Skip to content

Create embeddings

This page documents the Create Embeddings endpoint in models-model.md style: Overview, Authentication, Parameters, Request examples, Response example.


Overview

  • Method: POST
  • Path: /v1/embeddings
  • Content-Type: application/json

Authentication

  • Use HTTP Bearer Token, e.g. Authorization: Bearer sk-xxxxx

Request parameters

ParameterTypeRequiredDescription
modelstringyesModel ID to use, e.g. text-embedding-3-large (see model list)
inputstring | array[string]yesText(s) to encode as embeddings. Single string or array of strings supported; length limits depend on the model

Request examples

Single input example:

json
{
  "model": "text-embedding-3-large",
  "input": "She is very beautiful and likes..."
}

Batch input example:

json
{
  "model": "text-embedding-3-large",
  "input": [
    "Text A",
    "Text B"
  ]
}

curl

bash
curl -X POST "https://api.gpt.ge/v1/embeddings" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxx" \
  -d '{"model":"text-embedding-3-large","input":"She is very beautiful and likes..."}'

JavaScript (fetch)

javascript
fetch('https://api.gpt.ge/v1/embeddings', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json', 'Authorization': 'Bearer sk-xxxx' },
  body: JSON.stringify({ model: 'text-embedding-3-large', input: 'She is very beautiful and likes...' })
}).then(r => r.json()).then(console.log)

Python (requests)

python
import requests

payload = { 'model': 'text-embedding-3-large', 'input': 'She is very beautiful and likes...' }
resp = requests.post('https://api.gpt.ge/v1/embeddings', headers={'Content-Type':'application/json','Authorization':'Bearer sk-xxxx'}, json=payload)
print(resp.json())

Response example (200)

json
{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [
        -0.022425562,
        -0.010263717,
        0.022136442,
        0.015323295,
        -0.0013466021
      ]
    }
  ],
  "model": "text-embedding-3-large",
  "usage": { "prompt_tokens": 16, "total_tokens": 16 }
}