> ## Documentation Index > Fetch the complete documentation index at: https://docs.orq.ai/llms.txt > Use this file to discover all available pages before exploring further. # Create embeddings > Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms. ## OpenAPI ````yaml post /v2/router/embeddings openapi: 3.1.0 info: title: orq.ai API version: '2.0' description: orq.ai API documentation servers: - url: https://api.orq.ai security: - ApiKey: [] tags: - description: List models available through the AI Router. name: Models - name: Guardrail Rules - name: Policies - name: Routing Rules - name: API keys description: >- API keys authenticate programmatic access to the workspace. The unified key model exposes opaque tokens, per-domain access grants, and budget / rate-limit constraints (see ADR 0001 and ADR 0002). - name: Budgets description: >- Budgets govern spend, token usage, and request rate across six scopes: workspace, project, identity, api-key, provider, and model. A budget is hierarchical and defense-in-depth — every applicable budget is a hard gate, and the most restrictive one wins per dimension (see ADR 0007). - name: Documentation description: >- Search the orq.ai documentation. Proxies the workspace's query to the hosted docs search index. - name: Files description: File upload and retrieval operations. - name: Identities description: >- Identities represent end users from your system for usage and engagement tracking. - name: Projects description: Projects organize resources within a workspace - name: Skills description: >- Skills are modular instructions you can use to codify processes and conventions - name: Responses - description: >- Run agents on a cadence — cron, interval, or one-off. Minimum firing interval is 1 hour. name: Agent Schedules - name: Embeddings - name: Reporting description: >- GenAI reporting API over canonical analytics rollups. Accepts a metric name, time range, grain, group-by, and filters; returns a typed time series and optional totals. externalDocs: url: https://docs.orq.ai description: orq.ai Documentation paths: /v2/router/embeddings: post: tags: - Embeddings summary: Create embeddings description: >- Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms. operationId: createEmbedding requestBody: content: application/json: examples: array_of_strings: summary: Array of strings input value: input: - The food was delicious - And the waiter was friendly model: openai/text-embedding-3-small single_string: summary: Single string input value: input: The food was delicious and the waiter... model: openai/text-embedding-3-small schema: additionalProperties: false properties: cache: $ref: '#/components/schemas/EmbeddingCacheConfig' description: Cache configuration for the request. dimensions: description: >- The number of dimensions the resulting output embeddings should have. format: int64 type: integer encoding_format: description: >- The format to return the embeddings in. Can be either float or base64. enum: - float - base64 type: string fallbacks: description: Array of fallback models to use if primary model fails. items: $ref: '#/components/schemas/FallbackConfig' type: - array - 'null' input: anyOf: - description: A single text string to embed. Must be non-empty. minLength: 1 title: String type: string - description: >- An array of strings or token arrays to embed. Must be non-empty. items: anyOf: - type: string minLength: 1 - items: type: integer minItems: 1 type: array minItems: 1 title: Array type: array description: Input text to embed, encoded as a string or array of tokens. load_balancer: $ref: '#/components/schemas/EmbeddingLoadBalancerConfig' description: Load balancer configuration for the request. model: description: ID of the model to use. type: string name: description: >- The name to display on the trace. If not specified, the default system name will be used. type: string orq: $ref: '#/components/schemas/EmbeddingOrqParams' description: >- Orq platform extension parameters. Top-level equivalents take priority when both are set. retry: $ref: '#/components/schemas/EmbeddingRetryConfig' description: Retry configuration for the request. timeout: $ref: '#/components/schemas/EmbeddingTimeoutConfig' description: Timeout configuration to apply to the request. user: description: A unique identifier representing your end-user. type: string required: - model - input type: object required: true responses: '200': content: application/json: schema: additionalProperties: false properties: data: description: List of embedding objects. items: $ref: '#/components/schemas/PublicEmbeddingData' minItems: 0 type: - array - 'null' model: description: ID of the model used. type: string object: description: Always "list". enum: - list type: string usage: $ref: '#/components/schemas/PublicEmbeddingUsage' description: The usage information for the request. required: - object - data - model - usage type: object description: Returns the embedding vector. components: schemas: EmbeddingCacheConfig: additionalProperties: false properties: ttl: description: >- Time to live for cached responses in seconds. Maximum 259200 seconds (3 days). format: int64 type: integer type: description: Cache type. enum: - exact_match type: string required: - type type: object FallbackConfig: additionalProperties: false properties: model: type: string required: - model type: object EmbeddingLoadBalancerConfig: additionalProperties: false properties: models: description: Array of models with weights for load balancing requests. items: $ref: '#/components/schemas/EmbeddingLoadBalancerModelConfig' type: - array - 'null' type: description: Load balancer type. enum: - weight_based type: string required: - type - models type: object EmbeddingOrqParams: additionalProperties: false properties: cache: $ref: '#/components/schemas/EmbeddingCacheConfig' description: 'Deprecated: use top-level cache instead.' contact: $ref: '#/components/schemas/EmbeddingContactParams' description: >- Deprecated: use identity instead. Information about the contact making the request. fallbacks: description: 'Deprecated: use top-level fallbacks instead.' items: $ref: '#/components/schemas/FallbackConfig' type: - array - 'null' identity: $ref: '#/components/schemas/PublicIdentity' description: Information about the identity making the request. load_balancer: $ref: '#/components/schemas/EmbeddingLoadBalancerConfig' description: 'Deprecated: use top-level load_balancer instead.' name: description: 'Deprecated: use top-level name instead.' type: string retry: $ref: '#/components/schemas/EmbeddingRetryConfig' description: 'Deprecated: use top-level retry instead.' timeout: $ref: '#/components/schemas/EmbeddingTimeoutConfig' description: 'Deprecated: use top-level timeout instead.' type: object EmbeddingRetryConfig: additionalProperties: false properties: count: description: Number of retry attempts (1-5). format: int64 type: integer on_codes: description: HTTP status codes that trigger retry logic. items: format: int64 type: integer type: - array - 'null' required: - count - on_codes type: object EmbeddingTimeoutConfig: additionalProperties: false properties: call_timeout: description: Timeout value in milliseconds. format: int64 type: integer required: - call_timeout type: object PublicEmbeddingData: additionalProperties: false properties: embedding: description: >- The embedding vector, which is a list of floats. The length of vector depends on the model. Can also be a base64-encoded string when encoding_format is base64. index: description: The index of the embedding in the list of embeddings. format: int64 type: integer object: description: The object type, which is always "embedding". enum: - embedding type: string required: - object - index - embedding type: object PublicEmbeddingUsage: additionalProperties: false properties: prompt_tokens: description: The number of tokens used by the prompt. format: int64 type: integer total_tokens: description: The total number of tokens used by the request. format: int64 type: integer required: - prompt_tokens - total_tokens type: object EmbeddingLoadBalancerModelConfig: additionalProperties: false properties: model: description: Model identifier for load balancing. type: string weight: description: Weight assigned to this model for load balancing. format: double type: number required: - model - weight type: object EmbeddingContactParams: additionalProperties: false properties: display_name: type: string email: type: string id: type: string metadata: items: type: object additionalProperties: {} type: - array - 'null' tags: items: type: string type: - array - 'null' required: - id type: object PublicIdentity: type: object properties: id: type: string description: Unique identifier for the contact example: contact_01ARZ3NDEKTSV4RRFFQ69G5FAV display_name: type: string description: Display name of the contact example: Jane Doe email: type: string format: email description: Email address of the contact example: jane.doe@example.com metadata: type: array items: type: object additionalProperties: {} description: >- A hash of key/value pairs containing any other data about the contact example: - department: Engineering role: Senior Developer logo_url: type: string description: URL to the contact's avatar or logo example: https://example.com/avatars/jane-doe.jpg tags: type: array items: type: string description: A list of tags associated with the contact example: - hr - engineering required: - id description: >- Information about the identity making the request. If the identity does not exist, it will be created automatically. securitySchemes: ApiKey: type: http scheme: bearer bearerFormat: JWT ````