - type: string
            enum:
            - none
            - image
            - video
          - type: 'null'
          title: Media Response Type
          description: The return format if there are media file outputs such as images
            or videos. `none` means to not return these files; `base64` means to return
            them as base64 string in response `content`, such as `The response content
            is... <img src="data:image/png;base64,{image_b64}" />`; `nvcf` means to
            store them in NVCF large storage directory
          default: none
      additionalProperties: false
      type: object
      required:
      - messages
      - model
      title: NIMLLMChatCompletionRequest
    NIMLLMChatCompletionResponse:
      properties:
        id:
          type: string
          title: Id
        object:
          type: string
          const: chat.completion
          title: Object
          default: chat.completion
        created:
          type: integer
          title: Created
        model:
          type: string
          title: Model
        choices:
          items:
            $ref: '#/components/schemas/ChatCompletionResponseChoice'
          type: array
          title: Choices
        usage:
          $ref: '#/components/schemas/UsageInfo'
        prompt_logprobs:
          anyOf:
          - items:
              anyOf:
              - additionalProperties:
                  $ref: '#/components/schemas/Logprob'
                type: object
              - type: 'null'
            type: array
          - type: 'null'
          title: Prompt Logprobs
        data:
          anyOf:
          - items:
              $ref: '#/components/schemas/NIMLLMMediaObject'
            type: array
          - type: 'null'
          title: Data
          description: If specified, returns the media data generated by chat completion.
      additionalProperties: false
      type: object
      required:
      - model
      - choices
      - usage
      title: NIMLLMChatCompletionResponse
    NIMLLMChatCompletionStreamResponse:
      properties:
        id:
          type: string
          title: Id
        object:
          type: string
          const: chat.completion.chunk
          title: Object
          default: chat.completion.chunk
        created:
          type: integer
          title: Created
        model:
          type: string
          title: Model
        choices:
          items:
            $ref: '#/components/schemas/ChatCompletionResponseStreamChoice'
          type: array
          title: Choices
        usage:
          anyOf:
          - $ref: '#/components/schemas/UsageInfo'
          - type: 'null'
        data:
          anyOf:
          - items:
              $ref: '#/components/schemas/NIMLLMMediaObject'
            type: array
          - type: 'null'
          title: Data
          description: If specified, returns the media data generated by chat completion.
      additionalProperties: false
      type: object
      required:
      - model
      - choices
      title: NIMLLMChatCompletionStreamResponse
    NIMLLMMediaObject:
      properties:
        type:
          type: string
          title: Type
          description: The media type, such as image/jpeg, video/mp4.
        b64_json:
          anyOf:
          - type: string
          - type: 'null'
          title: B64 Json
          description: The base64-encoded JSON of the generated media.
        url:
          anyOf:
          - type: string
          - type: 'null'
          title: Url
          description: The URL of the generated media, if response_format is url (default).
        revised_prompt:
          anyOf:
          - type: string
          - type: 'null'
          title: Revised Prompt
          description: The prompt that was used to generate the media, if there was
            any revision to the prompt.
      type: object
      required:
      - type
      title: NIMLLMMediaObject
    NIMLLMVersionResponse:
      properties:
        release:
          type: string
          title: Release
          description: The product release version of NIM for LLMs.
        api:
          type: string
          title: Api
          description: The semver API version running inside the NIM.
      type: object
      required:
      - release
      - api
      title: NIMLLMVersionResponse
    NIMLicenseInfoResponse:
      properties:
        name:
          type: string
          title: Name
          description: The name of the NIMs license.
        path:
          type: string
          title: Path
          description: The path of the NIMs license file inside the container.
        sha:
          type: string
          title: Sha
          description: The unique identifier of the license.
        size:
          type: integer
          title: Size
          description: The size, in bytes, of the license file.
        url:
          type: string
          title: Url
          description: The url of the NIMs license.
        type:
          type: string
          title: Type
          description: The content type of the license.
        content:
          type: string
          title: Content
          description: The content inside the NIMs license file.
      type: object
      required:
      - name
      - path
      - sha
      - size
      - url
      - type
      - content
      title: NIMLicenseInfoResponse
    NIMVLMChatCompletionContentPartImage:
      properties:
        image:
          type: string
          title: Image
        type:
          type: string
          const: image
          title: Type
      type: object
      required:
      - image
      - type
      title: NIMVLMChatCompletionContentPartImage
    NIMVLMChatCompletionContentPartText:
      properties:
        text:
          type: string
          minLength: 1
          title: Text
        type:
          type: string
          const: text
          title: Type
      type: object
      required:
      - text
      - type
      title: NIMVLMChatCompletionContentPartText
    NIMVLMChatCompletionContentPartVideo:
      properties:
        video:
          $ref: '#/components/schemas/VideoURL'
        start_offset:
          anyOf:
          - type: number
          - type: 'null'
          title: Start Offset
        duration:
          anyOf:
          - type: number
          - type: 'null'
          title: Duration
        type:
          type: string
          const: video
          title: Type
      type: object
      title: NIMVLMChatCompletionContentPartVideo
    NIMVLMChatCompletionContentPartVideoStreaming:
      properties:
        video_url:
          $ref: '#/components/schemas/VideoURL'
        connect_timeout:
          anyOf:
          - type: number
          - type: 'null'
          title: Connect Timeout
        duration:
          type: number
          title: Duration
        fps:
          anyOf:
          - type: number
          - type: 'null'
          title: Fps
        type:
          type: string
          const: rtsp
          title: Type
      type: object
      title: NIMVLMChatCompletionContentPartVideoStreaming
    NVExt:
      properties:
        ignore_eos:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Ignore Eos
          description: Whether to ignore End of Sequence (EOS) tokens.
        repetition_penalty:
          anyOf:
          - type: number
            maximum: 2.0
            exclusiveMinimum: 0.0
          - type: 'null'
          title: Repetition Penalty
          description: How much to penalize tokens based on how frequently they occur
            in the text. A value of 1 means no penalty, while values larger than 1
            discourage and values smaller encourage.
          default: 1.0
        top_k:
          type: integer
          minimum: -1.0
          title: Top K
          description: How many of the top tokens to sample from. Must be -1 or greater
            than or equal to 1, and cannot be null. If not set, then the default is
            -1 which disables `top_k` sampling (greedy).
          default: -1
        guided_choice:
          anyOf:
          - items:
              type: string
            type: array
          - type: 'null'
          title: Guided Choice
          description: If specified, the output is exactly one of the choices.
        guided_json:
          anyOf:
          - type: string
          - type: object
          - $ref: '#/components/schemas/BaseModel'
          - type: 'null'
          title: Guided Json
          description: If specified, the output follows the JSON schema. Can be a
            string, an object, a reference to a BaseModel, or null.
        guided_regex:
          anyOf:
          - type: string
          - type: 'null'
          title: Guided Regex
          description: If specified, the output follows the regex pattern. Can be
            a string or null.
        guided_grammar:
          anyOf:
          - type: string
          - type: 'null'
          title: Guided Grammar
          description: If specified, the output follows the context-free grammar.
            Can be a string or null.
      type: object
      title: NVExt
    ResponseFormat:
      properties:
        type:
          type: string
          enum:
          - text
          - json_object
          title: Type
          description: Must be one of `text` or `json_object`.
          example: json_object
      type: object
      required:
      - type
      title: ResponseFormat
    Role:
      type: string
      enum:
      - assistant
      - user
      - system
      - tool
      - function
      title: Role
    StreamOptions:
      properties:
        include_usage:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Include Usage
          default: true
        continuous_usage_stats:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Continuous Usage Stats
          default: true
      additionalProperties: false
      type: object
      title: StreamOptions
    ToolCall:
      properties:
        index:
          anyOf:
          - type: integer
          - type: 'null'
          title: Index
        id:
          type: string
          title: Id
        type:
          type: string
          const: function
          title: Type
          default: function
        function:
          $ref: '#/components/schemas/FunctionCall'
      additionalProperties: false
      type: object
      required:
      - function
      title: ToolCall
    UsageInfo:
      properties:
        prompt_tokens:
          type: integer
          title: Prompt Tokens
          default: 0
        total_tokens:
          type: integer
          title: Total Tokens
          default: 0
        completion_tokens:
          anyOf:
          - type: integer
          - type: 'null'
          title: Completion Tokens
          default: 0
      additionalProperties: false
      type: object
      title: UsageInfo
    ValidationError:
      properties:
        loc:
          items:
            anyOf:
            - type: string
            - type: integer
          type: array
          title: Location
        msg:
          type: string
          title: Message
        type:
          type: string
          title: Error Type
      type: object
      required:
      - loc
      - msg
      - type
      title: ValidationError
    VideoURL:
      properties:
        url:
          type: string
          title: Url
      type: object
      required:
      - url
      title: VideoURL