Embeddings API

The Embeddings API converts text into high-dimensional vector representations for semantic search, text similarity calculation, clustering analysis, and other applications.

Endpoint


POST https://aiapi.services/v1/embeddings

Authentication

All requests must include your API key in the HTTP header:


Authorization: Bearer YOUR_API_KEY

Supported Models

Embedding Models

text-embedding-004 - 4th generation text embedding model for semantic search and vector representation

See Available Models for complete model list.

Request Parameters

Required Parameters

Parameter	Type	Description
`model`	string	Model ID to use, e.g., `text-embedding-3-small`
`input`	string/array	Text to convert to vectors, can be a single string or array of strings

Optional Parameters

Parameter	Type	Default	Description
`encoding_format`	string	`float`	Return format: `float` or `base64`
`dimensions`	integer	-	Output vector dimensions (supported by some models only)
`user`	string	-	Unique identifier for end user

Code Examples

cURL


curl https://aiapi.services/v1/embeddings \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-3-small",
    "input": "Artificial intelligence is transforming the world"
  }'

Python


import requests
 
response = requests.post(
  'https://aiapi.services/v1/embeddings',
  headers={
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  json={
    'model': 'text-embedding-3-small',
    'input': 'Artificial intelligence is transforming the world'
  }
)
 
data = response.json()
embedding = data['data'][0]['embedding']
print(f'Vector dimensions: {len(embedding)}')
print(f'First 5 values: {embedding[:5]}')

JavaScript


const response = await fetch('https://aiapi.services/v1/embeddings', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: 'text-embedding-3-small',
    input: 'Artificial intelligence is transforming the world'
  })
});
 
const data = await response.json();
console.log(data.data[0].embedding); // Vector array

Go


package main
 
import (
  "bytes"
  "encoding/json"
  "fmt"
  "io"
  "net/http"
)
 
func main() {
  url := "https://aiapi.services/v1/embeddings"
 
  payload := map[string]interface{}{
    "model": "text-embedding-3-small",
    "input": "Artificial intelligence is transforming the world",
  }
 
  jsonData, _ := json.Marshal(payload)
  req, _ := http.NewRequest("POST", url, bytes.NewBuffer(jsonData))
  req.Header.Set("Authorization", "Bearer YOUR_API_KEY")
  req.Header.Set("Content-Type", "application/json")
 
  client := &http.Client{}
  resp, _ := client.Do(req)
  defer resp.Body.Close()
 
  body, _ := io.ReadAll(resp.Body)
  fmt.Println(string(body))
}

Rust


use reqwest::header::{HeaderMap, HeaderValue, AUTHORIZATION, CONTENT_TYPE};
use serde_json::json;
 
#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let client = reqwest::Client::new();
 
    let mut headers = HeaderMap::new();
    headers.insert(AUTHORIZATION, HeaderValue::from_static("Bearer YOUR_API_KEY"));
    headers.insert(CONTENT_TYPE, HeaderValue::from_static("application/json"));
 
    let payload = json!({
        "model": "text-embedding-3-small",
        "input": "Artificial intelligence is transforming the world"
    });
 
    let response = client
        .post("https://aiapi.services/v1/embeddings")
        .headers(headers)
        .json(&payload)
        .send()
        .await?;
 
    let data: serde_json::Value = response.json().await?;
    let embedding = &data["data"][0]["embedding"];
 
    println!("Vector dimensions: {}", embedding.as_array().unwrap().len());
    println!("Vector data: {:?}", embedding);
 
    Ok(())
}

PHP


<?php
 
$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, "https://aiapi.services/v1/embeddings");
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_POST, true);
curl_setopt($ch, CURLOPT_HTTPHEADER, [
    "Authorization: Bearer YOUR_API_KEY",
    "Content-Type: application/json"
]);
 
$data = [
    "model" => "text-embedding-3-small",
    "input" => "Artificial intelligence is transforming the world"
];
 
curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($data));
$response = curl_exec($ch);
curl_close($ch);
 
$result = json_decode($response, true);
$embedding = $result['data'][0]['embedding'];
 
echo "Vector dimensions: " . count($embedding) . "\n";
echo "First 5 values: " . implode(", ", array_slice($embedding, 0, 5)) . "\n";
?>

Ruby


require 'net/http'
require 'json'
 
uri = URI('https://aiapi.services/v1/embeddings')
request = Net::HTTP::Post.new(uri)
request['Authorization'] = 'Bearer YOUR_API_KEY'
request['Content-Type'] = 'application/json'
 
request.body = {
  model: 'text-embedding-3-small',
  input: 'Artificial intelligence is transforming the world'
}.to_json
 
response = Net::HTTP.start(uri.hostname, uri.port, use_ssl: true) do |http|
  http.request(request)
end
 
data = JSON.parse(response.body)
embedding = data['data'][0]['embedding']
 
puts "Vector dimensions: #{embedding.length}"
puts "First 5 values: #{embedding[0..4].join(', ')}"

Response Format

Success Response


{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [
        -0.006929283,  // Dimension 1
        -0.005336422,  // Dimension 2
        0.024047505,   // Dimension 3
        // ... total 1536 dimensions (text-embedding-3-small)
      ]
    }
  ],
  "model": "text-embedding-3-small",
  "usage": {
    "prompt_tokens": 8,      // Input tokens consumed
    "total_tokens": 8        // Total tokens consumed
  }
}

Response Fields

Field	Type	Description
`object`	string	Fixed value `"list"`
`data`	array	Array of embedding vectors, one per input text
`data[].object`	string	Fixed value `"embedding"`
`data[].index`	integer	Index of input text in batch request (starting from 0)
`data[].embedding`	array[float]	Float vector, dimensions depend on model: • text-embedding-3-small: 1536 dimensions • text-embedding-3-large: 3072 dimensions • text-embedding-004: 768 dimensions
`model`	string	Actual model name used
`usage.prompt_tokens`	integer	Number of tokens consumed by input text
`usage.total_tokens`	integer	Total tokens consumed (for embedding API, equals prompt_tokens)

Vector Dimensions

Different models return different dimensional vectors:

Model	Dimensions	Use Case
text-embedding-3-small	1536	General embeddings, cost-effective
text-embedding-3-large	3072	High-precision embeddings, more accurate
text-embedding-004	768	Google’s text embedding model
text-embedding-ada-002	1536	Classic model, backward compatible

Error Response

When requests fail, standard error format is returned. See Error Handling documentation for details.


{
  "code": "invalid_request_error",
  "message": "Invalid parameter: input text too long",
  "data": null
}

Authentication - Learn how to get and use API keys
Available Models - View all supported models and pricing
Chat API - Conversational AI interface