Embeddings

This page contains the endpoints related to text-embedding capabilities.

Pham vi Apifox

• Create text embeddings (OpenAI)
• Batch create embeddings (OpenAI)
• Create text embeddings (Gemini)

API model / Embeddings

POST Create Text Embedding (Gemini)

POST /embeddings

Body Parameters

{
    "input": "Your text string goes here",
    "model": "gemini-embedding-001"
}

Request Parameters

Name	In	Type	Required	Description
Authorization	header	string	No	none
body	body	object	No	none
» model	body	string	Yes	ID of the model to use. You can call the List models API to see all available models, or review the model overview for descriptions.
» input	body	string	Yes	Input text to embed, encoded as a string or token array. To create embeddings for multiple inputs in a single request, pass an array of strings or an array of token arrays. Each input must not exceed 8192 tokens.

Response Example

200 Response

{
  "object": "string",
  "data": [
    {
      "object": "string",
      "embedding": [
        0
      ],
      "index": 0
    }
  ],
  "model": "string",
  "usage": {
    "prompt_tokens": 0,
    "total_tokens": 0
  }
}

Responses

Status	Meaning	Description	Model
200	OK	none	Inline

Response Schema

Status 200

Name	Type	Required	Constraints	Chinese Name	Description
» object	string	true	none		none
» data	[object]	true	none		none
»» object	string	false	none		none
»» embedding	[number]	false	none		none
»» index	integer	false	none		none
» model	string	true	none		none
» usage	object	true	none		none
»» prompt_tokens	integer	true	none		none
»» total_tokens	integer	true	none		none