Sends one prompt to several engines and returns one result per engine, each with the answer text and its sources. Pick the engines with engines (default chatgpt,gemini). Available engines: chatgpt, gemini, google_ai_mode, google_ai_overview. Each engine that returns an answer costs 1 credit. An engine that fails is not billed and does not fail the call: its entry holds an error instead. The call fails with status 503 and no charge only when no engine answers. Engines run one after the other inside a 70 second budget, so set client timeouts to 90 seconds. An engine that cannot start inside the budget is reported as failed and not billed. Prompts for google_ai_overview may hold up to 2048 characters. Microsoft Copilot and Perplexity are not available as engines.
Run this endpoint
Endpoint
Parameters
Start with the required fields, then add optional filters only when your use case needs them.
Runnable path
1 required parameter needed before sending a request.
5 optional filters available.
string
Required
The question or instruction, 1 to 4000 characters. Alias: q.
What is the capital of France?
string
Optional
Comma separated list of engines: chatgpt, gemini, google_ai_mode, google_ai_overview. Defaults to chatgpt,gemini.
chatgpt,gemini
string
Optional
Language hint such as en-US or de-DE for chatgpt and gemini.
en-US
string
Optional
IANA timezone such as Europe/Berlin. Used by chatgpt. Defaults to UTC.
example
string
Optional
Two letter interface language for the Google engines, such as en or de.
en
string
Optional
Two letter country code for the Google engines, such as us or de.
us
Request Examples
<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://scrappa.co/api/llm-answers/multi?prompt=What+is+the+capital+of+France%3F&engines=chatgpt%2Cgemini",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "GET",
CURLOPT_HTTPHEADER => [
"x-api-key: YOUR_API_KEY_HERE"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}
<?php
use Illuminate\Support\Facades\Http;
$response = Http::timeout(30)
->withHeaders(['x-api-key' => 'YOUR_API_KEY_HERE'])
->get('https://scrappa.co/api/llm-answers/multi?prompt=What+is+the+capital+of+France%3F&engines=chatgpt%2Cgemini');
if ($response->successful()) {
echo $response->body();
} else {
echo "Error: " . $response->status();
}
const options = {
method: 'GET',
headers: {
'x-api-key': 'YOUR_API_KEY_HERE'
}
};
fetch('https://scrappa.co/api/llm-answers/multi?prompt=What+is+the+capital+of+France%3F&engines=chatgpt%2Cgemini', options)
.then(response => {
if (!response.ok) {
throw new Error(`HTTP error! status: ${response.status}`);
}
return response.text();
})
.then(data => console.log(data))
.catch(error => console.error('Error:', error));
const axios = require('axios');
const options = {
method: 'GET',
url: 'https://scrappa.co/api/llm-answers/multi?prompt=What+is+the+capital+of+France%3F&engines=chatgpt%2Cgemini',
headers: {
x-api-key: 'YOUR_API_KEY_HERE',
}
};
try {
const response = await axios(options);
console.log(response.data);
} catch (error) {
console.error('Error:', error.message);
}
require 'net/http'
require 'uri'
uri = URI.parse("https://scrappa.co/api/llm-answers/multi?prompt=What+is+the+capital+of+France%3F&engines=chatgpt%2Cgemini")
http = Net::HTTP.new(uri.host, uri.port)
http.use_ssl = uri.scheme == 'https'
request = Net::HTTP::Get.new(uri.request_uri)
request['x-api-key'] = 'YOUR_API_KEY_HERE'
begin
response = http.request(request)
puts response.body
rescue => e
puts "Error: #{e.message}"
end
import http.client
import json
conn = http.client.HTTPSConnection("scrappa.co")
headers = {
'x-api-key': 'YOUR_API_KEY_HERE',
}
try:
conn.request("GET", "/api/llm-answers/multi?prompt=What+is+the+capital+of+France%3F&engines=chatgpt%2Cgemini", headers=headers)
res = conn.getresponse()
data = res.read()
print(data.decode("utf-8"))
except Exception as e:
print(f"Error: {e}")
finally:
conn.close()
import requests
headers = {
'x-api-key': 'YOUR_API_KEY_HERE',
}
try:
response = requests.get('https://scrappa.co/api/llm-answers/multi?prompt=What+is+the+capital+of+France%3F&engines=chatgpt%2Cgemini', headers=headers)
response.raise_for_status()
print(response.text)
except requests.exceptions.RequestException as e:
print(f"Error: {e}")
import okhttp3.OkHttpClient;
import okhttp3.Request;
import okhttp3.Response;
import java.io.IOException;
public class ApiExample {
public static void main(String[] args) {
OkHttpClient client = new OkHttpClient();
Request request = new Request.Builder()
.url("https://scrappa.co/api/llm-answers/multi?prompt=What+is+the+capital+of+France%3F&engines=chatgpt%2Cgemini")
.addHeader("x-api-key", "YOUR_API_KEY_HERE")
.build();
try (Response response = client.newCall(request).execute()) {
if (response.isSuccessful()) {
System.out.println(response.body().string());
} else {
System.out.println("Error: " + response.code());
}
} catch (IOException e) {
System.out.println("Error: " + e.getMessage());
}
}
}
package main
import (
"fmt"
"net/http"
"io/ioutil"
)
func main() {
client := &http.Client{}
req, err := http.NewRequest("GET", "https://scrappa.co/api/llm-answers/multi?prompt=What+is+the+capital+of+France%3F&engines=chatgpt%2Cgemini", nil)
if err != nil {
fmt.Println("Error creating request:", err)
return
}
req.Header.Set("x-api-key", "YOUR_API_KEY_HERE")
resp, err := client.Do(req)
if err != nil {
fmt.Println("Error making request:", err)
return
}
defer resp.Body.Close()
body, err := ioutil.ReadAll(resp.Body)
if err != nil {
fmt.Println("Error reading response:", err)
return
}
fmt.Println(string(body))
}
#!/bin/bash
curl -X GET \
-H "x-api-key: YOUR_API_KEY_HERE" \
"https://scrappa.co/api/llm-answers/multi?prompt=What+is+the+capital+of+France%3F&engines=chatgpt%2Cgemini"
using System;
using System.Net.Http;
using System.Threading.Tasks;
class Program
{
static async Task Main()
{
using var client = new HttpClient();
client.DefaultRequestHeaders.Add("x-api-key", "YOUR_API_KEY_HERE");
try
{
var response = await client.SendAsync(new HttpRequestMessage(HttpMethod.Get, "https://scrappa.co/api/llm-answers/multi?prompt=What+is+the+capital+of+France%3F&engines=chatgpt%2Cgemini"));
var content = await response.Content.ReadAsStringAsync();
Console.WriteLine(content);
}
catch (Exception ex)
{
Console.WriteLine($"Error: {ex.Message}");
}
}
}
import axios from 'axios';
async function run(): Promise<void> {
try {
const response = await axios({
method: 'GET',
url: 'https://scrappa.co/api/llm-answers/multi?prompt=What+is+the+capital+of+France%3F&engines=chatgpt%2Cgemini',
headers: {
'x-api-key': 'YOUR_API_KEY_HERE',
},
});
console.log(response.data);
} catch (error) {
console.error('Error:', error);
}
}
void run();
use reqwest::Client;
#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
let client = Client::new();
let response = client
.get("https://scrappa.co/api/llm-answers/multi?prompt=What+is+the+capital+of+France%3F&engines=chatgpt%2Cgemini")
.header("x-api-key", "YOUR_API_KEY_HERE")
.send()
.await?;
println!("{}", response.text().await?);
Ok(())
}
Response Schema
Example response fields are illustrative; inspect the JSON before integrating.
Example response fields
Scan these fields before integrating.
success
data
meta
{
"success": true,
"data": {
"results": [
{
"engine": "chatgpt",
"success": true,
"data": {
"engine": "chatgpt",
"answer": {
"text": "The capital of France is Paris.",
"length": 31
},
"sources": []
}
},
{
"engine": "gemini",
"success": true,
"data": {
"engine": "gemini",
"answer": {
"text": "The capital of France is **Paris**.",
"length": 35
},
"sources": [
{
"title": "Paris",
"url": "https://en.wikipedia.org/wiki/Paris",
"domain": "en.wikipedia.org",
"favicon": null,
"snippet": "Paris is the capital of France.",
"cited": true
}
]
}
}
]
},
"meta": {
"duration_ms": 14200,
"engines_requested": 2,
"billed_engines": 2,
"credits_charged": 2
}
}
Errors
Handle these documented responses before retrying or showing customer-facing failures.
Validation Error
Returned when the prompt is missing or longer than 4000 characters, or when engine, engines, model, history, timezone, locale, topic, limit or offset are invalid. engine=gemini rejects history and model.
No Answer Available
Returned as a non-billable failure when the answer engine refuses the request, returns no answer text, ends the answer early or returns an unexpected response. error.type names the cause. No credits are used.
Service Unavailable
The upstream service is temporarily unavailable. Please retry shortly.
Generate Code with AI
Copy a ready-made prompt with all the endpoint details, parameters, and example responses. Paste it into ChatGPT, Claude, or any AI assistant to instantly generate working code.
Try It Live
Test this endpoint in our interactive playground with real data.