Octen Vl Embedding API

openapi: 3.2.0
info:
  title: Octen Ai Vl Embedding API
  version: 1.0.0
  description: 'Operations tagged Vl Embedding across 2 of this provider''s published API definitions: octen-ai-openapi.json, octen-ai-openapi.yml. Each path carries the servers of the definition it was published in.'
servers:
- url: https://api.octen.ai
security:
- bearerAuth: []
- apiKeyAuth: []
tags:
- name: Vl Embedding
paths:
  /vl-embedding:
    post:
      summary: VL Embedding
      description: Converts multimodal input (text, images, and videos) into vector representations. Supports a single fused vector across modalities, independent per-element vectors, configurable output dimensions, video frame sampling control, and a custom task instruction.
      operationId: vl-embedding
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/VLEmbeddingRequest'
            examples:
              textOnly:
                summary: Text Only
                value:
                  model: octen-vl-embedding
                  input:
                    contents:
                    - text: What is multimodal vector search?
              multimodalFusion:
                summary: Multimodal Fusion (text + images + video)
                value:
                  model: octen-vl-embedding-large
                  input:
                    contents:
                    - text: Outdoor tent, 3-4 person, waterproof and windproof
                    - image: https://example.com/tent_setup.jpg
                    - image: https://example.com/tent_inside.jpg
                    - video: https://example.com/tent_demo.mp4
                  enable_fusion: true
                  dimension: 2048
                  fps: 0.3
                  instruct: Represent the outdoor product for retrieval
              independentImages:
                summary: Independent Image Embeddings
                value:
                  model: octen-vl-embedding
                  input:
                    contents:
                    - image: https://example.com/product_1.jpg
                    - image: https://example.com/product_2.jpg
                  enable_fusion: false
      responses:
        '200':
          description: Successful VL embedding response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/VLEmbeddingResponse'
              examples:
                fusion:
                  summary: Fusion mode response (single fused vector)
                  value:
                    code: 0
                    msg: success
                    request_id: a7b8c9d0-e1f2-3456-abcd-789012345678
                    data:
                      results:
                      - index: 0
                        embedding:
                        - 0.0156
                        - -0.0298
                        - 0.0411
                        type: fusion
                      model: octen-vl-embedding-large
                    meta:
                      usage:
                        input_tokens: 6814
                        text_tokens: 18
                        image_tokens: 6796
                        image_count: 2
                        duration: 22
                      warning: null
                independent:
                  summary: Independent mode response (one vector per element)
                  value:
                    code: 0
                    msg: success
                    request_id: a7b8c9d0-e1f2-3456-abcd-789012345678
                    data:
                      results:
                      - index: 0
                        embedding:
                        - 0.0234
                        - -0.0167
                        - 0.0389
                        type: vl
                      - index: 1
                        embedding:
                        - -0.0312
                        - 0.0445
                        - 0.0178
                        type: vl
                      - index: 2
                        embedding:
                        - 0.0198
                        - -0.0267
                        - 0.0356
                        type: vl
                      - index: 3
                        embedding:
                        - -0.0089
                        - 0.0334
                        - -0.0223
                        type: vl
                      model: octen-vl-embedding-large
                    meta:
                      usage:
                        input_tokens: 6814
                        text_tokens: 18
                        image_tokens: 6796
                        image_count: 2
                        duration: 22
                      warning: null
        '400':
          description: Missing or invalid parameter — Returned when a required parameter is missing or has an invalid value.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
              example:
                code: 400
                msg: Missing or invalid parameter
                request_id: req_abc123def456
        '401':
          $ref: '#/components/responses/Unauthorized'
        '403':
          $ref: '#/components/responses/InsufficientBalance'
        '413':
          $ref: '#/components/responses/PayloadTooLarge'
        '415':
          $ref: '#/components/responses/UnsupportedMediaType'
        '429':
          $ref: '#/components/responses/RateLimited'
        '500':
          $ref: '#/components/responses/InternalError'
      tags:
      - Vl Embedding
    servers:
    - url: https://api.octen.ai
components:
  schemas:
    VLEmbeddingUsage:
      type: object
      description: Usage information for the VL embedding request.
      properties:
        input_tokens:
          type: integer
          description: Total number of input tokens processed in this request.
        text_tokens:
          type: integer
          description: Number of tokens consumed by text inputs.
        image_tokens:
          type: integer
          description: Total tokens consumed by image and video inputs (videos are sampled into frames before counting).
        image_count:
          type: integer
          description: Number of images in the request (excluding frames extracted from videos).
        duration:
          type: integer
          description: Total duration of video inputs in seconds.
    VLEmbeddingResponse:
      type: object
      properties:
        code:
          type: integer
          description: Business status code. 0 indicates success.
        msg:
          type: string
          description: A message describing the result.
        request_id:
          type: string
          description: The unique identifier for this request.
        data:
          $ref: '#/components/schemas/VLEmbeddingData'
        meta:
          $ref: '#/components/schemas/VLEmbeddingMeta'
    VLEmbeddingResult:
      type: object
      description: A single VL embedding result.
      properties:
        index:
          type: integer
          description: The position of the embedding in the input array.
        embedding:
          type: array
          items:
            type: number
          description: The generated embedding vector. Type and encoding may vary based on the input parameters.
        type:
          type: string
          enum:
          - vl
          - fusion
          description: The result type.
    VLEmbeddingRequest:
      type: object
      required:
      - model
      - input
      properties:
        model:
          type: string
          enum:
          - octen-vl-embedding
          - octen-vl-embedding-large
          description: The multimodal embedding model used for this request.
        input:
          $ref: '#/components/schemas/VLEmbeddingInput'
        enable_fusion:
          type: boolean
          default: false
          description: Whether to generate a fused embedding. When `true`, all elements in `contents` are fused into a single vector; when `false`, each element produces an independent vector.
        dimension:
          type: integer
          description: 'The dimensionality of the output embedding vectors. Defaults to the model''s max dimension (octen-vl-embedding: 2048, octen-vl-embedding-large: 4096). Any positive integer ≤ the model''s max dimension is allowed.'
        fps:
          type: number
          minimum: 0
          maximum: 1
          default: 1.0
          description: Frames sampled per second of video. For example, `0.5` samples one frame every two seconds. Lower values sample fewer frames and reduce video token consumption. Each video is sampled to at most 64 frames.
        instruct:
          type: string
          default: Represent the user's input.
          description: Custom task description used to guide the model in understanding the query intent. Its length counts toward `input_tokens` and shares the 10,000-character total limit with `contents`.
    VLEmbeddingInput:
      type: object
      required:
      - contents
      description: 'The multimodal content to be vectorized. Supports text, images, videos, and combinations. Maximum total elements per request: 20. Maximum images per request: 5. Maximum videos per request: 1.'
      properties:
        contents:
          type: array
          maxItems: 20
          description: The list of content elements to process.
          items:
            $ref: '#/components/schemas/VLEmbeddingContent'
    VLEmbeddingData:
      type: object
      description: The main VL embedding response payload.
      properties:
        results:
          type: array
          description: A list of embedding results.
          items:
            $ref: '#/components/schemas/VLEmbeddingResult'
        model:
          type: string
          description: The embedding model used for this request.
    VLEmbeddingMeta:
      type: object
      description: Additional metadata for the VL embedding request.
      properties:
        usage:
          $ref: '#/components/schemas/VLEmbeddingUsage'
        warning:
          type: string
          nullable: true
          description: Optional warning message, if any.
    ErrorResponse:
      type: object
      properties:
        code:
          type: integer
          description: Business status code. Non-zero values indicate an error.
        msg:
          type: string
          description: A message describing the error.
        request_id:
          type: string
          description: Unique identifier for the request.
      required:
      - code
      - msg
      - request_id
    VLEmbeddingContent:
      type: object
      description: A single content element. Each object should provide exactly one of `text`, `image`, or `video`. For multiple images, include multiple content objects (one image per object).
      properties:
        text:
          type: string
          description: Text input. Maximum 10,000 characters per entry.
        image:
          type: string
          description: 'Image input. Supports a URL or a Base64 string. Maximum 5MB per image. Supported formats: JPEG, PNG, WEBP, BMP, TIFF, ICO, DIB, ICNS, SGI.'
        video:
          type: string
          description: 'Video input. URL only. Maximum 50MB per file. Supported formats: MP4, AVI, MOV.'
  responses:
    RateLimited:
      description: Exceeding the rate limit — Returned when the request exceeds the configured rate limit.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
          example:
            code: 429
            msg: Exceeding the rate limit
            request_id: req_abc123def456
    UnsupportedMediaType:
      description: Unsupported media type — Returned when the input media format is not supported.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
          example:
            code: 415
            msg: Unsupported media type
            request_id: req_abc123def456
    PayloadTooLarge:
      description: Payload too large — Returned when the request payload exceeds the size limit.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
          example:
            code: 413
            msg: Payload too large
            request_id: req_abc123def456
    Unauthorized:
      description: Invalid API Key — Returned when the API key is missing or invalid.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
          example:
            code: 401
            msg: Invalid API Key
            request_id: req_abc123def456
    InternalError:
      description: Internal error — Returned when an unexpected server-side error occurs.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
          example:
            code: 500
            msg: Internal error
            request_id: req_abc123def456
    InsufficientBalance:
      description: Insufficient balance in account — Returned when the account balance is insufficient to complete the request.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
          example:
            code: 403
            msg: Insufficient balance in account
            request_id: req_abc123def456
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: 'Bearer token used for request authentication. Alternatively, you can send the API key in the `x-api-key` header. Note: A payment method is required to use the API.'
    apiKeyAuth:
      type: apiKey
      in: header
      name: x-api-key
      description: 'API key used for request authentication. Alternatively, you can send the key as a Bearer token in the `Authorization` header. Note: A payment method is required to use the API.'
    bearerAuthNoPayment:
      type: http
      scheme: bearer
      description: Bearer token used for request authentication. Alternatively, you can send the API key in the `x-api-key` header.
    apiKeyAuthNoPayment:
      type: apiKey
      in: header
      name: x-api-key
      description: API key used for request authentication. Alternatively, you can send the key as a Bearer token in the `Authorization` header.
x-refined-from:
- octen-ai-openapi.json
- octen-ai-openapi.yml