> ## Documentation Index > Fetch the complete documentation index at: /docs/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. > [!NOTE] > > **Guia relacionado**: guia de Embeddings. Consulte o [guia de Embeddings](/docs/pt-BR/ai-gateway/features/embeddings.md) para um passo a passo com exemplos. ## OpenAPI ````yaml post /v2/router/embeddings openapi: 3.1.0 info: title: Toqan Router API version: '2.0' description: Toqan Router API documentation servers: - url: https://router.toqan.ai/eu description: Frankfurt (Europe) - url: https://router.toqan.ai/br description: São Paulo (Brazil) security: - ApiKey: [] tags: - description: >- API keys authenticate programmatic access to the workspace. They expose opaque tokens, per-domain access grants, and budget and rate-limit constraints. name: API keys - name: Logs description: >- OpenTelemetry log query API. Search, filter, aggregate, and facet log records ingested via OTLP. - 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. - name: Telemetry description: >- Unified query envelope for traces, metrics, and logs. One request shape, one filter dialect, and one response shape per source, validated by a per-source registry. - name: Traces description: >- Query and inspect ingested trace data: search trace summaries, aggregate metrics, and read individual traces and their spans. - name: Views description: Saved filters and columns for workspace observability pages. - description: List models available through the AI Router. name: Models - name: Alerts description: >- Alerts evaluate a telemetry metric on a fixed interval and fire notifications through notifiers when the value breaches a threshold. Each breach opens a trigger that tracks the incident until the value recovers. - name: Annotation Queues description: Annotation queues collect spans for human review. - name: Budgets description: >- Budgets govern spend, token usage, and request rate across six scopes: workspace, project, identity, API key, provider, and model. Every applicable budget is enforced, and the most restrictive limit applies per dimension. - name: Files description: File upload and retrieval operations. - name: Guardrail Rules description: >- Guardrail Rules conditionally enforce evaluators and plugins for AI Gateway traffic. Rules may be scoped to a project or the whole workspace. - name: Identities description: >- Identities represent end users from your system for usage and engagement tracking. - name: Management keys description: >- Management keys are workspace-scoped credentials that authenticate programmatic access to workspace administration surfaces (API keys, budgets). Unlike project-scoped API keys, a management key always operates at the workspace level. - name: MCP Gateway description: >- Register upstream MCP servers, discover and sync their tools, and assemble gateways that expose a curated tool surface to MCP clients. - name: Model Catalog description: >- Browse the Toqan Router model catalog: every model Toqan Router offers, across every provider, with pricing, capabilities and benchmark data. List endpoints only return models that are not deprecated. This API is public, requires no authentication, and is rate limited to 120 requests per minute per IP. Responses carry a 5-minute cache-control max-age. - name: Monitors description: >- Monitors are custom observability dashboards for traces, runtime metrics, and logs. Each monitor holds widgets that chart one telemetry query. List the metrics, operations, and dimensions available to your workspace with `GET /v3/telemetry/capabilities`, or start from a preset with `GET /v2/monitors/presets`. - name: Notifiers description: Notifier destinations used to send delivery and workflow notifications. - name: Routing Rules description: >- Routing Rules conditionally select models and enforce request plugins for AI Gateway traffic. Rules are evaluated by ascending priority and may be scoped to a project or the whole workspace. - name: Threads description: Threads group related trace invocations and their aggregate usage - name: Smart Routers description: >- Create and manage workspace Smart Routers. A Smart Router selects a model from an eligible pool for each request according to a quality, balanced, or cost profile. - name: Responses - name: Embeddings - description: Beta. Run typed classification questions against a classify model. name: Classify - description: Beta. Run classification decisions with the classify contract. name: Decisions - description: >- Run large offline workloads as JSONL batches and download OpenAI-compatible result files. name: Batches 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 fallback_on_codes: description: >- HTTP status codes that trigger fallback. Defaults to [408,429,500,502,503,504,529]. Each code must be unique and between 400 and 599. items: format: int64 type: integer maxItems: 20 type: - array - 'null' 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: - minLength: 1 type: string - 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: type: string description: >- The name to display on the trace. If not specified, the default system name will be used. orq: $ref: '#/components/schemas/EmbeddingOrqParams' description: >- 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. '401': description: >- Authentication required. See https://router.toqan.ai/docs/reference/errors for the error codes. content: application/json: schema: $ref: '#/components/schemas/APIErrorResponse' security: - ApiKey: [] 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/ResponseIdentity' 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 retries per model after the initial attempt (0-5). Set 0 to disable retries. When retry is omitted, the gateway retries twice. format: int64 type: integer on_codes: description: >- HTTP status codes that trigger a retry. Defaults to [408, 429, 500, 502, 503, 504, 529]. items: format: int64 type: integer type: - array - 'null' required: - count 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 APIErrorResponse: type: object additionalProperties: false properties: error: $ref: '#/components/schemas/APIError' required: - error 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 ResponseIdentity: 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 APIError: additionalProperties: false properties: code: type: - string - 'null' failures: {} message: type: string param: type: - string - 'null' type: type: string required: - message - type - param - code type: object securitySchemes: ApiKey: type: http scheme: bearer bearerFormat: JWT ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.