Text-to-Embedding

Text-to-Embedding converts text into vector representations for semantic search and similarity. The API returns embedding vectors along with a task ID to track processing.

post

Endpoint for requesting text to embedding inference

Authorizations

bearerAuth

AuthorizationstringRequired

Bearer authentication header of the form Bearer <token>.

Header parameters

Acceptstring · enumRequiredDefault: application/jsonPossible values:

Body

application/json

inputone ofRequired

Input text(s) to generate embeddings for. Can be a single string or array of strings (max 2048 items). Each input limited to 8192 tokens, total request limited to 300k tokens.

stringOptionalExample: This is a sample text for embedding generation.

or

string[]OptionalExample: ["First text for embedding","Second text for embedding","Third text"]

modelstringRequired

The embedding model to use. Available models can be retrieved via the GET /api/v1/client/models endpoint.

Example: Bge_M3_FP16

return_result_in_responseboolean | nullableOptional

If true, the embedding result will be returned directly in the response instead of only download url. Optional parameter.

Default: falseExample: false

Responses

200

ID of the inference request.

application/json

401

Unauthorized user.

application/json

404

Unauthorized user.

application/json

post

/api/v1/client/txt2embedding

HTTPcURLJavaScriptPython

POST /api/v1/client/txt2embedding HTTP/1.1
Host: api.deapi.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: application/json
Content-Type: application/json
Content-Length: 115

{
  "input": "This is a sample text for embedding generation.",
  "model": "Bge_M3_FP16",
  "return_result_in_response": false
}

{
  "data": {
    "request_id": "c08a339c-73e5-4d67-a4d5-231302fbff9a"
  }
}

post

Endpoint for calculating price for text to embedding inference

Authorizations

bearerAuth

AuthorizationstringRequired

Bearer authentication header of the form Bearer <token>.

Header parameters

Acceptstring · enumRequiredDefault: application/jsonPossible values:

Body

application/json

inputone ofRequired

Input text(s) to generate embeddings for. Can be a single string or array of strings (max 2048 items). Each input limited to 8192 tokens, total request limited to 300k tokens.

stringOptionalExample: This is a sample text for embedding generation.

or

string[]OptionalExample: ["First text for embedding","Second text for embedding"]

modelstringRequired

The embedding model to use. Available models can be retrieved via the GET /api/v1/client/models endpoint.

Example: Bge_M3_FP16

Responses

200

Calculated price for txt2embedding inference.

application/json

401

Unauthorized user.

application/json

404

Unauthorized user.

application/json

post

/api/v1/client/txt2embedding/price-calculation

HTTPcURLJavaScriptPython

POST /api/v1/client/txt2embedding/price-calculation HTTP/1.1
Host: api.deapi.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: application/json
Content-Type: application/json
Content-Length: 81

{
  "input": "This is a sample text for embedding generation.",
  "model": "Bge_M3_FP16"
}

{
  "data": {
    "price": 0.0003
  }
}