Skip to main content
POST
/
openai
/
v1
/
embeddings
Create Embeddings
curl --request POST \
  --url https://api.myrouter.ai/openai/v1/embeddings \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "input": [
    "<string>"
  ],
  "model": "<string>",
  "encoding_format": "<string>"
}
'
{
  "object": "<string>",
  "data": [
    {
      "index": 123,
      "embedding": [
        {}
      ],
      "object": "<string>"
    }
  ],
  "model": "<string>",
  "usage": {
    "prompt_tokens": 123,
    "total_tokens": 123
  }
}
Creates an embedding vector representing the input text.

​
Request Headers

​
Content-Type
string
required
Enum: application/json
​
Authorization
string
required
Bearer authentication format: Bearer {{API Key}}.

​
Request Body

​
input
string[]
required
Input text to embed, encoded as a string or array of tokens. To embed multiple inputs in a single request, pass an array of strings or token arrays. The input must not exceed the model’s maximum input tokens (8192 tokens for text-embedding-ada-002), must not be an empty string, and any array must have dimensions less than or equal to 2048.
​
model
string
required
The model ID to use. Enum:
  • baai/bge-m3
​
encoding_format
string
The format to return the embedding vectors in. Can be float or base64.

​
Response

​
object
string
required
Always list.
​
data
array
required
A list of embedding vectors generated by the model.
​
model
string
required
The model ID used.
​
usage
object
required
Usage information.