Image Query API for Visual Q&A & Image Understanding

API Endpoint Access URL

https://api.pixlab.io/query

Description

The QUERY API endpoint lets you ask natural-language questions about an image and receive a grounded response based on the visual content. It is useful for product catalogs, support tools, moderation review, visual assistants, and internal workflows where teams need more than static labels or captions.

Typical prompts include questions about visible objects, scene details, product attributes, counts, likely setting, or other contextual information present in the image. The endpoint supports multiple languages, making it practical for customer-facing features as well as developer and business workflows across regions.

HTTP Methods

GET, POST

HTTP Parameters

Required

Fields	Type	Description
`img`	URL	URL to the input image you want to query in the event of a `GET` request. If you want to upload an image directly from your app, then submit a `multipart/form-data` POST request instead. Refer to the POST Request Data section below.
`query`	String	The question or instruction you want to ask about the submitted image.
`key`	String	Your PixLab API Key ↗. You can also send the key in the `WWW-Authenticate` HTTP header and omit this parameter.

Optional

Fields	Type	Description
`lang`	String	Response language. Defaults to `english`.

POST Request Body

This section explains when to use a POST request instead of a simple GET request.

Allowed Content-Types:

multipart/form-data
application/json

Use multipart/form-data to upload an image directly from your app. Refer to the PixLab GitHub Repository ↗ for a working example. If you're using application/json, pass a public image URL or a previously stored asset reference in img. The store endpoint can help when you want to upload media before invoking this endpoint.

HTTP Response

application/json

This endpoint returns a JSON object containing the generated answer for your image prompt. Response fields include:

Fields	Type	Description
`status`	Integer	HTTP 200 indicates success. Any other code indicates failure.
`response`	String	Natural-language answer generated from the submitted image and prompt, returned in the selected language.
`error`	String	Error details returned when `status` != 200.

Code Samples



import requests
import json

# Get natural language responses to image-related queries

# Target Image: Change to any link or switch to POST if you want to upload your image directly, refer to the REST API code samples for more info.
img = 'https://pixlab.io/assets/images/nature31.jpg' 

key = 'PIXLAB_API_KEY' # Get your API key from https://console.pixlab.io/

req = requests.get('https://api.pixlab.io/query',params={
  'img':img,
  'key':key,
  'lang':'english',
  'query':'What does this image depict? Can you guess the location where it was taken?'
})
reply = req.json()
if reply['status'] != 200:
	print (reply['error'])
else:
  response = reply['response']
  print(f"Query Response: {response}")


// Ask a natural-language question about an image and get a grounded response.

// Target Image: Change to any link or switch to POST if you want to upload your image directly, refer to the REST API code samples for more info.
const img = 'https://pixlab.io/assets/images/nature31.jpg';

const key = 'PIXLAB_API_KEY'; // Get your API key from https://console.pixlab.io/

fetch('https://api.pixlab.io/query', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    img: img,
    key: key,
    lang: 'english',
    query: 'What does this image depict?'
  })
})
  .then(response => response.json())
  .then(reply => {
    if (reply.status !== 200) {
      console.error(reply.error);
    } else {
      const response = reply.response;
      console.log(`Query Response: ${response}`);
    }
  })
  .catch(error => console.error('Error:', error));

<?php
# Get natural language responses to image-related queries

# Target Image: Change to any link or switch to POST if you want to upload your image directly, refer to the REST API code samples for more info.
$img = 'https://pixlab.io/assets/images/nature31.jpg';

$key = 'PIXLAB_API_KEY'; // Get your API key from https://console.pixlab.io/

$ch = curl_init();

curl_setopt($ch, CURLOPT_URL, 'https://api.pixlab.io/query?img=' . urlencode($img) . '&key=' . $key . '&query=What does this image depict?');
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);

$reply = json_decode(curl_exec($ch), true);
curl_close($ch);

if ($reply['status'] != 200) {
    echo $reply['error'];
} else {
    $response = $reply['response'];
    echo "Query Response: " . $response;
}


require 'net/http'
require 'json'

# Get natural language responses to image-related queries

# Target Image: Change to any link or switch to POST if you want to upload your image directly, refer to the REST API code samples for more info.
img = 'https://pixlab.io/assets/images/nature31.jpg'

key = 'PIXLAB_API_KEY' # Get your API key from https://console.pixlab.io/

uri = URI('https://api.pixlab.io/query')
params = {
  'img' => img,
  'key' => key,
  'query' => 'What does this image depict?',
}

uri.query = URI.encode_www_form(params)
response = Net::HTTP.get_response(uri)
reply = JSON.parse(response.body)

if reply['status'] != 200
  puts reply['error']
else
  response = reply['response']
  puts "Query Response: #{response}"
end

Similar API Endpoints

tagimg, nsfw, img-embed, docscan, text-embed, chat, mogrify, facelookup ↗, faceverify ↗, describe