> ## Documentation Index
> Fetch the complete documentation index at: https://docs.siray.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Qwen3 Max 256K


## OpenAPI

````yaml openapi-spec/qwen3-max-256k.json POST /v1/chat/completions
openapi: 3.1.0
info:
  description: >-
    Alibaba's Qwen3 Max is a premium LLM with an ultra-long 256K context for
    deep document analysis, complex reasoning, and high-quality generation.
  summary: API for Qwen3 Max 256K model
  title: Qwen3 Max 256K API
  version: 1.0.0
servers:
  - description: Model Verse API Server
    url: https://api.siray.ai
security: []
tags:
  - description: >-
      Qwen3 Max 256K - Alibaba's Qwen3 Max is a premium LLM with an ultra-long
      256K context for deep document analysis, complex reasoning, and
      high-quality generation.
    name: Qwen3 Max 256K
paths:
  /v1/chat/completions:
    post:
      tags:
        - Qwen3 Max 256K
      summary: Create chat completion
      description: Generate a chat completion using the Qwen3 Max 256K model
      operationId: token_model-de6tzdf802fbb9gd
      requestBody:
        content:
          application/json:
            example:
              frequency_penalty: 0
              max_tokens: 32768
              messages:
                - content: example_value
                  role: system
              model: alibaba/qwen3-max-256k
              presence_penalty: 0
              stream: false
              temperature: 1
              top_p: 1
            schema:
              description: OpenAI-compatible chat completions API request format
              properties:
                frequency_penalty:
                  default: 0
                  description: Penalty for frequent tokens
                  maximum: 2
                  minimum: -2
                  type: number
                max_tokens:
                  default: 32768
                  description: Maximum number of tokens to generate
                  maximum: 32768
                  minimum: 1
                  type: integer
                messages:
                  description: Array of conversation messages with roles
                  items:
                    properties:
                      content:
                        description: Message content
                        type: string
                      role:
                        description: Message role
                        enum:
                          - system
                          - user
                          - assistant
                        type: string
                    required:
                      - role
                      - content
                    type: object
                  minItems: 1
                  type: array
                model:
                  description: Model name to use for the request
                  enum:
                    - alibaba/qwen3-max-256k
                  type: string
                presence_penalty:
                  default: 0
                  description: Penalty for new topics
                  maximum: 2
                  minimum: -2
                  type: number
                stream:
                  default: false
                  description: Enable streaming response
                  type: boolean
                temperature:
                  default: 1
                  description: Controls randomness in output (higher = more random)
                  maximum: 2
                  minimum: 0
                  type: number
                top_p:
                  default: 1
                  description: Nucleus sampling parameter (controls diversity)
                  maximum: 1
                  minimum: 0
                  type: number
              required:
                - model
                - messages
              title: Chat Completions Request
              type: object
        description: Request payload
        required: true
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ChatCompletionResponse'
          description: Successful response
      security:
        - bearerAuth: []
components:
  schemas:
    ChatCompletionResponse:
      description: Chat completion response
      properties:
        choices:
          items:
            $ref: '#/components/schemas/ChatCompletionChoice'
          type: array
        created:
          description: Unix timestamp of when the completion was created
          type: integer
        id:
          description: Unique identifier for the chat completion
          type: string
        model:
          description: The model used for the completion
          type: string
        object:
          description: Object type, typically 'chat.completion.chunk'
          type: string
        system_fingerprint:
          description: System fingerprint for the completion
          type: string
        usage:
          oneOf:
            - $ref: '#/components/schemas/ChatUsage'
            - type: 'null'
      required:
        - id
        - object
        - created
        - model
        - choices
      title: ChatCompletionsStreamResponse
      type: object
    ChatCompletionChoice:
      description: Chat completion choice
      properties:
        delta:
          $ref: '#/components/schemas/ChatCompletionDelta'
        finish_reason:
          description: Reason why the completion finished
          enum:
            - stop
            - length
            - tool_calls
            - content_filter
            - null
          type: string
        index:
          description: Index of the choice
          type: integer
        logprobs:
          description: Log probabilities for the choice
      required:
        - index
      type: object
    ChatUsage:
      description: Token usage information
      properties:
        completion_tokens:
          description: Number of tokens in the completion
          type: integer
        completion_tokens_details:
          $ref: '#/components/schemas/OutputTokenDetails'
        input_tokens:
          description: Number of input tokens
          type: integer
        input_tokens_details:
          oneOf:
            - $ref: '#/components/schemas/InputTokenDetails'
            - type: 'null'
        output_tokens:
          description: Number of output tokens
          type: integer
        prompt_cache_hit_tokens:
          description: Number of prompt tokens retrieved from cache
          type: integer
        prompt_tokens:
          description: Number of tokens in the prompt
          type: integer
        prompt_tokens_details:
          $ref: '#/components/schemas/InputTokenDetails'
        total_tokens:
          description: Total number of tokens used
          type: integer
      required:
        - prompt_tokens
        - completion_tokens
        - total_tokens
        - prompt_tokens_details
        - completion_tokens_details
        - input_tokens
        - output_tokens
      type: object
    ChatCompletionDelta:
      description: Message delta in streaming response
      properties:
        content:
          description: Content of the message delta
          type: string
        reasoning:
          description: Alternative reasoning field
          type: string
        reasoning_content:
          description: Reasoning content of the message delta
          type: string
        role:
          description: Role of the message author
          enum:
            - system
            - user
            - assistant
            - tool
          type: string
        tool_calls:
          items:
            $ref: '#/components/schemas/ToolCallResponse'
          type: array
      type: object
    OutputTokenDetails:
      description: Detailed output token usage information
      properties:
        audio_tokens:
          description: Number of audio tokens in output
          type: integer
        reasoning_tokens:
          description: Number of reasoning tokens in output
          type: integer
        text_tokens:
          description: Number of text tokens in output
          type: integer
      required:
        - text_tokens
        - audio_tokens
        - reasoning_tokens
      type: object
    InputTokenDetails:
      description: Detailed input token usage information
      properties:
        audio_tokens:
          description: Number of audio tokens
          type: integer
        cached_tokens:
          description: Number of cached tokens
          type: integer
        image_tokens:
          description: Number of image tokens
          type: integer
        text_tokens:
          description: Number of text tokens
          type: integer
      required:
        - cached_tokens
        - text_tokens
        - audio_tokens
        - image_tokens
      type: object
    ToolCallResponse:
      description: Tool call in the response
      properties:
        function:
          $ref: '#/components/schemas/FunctionResponse'
        id:
          description: Unique identifier for the tool call
          type: string
        index:
          description: Index of the tool call in streaming chunks
          type: integer
        type:
          description: Type of the tool call
      required:
        - function
      type: object
    FunctionResponse:
      description: Function call details
      properties:
        arguments:
          description: Arguments to call the function with, in JSON format
          type: string
        description:
          description: Description of the function
          type: string
        name:
          description: Name of the function
          type: string
        parameters:
          description: Parameters schema for the function
      required:
        - arguments
      type: object
  securitySchemes:
    bearerAuth:
      bearerFormat: API Key
      description: Bearer authentication using API key
      scheme: bearer
      type: http

````