Skip to main content
POST
/
v2
/
router
/
embeddings
curl --request POST \ --url https://api.orq.ai/v2/router/embeddings \ --header 'Authorization: Bearer <token>' \ --header 'Content-Type: application/json' \ --data ' { "input": [ "The food was delicious", "And the waiter was friendly" ], "model": "openai/text-embedding-3-small" } '
{
  "data": [
    {
      "embedding": "<unknown>",
      "index": 123
    }
  ],
  "model": "<string>",
  "usage": {
    "prompt_tokens": 123,
    "total_tokens": 123
  }
}

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
​
input
required

Input text to embed, encoded as a string or array of tokens.

Minimum string length: 1
​
model
string
required

ID of the model to use.

​
cache
object

Cache configuration for the request.

​
dimensions
integer<int64>

The number of dimensions the resulting output embeddings should have.

​
encoding_format
enum<string>

The format to return the embeddings in. Can be either float or base64.

Available options:
float,
base64
​
fallbacks
object[] | null

Array of fallback models to use if primary model fails.

​
load_balancer
object

Load balancer configuration for the request.

​
name
string

The name to display on the trace. If not specified, the default system name will be used.

​
orq
object

Orq platform extension parameters. Top-level equivalents take priority when both are set.

​
retry
object

Retry configuration for the request.

​
timeout
object

Timeout configuration to apply to the request.

​
user
string

A unique identifier representing your end-user.

Response

200 - application/json

Returns the embedding vector.

​
data
object[] | null
required

List of embedding objects.

​
model
string
required

ID of the model used.

​
object
enum<string>
required

Always "list".

Available options:
list
​
usage
object
required

The usage information for the request.