Skip to main content
POST
/
v1
/
embeddings
Create embeddings
curl --request POST \
  --url https://api.naga.ac/v1/embeddings \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "input": "<string>"
}
'
{
  "model": "<string>",
  "data": [
    {
      "index": 123,
      "embedding": [
        123
      ],
      "object": "embedding"
    }
  ],
  "usage": {
    "prompt_tokens": 123,
    "total_tokens": 123
  },
  "object": "list"
}

Authorizations

​
Authorization
string
header
required

Primary authentication for inference endpoints. Send your Naga API key as Authorization: Bearer <api-key>.

Body

application/json
​
model
string
required

Embedding model identifier.

Example:

"text-embedding-3-small"

​
input
required

Single input or batch of inputs to embed.

​
dimensions
integer

Optional target embedding dimension when supported by the model.

​
encoding_format
enum<string>
default:float

Return vectors as JSON floats or base64-encoded binary data.

Available options:
float,
base64

Response

Successful Response

​
model
string
required
​
data
EmbeddingDataResponse · object[]
required
​
usage
EmbeddingUsageResponse · object
required
​
object
string
default:list
Allowed value: "list"