QuantCDN AI Inference API

openapi: 3.0.0
info:
  description: Unified API for QuantCDN Admin and QuantCloud Platform services
  title: QuantCDN AI Agents AI Inference API
  version: 4.15.8
servers:
- description: QuantCDN Public Cloud
  url: https://dashboard.quantcdn.io
- description: QuantGov Cloud
  url: https://dash.quantgov.cloud
security:
- BearerAuth: []
tags:
- description: Chat inference, embeddings, and image generation services
  name: AI Inference
paths:
  /api/v3/organizations/{organisation}/ai/chat:
    post:
      description: "Sends requests to the AI API Gateway endpoint which buffers responses. Supports text, images, videos, and documents via base64 encoding.\n     *\n     * **Execution Modes:**\n     * - **Sync Mode** (default): Standard JSON response, waits for completion (200 response)\n     * - **Async Mode**: Set `async: true` for long-running tasks with polling (202 response)\n     *\n     * **Async/Durable Mode (`async: true`):**\n     * - Returns immediately with `requestId` and `pollUrl` (HTTP 202)\n     * - Uses AWS Lambda Durable Functions for long-running inference\n     * - Supports client-executed tools via `waiting_callback` state\n     * - Poll `/ai/chat/executions/{requestId}` for status\n     * - Submit client tool results via `/ai/chat/callback`\n     * - Ideal for complex prompts, large contexts, or client-side tools\n     *\n     * **Multimodal Support:**\n     * - **Text**: Simple string content\n     * - **Images**: Base64-encoded PNG, JPEG, GIF, WebP (up to 25MB)\n     * - **Videos**: Base64-encoded MP4, MOV, WebM, etc. (up to 25MB)\n     * - **Documents**: Base64-encoded PDF, DOCX, CSV, etc. (up to 25MB)\n     *\n     * **Supported Models (Multimodal):**\n     * - **Claude 4.5 Series**: Sonnet 4.5, Haiku 4.5, Opus 4.5 (images, up to 20 per request)\n     * - **Claude 3.5 Series**: Sonnet v1/v2 (images, up to 20 per request)\n     * - **Amazon Nova**: Lite, Pro, Micro (images, videos, documents)\n     *\n     * **Usage Tips:**\n     * - Use base64 encoding for images/videos < 5-10MB\n     * - Place media before text prompts for best results\n     * - Label multiple media files (e.g., 'Image 1:', 'Image 2:')\n     * - Maximum 25MB total payload size\n     *\n     * **Response Patterns:**\n     * - **Text-only**: Returns simple text response when no tools requested\n     * - **Single tool**: Returns `toolUse` object when AI requests one tool\n     * - **Multiple tools**: Returns `toolUse` array when AI requests multiple tools\n     * - **Auto-execute sync**: Automatically executes tool and returns final text response\n     * - **Auto-execute async**: Returns toolUse with `executionId` and `status` for polling"
      operationId: chatInference
      parameters:
      - description: The organisation ID
        explode: false
        in: path
        name: organisation
        required: true
        schema:
          type: string
        style: simple
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/chatInference_request'
        description: Chat request with optional multimodal content blocks
        required: true
      responses:
        '200':
          content:
            application/json:
              example:
                response:
                  role: assistant
                  content: The capital of Australia is Canberra.
                model: amazon.nova-lite-v1:0
                requestId: req-abc123
                finishReason: stop
                usage:
                  inputTokens: 12
                  outputTokens: 8
                  totalTokens: 20
                  costCents: 0.18
              schema:
                $ref: '#/components/schemas/chatInference_200_response'
          description: Chat inference completed (buffered response, sync mode)
        '202':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/chatInference_202_response'
          description: 'Async execution started (when `async: true` in request)'
        '500':
          description: Failed to perform chat inference
      summary: Chat inference via API Gateway (buffered responses) with multimodal support
      tags:
      - AI Inference
  /api/v3/organizations/{organisation}/ai/chat/stream:
    post:
      description: "Streams responses from the AI streaming subdomain using Server-Sent Events (SSE). Tokens are streamed in real-time as they are generated.\n     *\n     * **Execution Modes:**\n     * - **Streaming Mode** (default): Real-time SSE token-by-token responses\n     * - **Async Mode**: Set `async: true` for long-running tasks with polling (202 response)\n     *\n     * **Async/Durable Mode (`async: true`):**\n     * - Returns immediately with `requestId` and `pollUrl` (HTTP 202)\n     * - Uses AWS Lambda Durable Functions for long-running inference\n     * - Supports client-executed tools via `waiting_callback` state\n     * - Poll `/ai/chat/executions/{requestId}` for status\n     * - Submit client tool results via `/ai/chat/callback`\n     *\n     * **Multimodal Support:**\n     * - **Text**: Simple string content\n     * - **Images**: Base64-encoded PNG, JPEG, GIF, WebP (up to 25MB)\n     * - **Videos**: Base64-encoded MP4, MOV, WebM, etc. (up to 25MB)\n     * - **Documents**: Base64-encoded PDF, DOCX, CSV, etc. (up to 25MB)\n     *\n     * **Supported Models (Multimodal):**\n     * - **Claude 4.5 Series**: Sonnet 4.5, Haiku 4.5, Opus 4.5 (images, up to 20 per request)\n     * - **Claude 3.5 Series**: Sonnet v1/v2 (images, up to 20 per request)\n     * - **Amazon Nova**: Lite, Pro, Micro (images, videos, documents)\n     *\n     * **Usage Tips:**\n     * - Use base64 encoding for images/videos < 5-10MB\n     * - Place media before text prompts for best results\n     * - Label multiple media files (e.g., 'Image 1:', 'Image 2:')\n     * - Maximum 25MB total payload size\n     * - Streaming works with all content types (text, image, video, document)"
      operationId: chatInferenceStream
      parameters:
      - description: The organisation ID
        explode: false
        in: path
        name: organisation
        required: true
        schema:
          type: string
        style: simple
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/chatInferenceStream_request'
        description: Chat request with optional multimodal content blocks
        required: true
      responses:
        '200':
          content:
            text/event-stream:
              example: 'id: chunk-0

                event: start

                data: {"requestId":"abc123","model":"amazon.nova-lite-v1:0","streaming":true}


                id: chunk-1

                event: content

                data: {"delta":"Hello","complete":false}


                id: chunk-2

                event: content

                data: {"delta":" there!","complete":false}


                id: chunk-3

                event: done

                data: {"complete":true,"usage":{"inputTokens":8,"outputTokens":15,"totalTokens":23}}'
              schema:
                description: 'Server-Sent Events stream with chunks of generated text. Format: id, event, data lines separated by newlines.'
                type: string
          description: Streaming response (text/event-stream, sync mode)
        '202':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/chatInference_202_response'
          description: 'Async execution started (when `async: true` in request)'
        '500':
          description: Failed to perform streaming inference
      summary: Chat inference via streaming endpoint (true HTTP streaming) with multimodal support
      tags:
      - AI Inference
  /api/v3/organizations/{organisation}/ai/embeddings:
    post:
      description: "Generates vector embeddings for text content using embedding models. Used for semantic search, document similarity, and RAG applications.\n     *\n     * **Features:**\n     * - Single text or batch processing (up to 100 texts)\n     * - Configurable dimensions (256, 512, 1024, 8192 for Titan v2)\n     * - Optional normalization to unit length\n     * - Usage tracking for billing\n     *\n     * **Use Cases:**\n     * - Semantic search across documents\n     * - Similarity matching for content recommendations\n     * - RAG (Retrieval-Augmented Generation) pipelines\n     * - Clustering and classification\n     *\n     * **Available Embedding Models:**\n     * - amazon.titan-embed-text-v2:0 (default, supports 256-8192 dimensions)\n     * - amazon.titan-embed-text-v1:0 (1536 dimensions fixed)"
      operationId: embeddings
      parameters:
      - description: The organisation ID
        explode: false
        in: path
        name: organisation
        required: true
        schema:
          type: string
        style: simple
      requestBody:
        content:
          application/json:
            example:
              input: The Australian government announced new climate policy
              modelId: amazon.titan-embed-text-v2:0
              dimensions: 1024
              normalize: true
            schema:
              $ref: '#/components/schemas/embeddings_request'
        description: Embedding request with single or multiple texts
        required: true
      responses:
        '200':
          content:
            application/json:
              example:
                embeddings:
                - 0.0215
                - 0.0008
                - 0.0312
                - -0.0087
                - 0.0273
                model: amazon.titan-embed-text-v2:0
                dimension: 1024
                usage:
                  inputTokens: 8
                  totalTokens: 8
              schema:
                $ref: '#/components/schemas/embeddings_200_response'
          description: Embeddings generated successfully
        '400':
          description: Invalid request parameters
        '403':
          description: Access denied
        '500':
          description: Failed to generate embeddings
      summary: Generate text embeddings for semantic search and RAG applications
      tags:
      - AI Inference
  /api/v3/organizations/{organisation}/ai/image-generation:
    post:
      description: "Generates images using Amazon Nova Canvas image generation model.\n     *\n     * **Region Restriction:** Nova Canvas is ONLY available in:\n     * - `us-east-1` (US East, N. Virginia)\n     * - `ap-northeast-1` (Asia Pacific, Tokyo)\n     * - `eu-west-1` (Europe, Ireland)\n     * ❌ NOT available in `ap-southeast-2` (Sydney)\n     *\n     * **Supported Task Types:**\n     * - **TEXT_IMAGE**: Basic text-to-image generation\n     * - **TEXT_IMAGE with Conditioning**: Layout-guided generation using edge detection or segmentation\n     * - **COLOR_GUIDED_GENERATION**: Generate images with specific color palettes\n     * - **IMAGE_VARIATION**: Create variations of existing images\n     * - **INPAINTING**: Fill masked areas in images\n     * - **OUTPAINTING**: Extend images beyond their borders\n     * - **BACKGROUND_REMOVAL**: Remove backgrounds from images\n     * - **VIRTUAL_TRY_ON**: Try on garments/objects on people\n     *\n     * **Quality Options:**\n     * - **standard**: Faster generation, lower cost\n     * - **premium**: Higher quality, slower generation\n     *\n     * **Timeout:** Image generation can take up to 5 minutes"
      operationId: imageGeneration
      parameters:
      - description: The organisation ID
        explode: false
        in: path
        name: organisation
        required: true
        schema:
          type: string
        style: simple
      requestBody:
        content:
          application/json:
            example:
              taskType: TEXT_IMAGE
              textToImageParams:
                text: A serene mountain landscape at sunset with snow-capped peaks
                negativeText: blurry, low quality, distorted
                style: PHOTOREALISM
              imageGenerationConfig:
                width: 1024
                height: 1024
                quality: premium
                numberOfImages: 1
                cfgScale: 7
              region: us-east-1
            schema:
              $ref: '#/components/schemas/imageGeneration_request'
        description: Image generation request
        required: true
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/imageGeneration_200_response'
          description: Image(s) generated successfully
        '400':
          description: Invalid request parameters
        '403':
          description: Access denied
        '500':
          description: Failed to generate images
      summary: Generate images with Amazon Nova Canvas
      tags:
      - AI Inference
  /api/v3/organizations/{organisation}/ai/chat/executions/{identifier}:
    get:
      description: "Poll the status of an async/durable chat execution.\n     *\n     * **When to use:** After starting chat inference with `async: true`, poll this endpoint\n     * to check execution status and retrieve results when complete.\n     *\n     * **Identifier:** Accepts either:\n     * - `requestId` (recommended): The short ID returned from the async request\n     * - `executionArn`: The full AWS Lambda durable execution ARN (must be URL-encoded)\n     *\n     * **Statuses:**\n     * - `pending`: Execution is starting (retry shortly)\n     * - `running`: Execution is in progress\n     * - `waiting_callback`: Execution paused, waiting for client tool results\n     * - `complete`: Execution finished successfully\n     * - `failed`: Execution failed with error\n     *\n     * **Client Tool Callback:**\n     * When status is `waiting_callback`, submit tool results via `POST /ai/chat/callback`.\n     *\n     * **Polling Recommendations:**\n     * - Start with 1 second delay, exponential backoff up to 30 seconds\n     * - Stop polling after 15 minutes (consider failed)"
      operationId: getDurableExecutionStatus
      parameters:
      - description: The organisation ID
        explode: false
        in: path
        name: organisation
        required: true
        schema:
          type: string
        style: simple
      - description: Either the requestId from async response, or full executionArn (URL-encoded)
        example: XkdVWiEfSwMEPrw=
        explode: false
        in: path
        name: identifier
        required: true
        schema:
          type: string
        style: simple
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/getDurableExecutionStatus_200_response'
          description: Execution status retrieved
        '404':
          description: Execution not found
        '403':
          description: Access denied
        '500':
          description: Failed to retrieve execution status
      summary: Get Durable Execution Status
      tags:
      - AI Inference
  /api/v3/organizations/{organisation}/ai/chat/callback:
    post:
      description: "Submit tool execution results to resume a suspended durable execution.\n     *\n     * **When to use:** When polling the execution status returns `waiting_callback`, use this endpoint\n     * to submit the results of client-executed tools. The execution will then resume.\n     *\n     * **Flow:**\n     * 1. Start async chat with client-executed tools (`autoExecute: []` or tools not in autoExecute list)\n     * 2. Poll status until `waiting_callback`\n     * 3. Execute tools locally using `pendingTools` from status response\n     * 4. Submit results here with the `callbackId`\n     * 5. Poll status until `complete`\n     *\n     * **Important:** Each `callbackId` can only be used once. After submission, poll the execution\n     * status to see the updated state."
      operationId: submitToolCallback
      parameters:
      - description: The organisation ID
        explode: false
        in: path
        name: organisation
        required: true
        schema:
          type: string
        style: simple
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/submitToolCallback_request'
        required: true
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/submitToolCallback_200_response'
          description: Callback submitted successfully, execution will resume
        '400':
          description: Invalid request (missing callbackId or toolResults)
        '404':
          description: Callback not found or already processed
        '403':
          description: Access denied
        '500':
          description: Failed to submit callback
      summary: Submit Client Tool Results (Callback)
      tags:
      - AI Inference
components:
  schemas:
    chatInference_request_toolConfig:
      description: Function calling configuration (Claude 3+, Nova Pro)
      properties:
        tools:
          items:
            $ref: '#/components/schemas/chatInference_request_toolConfig_tools_inner'
          type: array
        autoExecute:
          default: false
          description: 'When true, backend automatically executes tools and feeds results back to AI. For async tools (e.g., image generation), returns executionId for polling. Security: Use allowedTools to whitelist which tools can auto-execute.'
          type: boolean
        allowedTools:
          description: 'Whitelist of tool names that can be auto-executed. Required when autoExecute is true for security. Example: [''get_weather'', ''generate_image'']'
          items:
            type: string
          type: array
      type: object
    imageGeneration_request_colorGuidedGenerationParams:
      description: Parameters for COLOR_GUIDED_GENERATION task
      properties:
        colors:
          items:
            pattern: ^#[0-9A-Fa-f]{6}$
            type: string
          maxItems: 10
          minItems: 1
          type: array
        referenceImage:
          format: byte
          type: string
        text:
          maxLength: 1024
          minLength: 1
          type: string
        negativeText:
          maxLength: 1024
          minLength: 1
          type: string
      type: object
    chatInference_200_response:
      example:
        response:
          role: assistant
          toolUse:
            result:
              s3Urls:
              - s3Urls
              - s3Urls
              images:
              - images
              - images
            input:
              location: Sydney
            executionId: exec_abc123def456
            name: get_weather
            toolUseId: abc123
            status: pending
          content: I'll help you with that.
        requestId: req-abc123
        usage:
          costCents: 0.42
          inputTokens: 25
          outputTokens: 150
          totalTokens: 175
        finishReason: stop
        model: amazon.nova-pro-v1:0
      properties:
        response:
          $ref: '#/components/schemas/chatInference_200_response_response'
        model:
          description: Model used for generation
          example: amazon.nova-pro-v1:0
          type: string
        requestId:
          description: Unique request identifier
          example: req-abc123
          type: string
        finishReason:
          description: Why the model stopped generating
          enum:
          - stop
          - length
          - content_filter
          - tool_use
          type: string
        usage:
          $ref: '#/components/schemas/chatInference_200_response_usage'
      type: object
    getDurableExecutionStatus_200_response_error:
      description: Present when status is failed
      example:
        ErrorType: ErrorType
        ErrorMessage: ErrorMessage
      properties:
        ErrorMessage:
          type: string
        ErrorType:
          type: string
      type: object
    embeddings_200_response_embeddings:
      description: Vector embeddings for the input text(s). Single array for string input, array of arrays for batch input.
      oneOf:
      - description: Single embedding vector if input was a string
        items:
          format: float
          type: number
        type: array
      - description: Array of embedding vectors if input was an array
        items:
          items:
            format: float
            type: number
          type: array
        type: array
    imageGeneration_200_response:
      example:
        images:
        - images
        - images
        error: error
        maskImage: maskImage
      properties:
        images:
          description: Array of base64-encoded generated images
          items:
            format: byte
            type: string
          type: array
        maskImage:
          description: Base64-encoded mask image (for virtual try-on)
          format: byte
          type: string
        error:
          description: Error message if any images were blocked by content moderation
          type: string
      required:
      - images
      type: object
    imageGeneration_request_imageVariationParams:
      description: Parameters for IMAGE_VARIATION task
      properties:
        images:
          items:
            format: byte
            type: string
          maxItems: 5
          minItems: 1
          type: array
        similarityStrength:
          format: float
          maximum: 1
          minimum: 0.2
          type: number
        text:
          maxLength: 1024
          minLength: 1
          type: string
        negativeText:
          maxLength: 1024
          minLength: 1
          type: string
      type: object
    chatInferenceStream_request_messages_inner_content:
      example: What is the capital of Australia?
      oneOf:
      - description: Simple text message
        type: string
      - description: Multimodal content blocks
        items:
          description: Text, image, video, or document block
          type: object
        type: array
    chatInference_request_messages_inner:
      properties:
        role:
          enum:
          - user
          - assistant
          - system
          type: string
        content:
          $ref: '#/components/schemas/chatInference_request_messages_inner_content'
      required:
      - content
      - role
      type: object
    chatInference_request_messages_inner_content_oneOf_inner:
      oneOf:
      - $ref: '#/components/schemas/chatInference_request_messages_inner_content_oneOf_inner_oneOf'
      - $ref: '#/components/schemas/chatInference_request_messages_inner_content_oneOf_inner_oneOf_1'
      - $ref: '#/components/schemas/chatInference_request_messages_inner_content_oneOf_inner_oneOf_2'
      - $ref: '#/components/schemas/chatInference_request_messages_inner_content_oneOf_inner_oneOf_3'
    chatInference_request_messages_inner_content_oneOf_inner_oneOf_2_video:
      properties:
        format:
          enum:
          - mp4
          - mov
          - mkv
          - webm
          type: string
        source:
          $ref: '#/components/schemas/chatInference_request_messages_inner_content_oneOf_inner_oneOf_2_video_source'
      required:
      - format
      - source
      type: object
    chatInference_request_messages_inner_content_oneOf_inner_oneOf_3_document_source:
      properties:
        bytes:
          description: Base64-encoded document data
          format: byte
          type: string
      required:
      - bytes
      type: object
    chatInference_request_toolConfig_tools_inner_toolSpec:
      properties:
        name:
          type: string
        description:
          type: string
        inputSchema:
          $ref: '#/components/schemas/chatInference_request_toolConfig_tools_inner_toolSpec_inputSchema'
      type: object
    chatInference_request_messages_inner_content_oneOf_inner_oneOf_2_video_source:
      properties:
        bytes:
          description: Base64-encoded video data
          format: byte
          type: string
      required:
      - bytes
      type: object
    getDurableExecutionStatus_200_response_result:
      description: Present when status is complete
      example:
        response:
          role: assistant
          content: The weather in Sydney is sunny.
        usage:
          costCents: 5.962134
          inputTokens: 0
          outputTokens: 6
          totalTokens: 1
        toolExecutions:
        - '{}'
        - '{}'
      properties:
        response:
          $ref: '#/components/schemas/getDurableExecutionStatus_200_response_result_response'
        usage:
          $ref: '#/components/schemas/getDurableExecutionStatus_200_response_result_usage'
        toolExecutions:
          items:
            type: object
          type: array
      type: object
    imageGeneration_request_textToImageParams:
      description: Parameters for TEXT_IMAGE task
      properties:
        text:
          description: Text prompt
          maxLength: 1024
          minLength: 1
          type: string
        negativeText:
          description: What NOT to include
          maxLength: 1024
          minLength: 1
          type: string
        style:
          enum:
          - 3D_ANIMATED_FAMILY_FILM
          - DESIGN_SKETCH
          - FLAT_VECTOR_ILLUSTRATION
          - GRAPHIC_NOVEL_ILLUSTRATION
          - MAXIMALISM
          - MIDCENTURY_RETRO
          - PHOTOREALISM
          - SOFT_DIGITAL_PAINTING
          type: string
        conditionImage:
          description: Base64-encoded conditioning image
          format: byte
          type: string
        controlMode:
          default: CANNY_EDGE
          enum:
          - CANNY_EDGE
          - SEGMENTATION
          type: string
        controlStrength:
          default: 0.7
          format: float
          maximum: 1
          minimum: 0
          type: number
      type: object
    imageGeneration_request:
      properties:
        modelId:
          default: amazon.nova-canvas-v1:0
          description: Model to use for image generation
          type: string
        taskType:
          description: Type of image generation task
          enum:
          - TEXT_IMAGE
          - COLOR_GUIDED_GENERATION
          - IMAGE_VARIATION
          - INPAINTING
          - OUTPAINTING
          - BACKGROUND_REMOVAL
          - VIRTUAL_TRY_ON
          type: string
        textToImageParams:
          $ref: '#/components/schemas/imageGeneration_request_textToImageParams'
        colorGuidedGenerationParams:
          $ref: '#/components/schemas/imageGeneration_request_colorGuidedGenerationParams'
        imageVariationParams:
          $ref: '#/components/schemas/imageGeneration_request_imageVariationParams'
        inPaintingParams:
          $ref: '#/components/schemas/imageGeneration_request_inPaintingParams'
        outPaintingParams:
          $ref: '#/components/schemas/imageGeneration_request_outPaintingParams'
        backgroundRemovalParams:
          $ref: '#/components/schemas/imageGeneration_request_backgroundRemovalParams'
        virtualTryOnParams:
          description: Parameters for VIRTUAL_TRY_ON task
          type: object
        imageGenerationConfig:
          $ref: '#/components/schemas/imageGeneration_request_imageGenerationConfig'
        region:
          default: us-east-1
          description: AWS region for Nova Canvas
          enum:
          - us-east-1
          - ap-northeast-1
          - eu-west-1
          type: string
      required:
      - taskType
      type: object
    chatInference_request_messages_inner_content_oneOf_inner_oneOf_1_image:
      properties:
        format:
          enum:
          - png
          - jpeg
          - gif
          - webp
          type: string
        source:
          $ref: '#/components/schemas/chatInference_request_messages_inner_content_oneOf_inner_oneOf_1_image_source'
      required:
      - format
      - source
      type: object
    getDurableExecutionStatus_200_response_result_usage:
      description: Token usage and cost for the final synthesis turn
      example:
        costCents: 5.962134
        inputTokens: 0
        outputTokens: 6
        totalTokens: 1
      properties:
        inputTokens:
          type: integer
        outputTokens:
          type: integer
        totalTokens:
          type: integer
        costCents:
          description: Cost of the final synthesis turn in US cents
          format: float
          type: number
      type: object
    getDurableExecutionStatus_200_response:
      example:
        result:
          response:
            role: assistant
            content: The weather in Sydney is sunny.
          usage:
            costCents: 5.962134
            inputTokens: 0
            outputTokens: 6
            totalTokens: 1
          toolExecutions:
          - '{}'
          - '{}'
        callbackId: Ab9hZXi/YXJuOmF3czpsYW1iZGE...
        requestId: XkdVWiEfSwMEPrw=
        executionArn: arn:aws:lambda:ap-southeast-2:...
        awsStatus: SUCCEEDED
        pendingTools:
        - input:
            location: Sydney
          name: get_weather
          toolUseId: toolu_bdrk_012KTC8NCG...
        - input:
            location: Sydney
          name: get_weather
          toolUseId: toolu_bdrk_012KTC8NCG...
        error:
          ErrorType: ErrorType
          ErrorMessage: ErrorMessage
        status: complete
      properties:
        requestId:
          example: XkdVWiEfSwMEPrw=
          type: string
        executionArn:
          example: arn:aws:lambda:ap-southeast-2:...
          type: string
        status:
          enum:
          - pending
          - running
          - waiting_callback
          - complete
          - failed
          example: complete
          type: string
        awsStatus:
          description: Raw AWS Step Functions status
          example: SUCCEEDED
          type: string
        callbackId:
          description: Present when status is waiting_callback - use with /chat/callback
          example: Ab9hZXi/YXJuOmF3czpsYW1iZGE...
          type: string
        pendingTools:
          description: Present when status is waiting_callback - tools waiting for results
          items:
            $ref: '#/components/schemas/getDurableExecutionStatus_200_response_pendingTools_inner'
          type: array
        result:
          $ref: '#/components/schemas/getDurableExecutionStatus_200_response_result'
        error:
          $ref: '#/components/schemas/getDurableExecutionStatus_200_response_error'
      type: object
    chatInference_request_messages_inner_content:
      example: What is the capital of Australia?
      oneOf:
      - description: Simple text message
        type: string
      - description: Multimodal content blocks (text, image, video, document)
        items:
          $ref: '#/components/schemas/chatInference_request_messages_inner_content_oneOf_inner'
        type: array
    chatInference_request_messages_inner_content_oneOf_inner_oneOf_3:
      properties:
        document:
          $ref: '#/components/schemas/chatInference_request_messages_inner_content_oneOf_inner_oneOf_3_document'
      required:
      - document
      type: object
    chatInference_request_messages_inner_content_oneOf_inner_oneOf:
      properties:
        text:
          example: What's in this image?
          type: string
      required:
      - text
      type: object
    chatInferenceStream_request:
      properties:
        messages:
          description: Array of chat messages. Content can be a simple string or an array of content blocks for multimodal input.
          items:
            $ref: '#/components/schemas/chatInferenceStream_request_messages_inner'
          minItems: 1
          type: array
        modelId:
          description: Model ID. Use Nova models for multimodal support.
          example: amazon.nova-lite-v1:0
          type: string
        temperature:
          default: 0.7
          maximum: 2
          minimum: 0
          type: number
        maxTokens:
          default: 4096
          description: Max tokens. Claude 4.5 supports up to 64k.
          maximum: 65536
          minimum: 1
          type: integer
        topP:
          maximum: 1
          minimum: 0
          type: number
        systemPrompt:
          description: Optional custom system prom

# --- truncated at 32 KB (50 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/quantcdn/refs/heads/main/openapi/quantcdn-ai-inference-api-openapi.yml