> ## Documentation Index > Fetch the complete documentation index at: https://docs.octen.ai/llms.txt > Use this file to discover all available pages before exploring further. # VL Embedding > 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. ## OpenAPI ````yaml /api-reference/openapi.json post /vl-embedding openapi: 3.1.0 info: title: Octen API description: >- Octen API provides Search, Extract, Embeddings, VL Embeddings, Web Chat, Broad Search, and Deep Research services. The Search API searches ranked web results with optional filters, highlights, and full content. The Extract API extracts clean markdown content from URLs, with optional query-focused highlights, page classification, and multimedia resources. The Embeddings API converts text into vector representations. The VL Embeddings API converts multimodal inputs (text, images, videos) into vector representations. The Web Chat API provides LLM chat completions with search augmentation. The Broad Search API automatically decomposes queries into multiple sub-queries for comprehensive search and synthesis. The Deep Research API runs a multi-round adaptive research pipeline that produces a structured research plan, executes iterative web searches, builds a report brief with evidence, and streams a final long-form report. version: 1.0.0 servers: - url: https://api.octen.ai security: - apiKeyAuth: [] 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 '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' components: schemas: 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 description: >- Controls the frame sampling density for video inputs. Smaller values reduce the number of extracted frames and lower video token consumption. 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 32,000-token total context limit with `contents`. VLEmbeddingResponse: type: object properties: code: type: integer description: Business status code. 0 indicates success. msg: type: string description: A human-readable 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' ErrorResponse: type: object properties: code: type: integer description: Business status code. Non-zero values indicate an error. msg: type: string description: A human-readable message describing the error. required: - code - msg 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. 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 32,000 tokens 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. 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. 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. responses: 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 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 PayloadTooLarge: description: >- Payload too large — Returned when the request payload exceeds the size limit (e.g. image > 5MB, video > 50MB, or request body > 2MB). content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: code: 413 msg: Payload too large UnsupportedMediaType: description: >- Unsupported media type — Returned when the input media format is not supported (e.g. an image or video format outside the supported list). content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: code: 415 msg: Unsupported media type 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 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 securitySchemes: apiKeyAuth: type: apiKey in: header name: x-api-key description: >- API key used for request authentication. Obtain an API key before using the API. Note: A payment method is required to use the API. ````