Create an Embedding

Convert input content into vectors for retrieval or similarity calculations.

POST https://token.moi.matrixorigin.cn/v1/embeddings

Before you begin

1. Prepare a personal access token or service account API key for Genesis. See Access credentials for credential selection and permissions.

2. Use List callable models to select a model that supports Embeddings.

Request body

Replace $GENESIS_ACCESS_TOKEN and $MODEL_ID with your credential and the selected model ID.

Request example

curl -X POST \
  "https://token.moi.matrixorigin.cn/v1/embeddings" \
  -H "Authorization: Bearer $GENESIS_ACCESS_TOKEN" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "'"$MODEL_ID"'",
  "input": [
    "database",
    "search"
  ],
  "encoding_format": "float"
}'

Parameters

The fields below cover text input. Images, videos, and multi-content vector output require corresponding model capabilities and input configuration.

Parameter	Type	Required	Description
model	string	Yes	Selected model ID from data[].id in the model list.
input	string or array of string or array of object	Yes	Nonempty text input. Object fields are listed below.
input[].content	string or array of object	Required for object input	Text or text blocks for an object input.
input[].content[].type	string	Required for a text block	Use text for a text block.
input[].content[].text	string	Required for a text block	Nonempty text content.
encoding_format	string	No	Vector encoding. The text example uses float; base64 requires model and service support.
dimensions	integer	No	Requested positive vector dimension; set only when supported by the selected model.

Successful response

A successful request returns the vector for each input and token usage.

Response example

{
  "object": "list",
  "model": "MODEL_ID",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [
        0.018,
        -0.042,
        0.337
      ]
    },
    {
      "object": "embedding",
      "index": 1,
      "embedding": [
        0.032,
        0.011,
        0.296
      ]
    }
  ],
  "usage": {
    "prompt_tokens": 2,
    "total_tokens": 2
  }
}

Fields

Field	Type	Description
object	string	Object type list.
model	string	Model that processed the request.
data	array of object	Vectors for the input texts.
data[].object	string	Result type embedding.
data[].index	integer	Zero-based position in the input.
data[].embedding	array of number or string	Vector values; float returns a numeric array. The example vectors are shortened; actual length depends on the model and dimension setting.
usage	object	Token usage returned by the model.
usage.prompt_tokens	integer	Input tokens.
usage.total_tokens	integer	Total tokens.

Error response

A missing model ID returns HTTP 400. Supply the model ID before sending the request again.

Response example

{
  "error": {
    "message": "missing required parameter: model",
    "type": "invalid_request",
    "code": "invalid_request"
  }
}

Fields

Field	Type	Description
error	object	Error details.
error.message	string	Error description; the example indicates a missing model ID.
error.type	string	Error type; may be omitted by a model service.
error.code	string or null	Error code; may be omitted by a model service.

Last updated on Oct 19, 2026