API ResourcesEmbeddings

Embeddings

The Embeddings API creates a vector representation for given text input. This vector captures the deep semantic information of the text and can be easily consumed by machine learning models and algorithms, widely used in search, clustering, recommendation, anomaly detection and other tasks.

With an OriginRouter One subscription, choose the corresponding Coding API endpoint and make sure the model ID comes from the Supported Models list; with the pay-as-you-go API plan, choose the corresponding Beta API endpoint and make sure the model ID comes from the Model List; a plan and endpoint mismatch may make models unavailable or result in unexpected billing.

POST/beta/v1/embeddings

Create Embedding

Creates an embedding vector representing the input text.

Request Headers

Name
Content-Type
Type
string
Required
Required
Description
The value must be application/json.
Name
Authorization
Type
string
Optional
Optional
Description
Optional authentication method. The credential for API authentication, see Authentication for details.
Name
x-api-key
Type
string
Optional
Optional
Description
Optional authentication method. Pass your API key directly. Note: Do not use Authorization and x-api-key at the same time.

Request Body

Name
input
Type
string | array
Required
Required
Description
The input text to embed, encoded as a string or an array of tokens. To embed multiple inputs in a single request, pass an array of strings or an array of token arrays. The input must not exceed the model's maximum input tokens (8192 tokens for all embedding models), cannot be an empty string, and any array dimension must not exceed 2048. See example Python code for counting tokens. In addition to the per-input token limit, all embedding models enforce a total token limit of 300,000 tokens across all inputs in a single request.
Name
model
Type
string
Required
Required
Description
The model ID used to generate the response. For example text-embedding-3-large, etc. See the Model List to choose the model that best suits your needs.
Name
dimensions
Type
integer
Optional
Optional
Description
The number of dimensions the output embedding should have. Only supported in text-embedding-3 and later models.
Reducing dimensions can lower vector storage costs, speed up similarity searches, and reduce memory footprint, but may slightly affect embedding accuracy. This is an important trade-off between performance and cost.
Name
encoding_format
Type
string
Optional
Optional
Description
The format of the returned embedding vector. Can be float or base64. Defaults to float.
Name
user
Type
string
Optional
Optional
Description
A unique identifier representing your end user.

Response Body

Name
object
Type
string
Required
Required
Description
The type of the response object, always list for this endpoint.
Name
data
Type
array
Required
Required
Description
An array containing embedding objects for each input text.
Name
model
Type
string
Required
Required
Description
The model ID used to generate this embedding, for example text-embedding-3-small.
Name
usage
Type
object
Required
Required
Description
An object containing token usage information for this API call.

Request

POST

/beta/v1/embeddings

curl https://api.easytransnote.com/beta/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $YOUR_API_KEY" \
  -d '{
    "input": "你今天过得怎么样？",
    "model": "text-embedding-3-small"
  }'

Response

{
  "object": "list",
  "data": [
      {
          "object": "embedding",
          "embedding": [
              -0.0069292834,
              -0.005336422,
              ...
              -4.5471322e-05
          ],
          "index": 0
      }
  ],
  "model": "text-embedding-3-small",
  "usage": {
      "prompt_tokens": 5,
      "total_tokens": 5
  }
}