---
title: "Create embeddings"
method: POST
path: "/v2/router/embeddings"
tags: ["Embeddings"]
---

# Create embeddings

`POST /v2/router/embeddings`

Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms.

## Request body

- object
  - `cache` EmbeddingCacheConfig
    - `ttl` integer — Time to live for cached responses in seconds. Maximum 259200 seconds (3 days).
    - `type` 'exact_match', required — Cache type.
  - `dimensions` integer — The number of dimensions the resulting output embeddings should have.
  - `encoding_format` 'float' | 'base64' — The format to return the embeddings in. Can be either float or base64.
  - `fallbacks` FallbackConfig[], nullable — Array of fallback models to use if primary model fails.
    - `model` string, required
  - `input` union, required — Input text to embed, encoded as a string or array of tokens.
    - string — A single text string to embed. Must be non-empty.
    - union[] — An array of strings or token arrays to embed. Must be non-empty.
      - union
        - string
        - integer[]
  - `load_balancer` EmbeddingLoadBalancerConfig
    - `models` EmbeddingLoadBalancerModelConfig[], nullable, required — Array of models with weights for load balancing requests.
      - `model` string, required — Model identifier for load balancing.
      - `weight` number, double, required — Weight assigned to this model for load balancing.
    - `type` 'weight_based', required — Load balancer type.
  - `model` string, required — ID of the model to use.
  - `name` string — The name to display on the trace. If not specified, the default system name will be used.
  - `orq` EmbeddingOrqParams
    - `cache` EmbeddingCacheConfig
      - `ttl` integer — Time to live for cached responses in seconds. Maximum 259200 seconds (3 days).
      - `type` 'exact_match', required — Cache type.
    - `contact` EmbeddingContactParams
      - `display_name` string
      - `email` string
      - `id` string, required
      - `metadata` object[], nullable
      - `tags` string[], nullable
    - `fallbacks` FallbackConfig[], nullable — Deprecated: use top-level fallbacks instead.
      - `model` string, required
    - `identity` ResponseIdentity
      - `display_name` string
      - `email` string
      - `id` string, required
      - `metadata` object[], nullable
      - `tags` string[], nullable
    - `load_balancer` EmbeddingLoadBalancerConfig
      - `models` EmbeddingLoadBalancerModelConfig[], nullable, required — Array of models with weights for load balancing requests.
        - `model` string, required — Model identifier for load balancing.
        - `weight` number, double, required — Weight assigned to this model for load balancing.
      - `type` 'weight_based', required — Load balancer type.
    - `name` string — Deprecated: use top-level name instead.
    - `retry` EmbeddingRetryConfig
      - `count` integer, required — Number of retry attempts (1-5).
      - `on_codes` integer[], nullable, required — HTTP status codes that trigger retry logic.
    - `timeout` EmbeddingTimeoutConfig
      - `call_timeout` integer, required — Timeout value in milliseconds.
  - `retry` EmbeddingRetryConfig
    - `count` integer, required — Number of retry attempts (1-5).
    - `on_codes` integer[], nullable, required — HTTP status codes that trigger retry logic.
  - `timeout` EmbeddingTimeoutConfig
    - `call_timeout` integer, required — Timeout value in milliseconds.
  - `user` string — A unique identifier representing your end-user.

## Response `200`

Returns the embedding vector.

- object
  - `data` PublicEmbeddingData[], nullable, required — List of embedding objects.
    - `embedding` unknown, required
    - `index` integer, required — The index of the embedding in the list of embeddings.
    - `object` 'embedding', required — The object type, which is always "embedding".
  - `model` string, required — ID of the model used.
  - `object` 'list', required — Always "list".
  - `usage` PublicEmbeddingUsage, required
    - `prompt_tokens` integer, required — The number of tokens used by the prompt.
    - `total_tokens` integer, required — The total number of tokens used by the request.

---

[API](https://skmtc.net/orq-ai/apis/orq-ai-api.md) · [All operations](https://skmtc.net/orq-ai/apis/orq-ai-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/orq-ai/orq-ai-api/revisions/deb8d376faee/schema)