FriendliAI Container.Chat API

openapi: 3.2.0
info:
  title: Friendli Suite API Reference Container.Audio Container.Chat API
  description: This is an OpenAPI reference of Friendli Suite API.
  termsOfService: https://friendli.ai/terms-of-service
  contact:
    name: FriendliAI Support Team
    email: support@friendli.ai
  version: 0.1.0
servers:
- url: https://api.friendli.ai
tags:
- name: Container.Chat
paths:
  /v1/chat/completions:
    servers:
    - url: http://localhost:8000
    post:
      tags:
      - Container.Chat
      summary: Chat completions
      description: Generate a model response from a list of messages comprising a conversation. Compatible with the OpenAI Chat Completions API, with support for streaming, tool calls, and structured outputs.
      operationId: containerChatComplete
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ContainerChatCompletionBody'
        required: true
      responses:
        '200':
          description: Successfully generated a chat response.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ContainerChatCompleteSuccess'
              examples:
                Example:
                  value:
                    id: chatcmpl-4b71d12c86d94e719c7e3984a7bb7941
                    object: chat.completion
                    choices:
                    - index: 0
                      message:
                        role: assistant
                        content: Hello there, how may I assist you today?
                      finish_reason: stop
                    usage:
                      prompt_tokens: 9
                      completion_tokens: 11
                      total_tokens: 20
                    created: 1735722153
        '422':
          description: Unprocessable Entity
      x-speakeasy-name-override: complete
      x-mint:
        metadata:
          title: Container Chat Completions
          sidebarTitle: Chat Completions
          og:title: Container Chat Completions
          description: Generate a model response from a list of messages comprising a conversation. Compatible with the OpenAI Chat Completions API, with support for streaming, tool calls, and structured outputs.
          og:description: Generate a model response from a list of messages comprising a conversation. Compatible with the OpenAI Chat Completions API, with support for streaming, tool calls, and structured outputs.
        href: /openapi/container/chat-completions
        content: 'Generate a model response from a list of messages comprising a conversation. Compatible with the OpenAI Chat Completions API, with support for streaming, tool calls, and structured outputs.


          When streaming mode is used (i.e., `stream` option is set to `true`), the response is in MIME type `text/event-stream`. Otherwise, the content type is `application/json`.

          You can view the schema of the streamed sequence of chunk objects in streaming mode [here](/openapi/container/chat-completions-chunk-object).'
  /v1/chat/completions#stream:
    servers:
    - url: http://localhost:8000
    post:
      tags:
      - Container.Chat
      summary: Stream chat completions
      description: Generate a model response from a list of messages comprising a conversation. Compatible with the OpenAI Chat Completions API, with support for streaming, tool calls, and structured outputs.
      operationId: containerChatStream
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ContainerChatCompletionStreamBody'
        required: true
      responses:
        '200':
          description: Successfully generated a chat response.
          content:
            text/event-stream:
              examples:
                Example:
                  value: 'data: {"id":"chatcmpl-4b71d12c86d94e719c7e3984a7bb7941","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"role":"assistant","content":"This"},"finish_reason":null,"logprobs":null}],"usage":null,"created":1726294381}


                    data: {"id":"chatcmpl-4b71d12c86d94e719c7e3984a7bb7941","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":" is"},"finish_reason":null,"logprobs":null}],"usage":null,"created":1726294381}


                    ...


                    data: {"id":"chatcmpl-4b71d12c86d94e719c7e3984a7bb7941","object":"chat.completion.chunk","choices":[{"index":0,"delta":{},"finish_reason":"stop","logprobs":null}],"usage":null,"created":1726294383}


                    data: {"id":"chatcmpl-4b71d12c86d94e719c7e3984a7bb7941","object":"chat.completion.chunk","choices":[],"usage":{"prompt_tokens":8,"completion_tokens":4,"total_tokens":12},"created":1726294402}


                    data: [DONE]

                    '
              x-speakeasy-sse-sentinel: '[DONE]'
              schema:
                $ref: '#/components/schemas/ContainerChatCompletionStreamSuccess'
        '422':
          description: Unprocessable Entity
      x-speakeasy-name-override: stream
      x-mint:
        metadata:
          title: Container Stream Chat Completions
          sidebarTitle: Stream Chat Completions
          og:title: Container Stream Chat Completions
          description: Generate a model response from a list of messages comprising a conversation. Compatible with the OpenAI Chat Completions API, with support for streaming, tool calls, and structured outputs.
          og:description: Generate a model response from a list of messages comprising a conversation. Compatible with the OpenAI Chat Completions API, with support for streaming, tool calls, and structured outputs.
        content: 'Generate a model response from a list of messages comprising a conversation. Compatible with the OpenAI Chat Completions API, with support for streaming, tool calls, and structured outputs.


          When streaming mode is used (i.e., `stream` option is set to `true`), the response is in MIME type `text/event-stream`. Otherwise, the content type is `application/json`.

          You can view the schema of the streamed sequence of chunk objects in streaming mode [here](/openapi/container/chat-completions-chunk-object).'
components:
  schemas:
    ChatCompleteBodyToolChoice:
      properties:
        type:
          type: string
          const: function
          title: Type
          description: The type of the tool. Currently, only `function` is supported.
        function:
          $ref: '#/components/schemas/ChatCompleteBodyToolChoiceFunction'
      type: object
      required:
      - type
      - function
      title: ChatCompleteBodyToolChoice
    PromptTokensDetails:
      properties:
        cached_tokens:
          anyOf:
          - type: integer
          - type: 'null'
          title: Cached Tokens
          description: Cached tokens present in the prompt.
      type: object
      title: PromptTokensDetails
    AssistantMessageToolCall:
      properties:
        id:
          type: string
          title: Id
          description: The ID of tool call.
        type:
          type: string
          const: function
          title: Type
          description: The type of tool call.
        function:
          $ref: '#/components/schemas/AssistantMessageToolCallFunction'
          description: The function specification
      type: object
      required:
      - id
      - type
      - function
      title: AssistantMessageToolCall
    AssistantMessage:
      properties:
        role:
          type: string
          const: assistant
          title: Role
          description: The role of the messages author.
        content:
          anyOf:
          - type: string
          - type: 'null'
          title: Content
          description: The content of assistant message. Required unless `tool_calls` is specified.
        reasoning_content:
          anyOf:
          - type: string
          - type: 'null'
          title: Reasoning Content
          description: The intermediate reasoning content of assistant message.
        reasoning:
          anyOf:
          - type: string
          - type: 'null'
          title: Reasoning
          description: The intermediate reasoning content of assistant message. This field is a compatible option for the 'reasoning_content' field.
        name:
          anyOf:
          - type: string
          - type: 'null'
          title: Name
          description: The name for the participant to distinguish between participants with the same role.
        tool_calls:
          anyOf:
          - items:
              $ref: '#/components/schemas/AssistantMessageToolCall'
            type: array
          - type: 'null'
          title: Tool Calls
      type: object
      required:
      - role
      title: AssistantMessage
    ResponseFormat:
      oneOf:
      - $ref: '#/components/schemas/ResponseFormatJsonSchema'
        title: Json Schema
      - $ref: '#/components/schemas/ResponseFormatJsonObject'
        title: Json Object
      - $ref: '#/components/schemas/ResponseFormatRegex'
        title: Regex
      - $ref: '#/components/schemas/ResponseFormatText'
        title: Text
      description: 'The enforced format of the model''s output.


        Note that the content of the output message may be truncated if it exceeds the `max_tokens`. You can check this by verifying that the `finish_reason` of the output message is `length`.


        For more detailed information, please refer [here](https://friendli.ai/docs/guides/structured-outputs).


        ***Important***

        You must explicitly instruct the model to produce the desired output format using a system prompt or user message (e.g., `You are an API generating a valid JSON as output.`).

        Otherwise, the model may result in an unending stream of whitespace or other characters.


        **When `response_format` is specified, `min_tokens` field is unsupported.**'
      discriminator:
        propertyName: type
        mapping:
          json_object: '#/components/schemas/ResponseFormatJsonObject'
          json_schema: '#/components/schemas/ResponseFormatJsonSchema'
          regex: '#/components/schemas/ResponseFormatRegex'
          text: '#/components/schemas/ResponseFormatText'
    ChatLogprobsContentTopLogprob:
      properties:
        token:
          type: string
          title: Token
          description: The token.
        logprob:
          type: number
          title: Logprob
          description: The log probability of this token.
        bytes:
          anyOf:
          - items:
              type: integer
            type: array
          - type: 'null'
          title: Bytes
          description: A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be `null` if there is no bytes representation for the token.
      type: object
      required:
      - token
      - logprob
      title: ChatLogprobsContentTopLogprob
    ResponseFormatJsonObject:
      properties:
        type:
          type: string
          const: json_object
          title: Type
          description: 'The type of the response format: `json_object`'
      type: object
      required:
      - type
      title: ResponseFormatJsonObject
    FunctionResult:
      properties:
        arguments:
          type: string
          title: Arguments
          description: 'The arguments for calling the function, generated by the model in JSON format.

            Ensure to validate these arguments in your code before invoking the function since the model may not always produce valid JSON.'
        name:
          type: string
          title: Name
          description: The name of the function to call.
      type: object
      required:
      - arguments
      - name
      title: FunctionResult
    UserMessageContentMultiModal:
      oneOf:
      - $ref: '#/components/schemas/TextContent'
        title: Text
      - $ref: '#/components/schemas/AudioContent'
        title: Audio
      - $ref: '#/components/schemas/ImageContent'
        title: Image
      - $ref: '#/components/schemas/VideoContent'
        title: Video
      discriminator:
        propertyName: type
        mapping:
          audio_url: '#/components/schemas/AudioContent'
          image_url: '#/components/schemas/ImageContent'
          text: '#/components/schemas/TextContent'
          video_url: '#/components/schemas/VideoContent'
    ChatLogprobsContent:
      properties:
        token:
          type: string
          title: Token
          description: The token.
        logprob:
          type: number
          title: Logprob
          description: The log probability of this token.
        bytes:
          anyOf:
          - items:
              type: integer
            type: array
          - type: 'null'
          title: Bytes
          description: A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be `null` if there is no bytes representation for the token.
        top_logprobs:
          items:
            $ref: '#/components/schemas/ChatLogprobsContentTopLogprob'
          type: array
          title: Top Logprobs
          description: List of the most likely tokens and their log probability, at this token position.
      type: object
      required:
      - token
      - logprob
      - top_logprobs
      title: ChatLogprobsContent
    VideoContent:
      properties:
        type:
          type: string
          const: video_url
          title: Type
          description: The type of the message content.
        video_url:
          $ref: '#/components/schemas/VideoData'
          description: The video URL data.
      type: object
      required:
      - type
      - video_url
      title: VideoContent
    ChatUsage:
      properties:
        prompt_tokens:
          type: integer
          title: Prompt Tokens
          description: Number of tokens in the prompt.
          examples:
          - 5
        completion_tokens:
          type: integer
          title: Completion Tokens
          description: Number of tokens in the generated chat completions.
          examples:
          - 7
        total_tokens:
          type: integer
          title: Total Tokens
          description: Total number of tokens used in the request (`prompt_tokens` + `completion_tokens`).
          examples:
          - 12
        prompt_tokens_details:
          anyOf:
          - $ref: '#/components/schemas/PromptTokensDetails'
          - type: 'null'
          description: Breakdown of tokens used in the prompt.
      type: object
      required:
      - prompt_tokens
      - completion_tokens
      - total_tokens
      title: ChatUsage
    StreamedToolCallResult:
      properties:
        type:
          type: string
          const: function
          title: Type
          description: The type of the tool.
        id:
          anyOf:
          - type: string
          - type: 'null'
          title: Id
          description: The ID of the tool call.
        index:
          type: integer
          title: Index
          description: The index of the tool call being generated.
        function:
          $ref: '#/components/schemas/StreamedFunctionResult'
      type: object
      required:
      - type
      - index
      - function
      title: StreamedToolCallResult
    AudioContent:
      properties:
        type:
          type: string
          const: audio_url
          title: Type
          description: The type of the message content.
        audio_url:
          $ref: '#/components/schemas/AudioData'
          description: The audio URL data.
      type: object
      required:
      - type
      - audio_url
      title: AudioContent
    TextContent:
      properties:
        type:
          type: string
          const: text
          title: Type
          description: The type of the message content.
        text:
          type: string
          title: Text
          description: The text content of the message.
      type: object
      required:
      - type
      - text
      title: TextContent
    AssistantMessageToolCallFunction:
      properties:
        name:
          type: string
          title: Name
          description: The name of function
        arguments:
          type: string
          title: Arguments
          description: The arguments of function in JSON schema format to call the function.
      type: object
      required:
      - name
      - arguments
      title: AssistantMessageToolCallFunction
    ToolMessage:
      properties:
        role:
          type: string
          const: tool
          title: Role
          description: The role of the messages author.
        content:
          type: string
          title: Content
          description: The content of tool message that contains the result of tool calling.
        tool_call_id:
          type: string
          title: Tool Call Id
          description: The ID of tool call corresponding to this message.
        name:
          anyOf:
          - type: string
          - type: 'null'
          title: Name
          description: An optional name of the tool call corresponding to this message.
      type: object
      required:
      - role
      - content
      - tool_call_id
      title: ToolMessage
    ToolCallResult:
      properties:
        type:
          type: string
          const: function
          title: Type
          description: The type of the tool.
        id:
          type: string
          title: Id
          description: The ID of the tool call.
        function:
          $ref: '#/components/schemas/FunctionResult'
      type: object
      required:
      - type
      - id
      - function
      title: ToolCallResult
    ResponseFormatText:
      properties:
        type:
          type: string
          const: text
          title: Type
          description: 'The type of the response format: `text`'
      type: object
      required:
      - type
      title: ResponseFormatText
    ResponseFormatRegex:
      properties:
        type:
          type: string
          const: regex
          title: Type
          description: 'The type of the response format: `regex`'
        schema:
          type: string
          title: Schema
          description: The schema of the output. Lookaheads or lookbehinds (e.g., `\a`, `\z`, `^`, `$`, `(?=)`, `(?!)`, `(?<=...)`, `(?<!...)`) are not supported. Group specials (e.g., `\w`, `\W`, `\d`, `\D`, `\s`, `\S`) do not support non-ASCII characters. Unicode escape patterns (e.g., `\N`, `\p`, `\P`) are not supported. Additionally, conditional matching (`(?(`) and back-references can cause inefficiency.
      type: object
      required:
      - type
      - schema
      title: ResponseFormatRegex
    SystemMessage:
      properties:
        role:
          type: string
          const: system
          title: Role
          description: The role of the messages author.
        content:
          type: string
          title: Content
          description: The content of system message.
        name:
          anyOf:
          - type: string
          - type: 'null'
          title: Name
          description: The name for the participant to distinguish between participants with the same role.
      type: object
      required:
      - role
      - content
      title: SystemMessage
    Message:
      oneOf:
      - $ref: '#/components/schemas/SystemMessage'
        title: System
      - $ref: '#/components/schemas/UserMessage'
        title: User
      - $ref: '#/components/schemas/AssistantMessage'
        title: Assistant
      - $ref: '#/components/schemas/ToolMessage'
        title: Tool
      discriminator:
        propertyName: role
        mapping:
          assistant: '#/components/schemas/AssistantMessage'
          system: '#/components/schemas/SystemMessage'
          tool: '#/components/schemas/ToolMessage'
          user: '#/components/schemas/UserMessage'
    ChatChoiceMessage:
      properties:
        content:
          anyOf:
          - type: string
          - type: 'null'
          title: Content
          description: The contents of the assistant message.
        role:
          type: string
          title: Role
          description: Role of the generated message author, in this case `assistant`.
        tool_calls:
          anyOf:
          - items:
              $ref: '#/components/schemas/ToolCallResult'
            type: array
          - type: 'null'
          title: Tool Calls
      type: object
      required:
      - role
      title: ChatChoiceMessage
    Function:
      properties:
        description:
          anyOf:
          - type: string
          - type: 'null'
          title: Description
          description: A description of what the function does, used by the model to choose when and how to call the function.
        name:
          type: string
          title: Name
          description: The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
        parameters:
          additionalProperties: true
          type: object
          title: Parameters
          description: 'The parameters the functions accepts, described as a JSON Schema object.

            To represent a function with no parameters, use the value `{"type": "object", "properties": {}}`.

            '
      type: object
      required:
      - name
      - parameters
      title: Function
    ChatResult:
      properties:
        id:
          type: string
          title: Id
          description: A unique ID of the chat completion.
        choices:
          items:
            $ref: '#/components/schemas/ChatChoice'
          type: array
          title: Choices
        usage:
          $ref: '#/components/schemas/ChatUsage'
        object:
          type: string
          const: chat.completion
          title: Object
          description: The object type, which is always set to `chat.completion`.
        created:
          type: integer
          title: Created
          description: The Unix timestamp (in seconds) for when the generation completed.
        model:
          anyOf:
          - type: string
          - type: 'null'
          title: Model
          description: The model to generate the completion. For dedicated endpoints, it returns the endpoint ID.
      type: object
      required:
      - id
      - choices
      - usage
      - object
      - created
      title: ChatResult
    StreamedChatResult:
      properties:
        data:
          $ref: '#/components/schemas/StreamedChatData'
      type: object
      required:
      - data
      title: StreamedChatResult
    ImageContent:
      properties:
        type:
          type: string
          const: image_url
          title: Type
          description: The type of the message content.
        image_url:
          $ref: '#/components/schemas/ImageData'
          description: The image URL data.
      type: object
      required:
      - type
      - image_url
      title: ImageContent
    ContainerChatCompleteSuccess:
      $ref: '#/components/schemas/ChatResult'
      title: ContainerChatCompleteSuccess
    ResponseFormatJsonSchema:
      properties:
        type:
          type: string
          const: json_schema
          title: Type
          description: 'The type of the response format: `json_schema`'
        json_schema:
          $ref: '#/components/schemas/ResponseFormatJsonSchemaSchema'
      type: object
      required:
      - type
      - json_schema
      title: ResponseFormatJsonSchema
    StreamedChatData:
      properties:
        id:
          type: string
          title: Id
          description: A unique ID of the chat completion.
        usage:
          anyOf:
          - $ref: '#/components/schemas/ChatUsage'
          - type: 'null'
        object:
          type: string
          const: chat.completion.chunk
          title: Object
          description: The object type, which is always set to `chat.completion.chunk`.
        choices:
          items:
            $ref: '#/components/schemas/StreamedChatChoice'
          type: array
          title: Choices
        created:
          type: integer
          title: Created
          description: The Unix timestamp (in seconds) for when the token is sampled.
        model:
          anyOf:
          - type: string
          - type: 'null'
          title: Model
          description: The model to generate the completion. For dedicated endpoints, it returns the endpoint ID.
      type: object
      required:
      - id
      - object
      - choices
      - created
      title: StreamedChatData
    VideoData:
      properties:
        url:
          type: string
          title: Url
          description: The URL of the video.
      type: object
      required:
      - url
      title: VideoData
    UserMessage:
      properties:
        role:
          type: string
          const: user
          title: Role
          description: The role of the message's author.
        content:
          anyOf:
          - type: string
            description: 'The content of user message, which is plain text.


              For **multi-modal format**, use `object[]` type. Support for non-text input is currently in **Beta**.'
          - items:
              $ref: '#/components/schemas/UserMessageContentMultiModal'
            type: array
            description: 'The content of user message.


              **Multi-modal format** can handle not just text, but also audio, image, and video content, allowing for more complex message structures. Support for non-text input is currently in **Beta**.'
          title: Content
        name:
          anyOf:
          - type: string
          - type: 'null'
          title: Name
          description: The name for the participant to distinguish between participants with the same role.
      type: object
      required:
      - role
      - content
      title: UserMessage
    StreamOptions:
      properties:
        include_usage:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Include Usage
          description: 'When set to `true`,

            the number of tokens used will be included at the end of the stream result in the form of

            `"usage": {"completion_tokens": number, "prompt_tokens": number, "total_tokens": number}`.

            '
      type: object
      title: StreamOptions
    ChatChoice:
      properties:
        index:
          type: integer
          title: Index
          description: The index of the choice in the list of generated choices.
          examples:
          - 0
        logprobs:
          anyOf:
          - $ref: '#/components/schemas/ChatLogprobs'
          - type: 'null'
        message:
          $ref: '#/components/schemas/ChatChoiceMessage'
        finish_reason:
          type: string
          enum:
          - stop
          - length
          - tool_calls
          title: Finish Reason
          description: 'Termination condition of the generation. `stop` means the API returned the full chat completions generated by the model without running into any limits.

            `length` means the generation exceeded `max_tokens` or the conversation exceeded the max context length.

            `tool_calls` means the API has generated tool calls.'
      type: object
      required:
      - index
      - message
      - finish_reason
      title: ChatChoice
    StreamedChatChoiceDelta:
      properties:
        content:
          anyOf:
          - type: string
          - type: 'null'
          title: Content
          description: The contents of the assistant message.
        role:
          anyOf:
          - type: string
          - type: 'null'
          title: Role
          description: Role of the generated message author, in this case `assistant`.
        tool_calls:
          anyOf:
          - items:
              $ref: '#/components/schemas/StreamedToolCallResult'
            type: array
          - type: 'null'
          title: Tool Calls
      type: object
      title: StreamedChatChoiceDelta
    ChatLogprobs:
      properties:
        content:
          anyOf:
          - items:
              $ref: '#/components/schemas/ChatLogprobsContent'
            type: array
          - type: 'null'
          title: Content
          description: A list of message content tokens with log probability information.
      type: object
      title: ChatLogprobs
    StreamedFunctionResult:
      properties:
        arguments:
          type: string
          title: Arguments
          description: 'The arguments for calling the function, generated by the model in JSON format.

            Ensure to validate these arguments in your code before invoking the function since the model may not always produce valid JSON.'
        name:
          anyOf:
          - type: string
          - type: 'null'
          title: Name
          description: The name of the function to call.
      type: object
      required:
      - arguments
      title: StreamedFunctionResult
    ImageData:
      properties:
        url:
          type: string
          title: Url
          description: The URL of the image.
      type: object
      required:
      - url
      title: ImageData
    ChatCompleteBodyToolChoiceFunction:
      properties:
        name:
          type: string
          title: Name
          description: The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
      type: object
      required:
      - name
      title: ChatCompleteBodyToolChoiceFunction
    ContainerChatCompletionBody:
      properties:
        model:
          anyOf:
          - type: string
          - type: 'null'
          title: Model
          description: Routes the request to a specific adapter.
          examples:
          - (adapter-route)
        messages:
          items:
            $ref: '#/components/schemas/Message'
          type: array
          title: Messages
          description: A list of messages comprising the conversation so far.
          examples:
          - - content: You are a helpful assistant.
              role: system
            - content: Hello!
              role: user
        chat_template_kwargs:
          anyOf:
          - additionalProperties: true
            type: object
          - type: 'null'
          title: Chat Template Kwargs
          description: Additional keyword arguments supplied to the template renderer. These parameters will be available for use within the chat template.
        eos_token:
          anyOf:
          - items:
              type: integer
            type: array
          - type: 'null'
          title: Eos Token
          description: A list of endpoint sentence tokens.
        frequency_penalty:
          anyOf:
          - type: number
          - type: 'null'
          title: Frequency Penalty
          description: Number between -2.0 and 2.0. Positive values penalizes tokens that have been sampled, taking into account their frequency in the preceding text. This penalization diminishes the model's tendency to reproduce identical lines verbatim.
        logit_bias:
          anyOf:
          - additionalProperties: true
            type: object
          - type: 'null'
          title: Logit Bias
          description: Accepts a JSON object that maps tokens to an associated bias value. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model.
        logprobs:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Logprobs
          description: Whether to return log probabilities of the output tokens or not.
        max_tokens:
          anyOf:
          - type: integer
          - type: 'null'
          title: Max Tokens
          description: The maximum number of tokens to generate. For decoder-only models like GPT, the length of your input tokens plus `max_tokens` should not exceed the model's maximum length (e.g., 2048 for OpenAI GPT-3). For encoder-decoder models like T5 or BlenderBot, `max_tokens` should

# --- truncated at 32 KB (59 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/friendliai/refs/heads/main/openapi/friendliai-container-chat-api-openapi.yml