curl --request POST \
  --url https://api.zerogpu.ai/v1/embeddings \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "model": "all-minilm-l6-v2",
  "input": "ZeroGPU runs high-volume inference tasks on small models at the edge."
}
'

import requests

url = "https://api.zerogpu.ai/v1/embeddings"

payload = {
    "model": "all-minilm-l6-v2",
    "input": "ZeroGPU runs high-volume inference tasks on small models at the edge."
}
headers = {
    "x-api-key": "<api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'x-api-key': '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'all-minilm-l6-v2',
    input: 'ZeroGPU runs high-volume inference tasks on small models at the edge.'
  })
};

fetch('https://api.zerogpu.ai/v1/embeddings', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

false

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.zerogpu.ai/v1/embeddings"

	payload := strings.NewReader("{\n  \"model\": \"all-minilm-l6-v2\",\n  \"input\": \"ZeroGPU runs high-volume inference tasks on small models at the edge.\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("x-api-key", "<api-key>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

require 'uri'
require 'net/http'

url = URI("https://api.zerogpu.ai/v1/embeddings")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["x-api-key"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"all-minilm-l6-v2\",\n  \"input\": \"ZeroGPU runs high-volume inference tasks on small models at the edge.\"\n}"

response = http.request(request)
puts response.read_body

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [
        0.012601,
        -0.072932,
        0.043332,
        0.028129,
        0.033064,
        -0.078302,
        -0.153619,
        -0.011621
      ]
    }
  ],
  "model": "all-MiniLM-L6-v2",
  "usage": {
    "prompt_tokens": 18,
    "total_tokens": 18
  }
}

{
  "error": {
    "code": "insufficient_quota",
    "message": "You have insufficient quota to complete this request."
  }
}