ChatGPT API

ChatGPT Scraper

Get exactly what users see in ChatGPT — including sources, citations, query fan-out, and follow-up queries — returned as clean, structured JSON.

Try free — 500 credits Read the docs →

3 credits / request No credit card required to start

api.scrapellm.com

curl "https://api.scrapellm.com/scrapers/chatgpt" \
  -H "X-API-Key: your_api_key" \
  -G \
  --data-urlencode "prompt=What brands do marketers recommend?" \
  --data-urlencode "country=US"

// Response
{
  "scraper": "chatgpt",
  "status": "done",
  "result": "Marketers commonly recommend...",
  "links": [ { "url": "...", "text": "..." } ],
  "credits_used": 3
}

Features

Everything you need from ChatGPT

Built for developers and data teams who need reliable, structured output at any volume.

Real UI responses

Captures exactly what a user sees in the ChatGPT interface, not a stripped-down API response.

Sources & citations

Full list of web sources ChatGPT references, with URLs and anchor text.

Query fan-out

Extracts the internal search queries ChatGPT issues behind the scenes.

Markdown & plain text

Response returned in both markdown and plain text so you can use it anywhere.

Multi-region

Request from any country to get region-specific ChatGPT responses.

Async support

Submit requests asynchronously and poll or use webhooks to retrieve results.

Integration

Simple to integrate

One GET request. Structured JSON back. Works in any language.

import requests

response = requests.get(
  "https://api.scrapellm.com/scrapers/chatgpt",
  headers={"X-API-Key": "your_api_key"},
  params={
    "prompt": "What brands do marketers recommend?",
    "country": "US",
  }
)

print(response.json())

const params = new URLSearchParams({
  prompt: 'What brands do marketers recommend?',
  country: 'US',
});

const response = await fetch(
  `https://api.scrapellm.com/scrapers/chatgpt?${params}`,
  { headers: { 'X-API-Key': 'your_api_key' } }
);
const data = await response.json();
console.log(data);

curl "https://api.scrapellm.com/scrapers/chatgpt" \
  -H "X-API-Key: your_api_key" \
  -G \
  --data-urlencode "prompt=What brands do marketers recommend?" \
  --data-urlencode "country=US"

Response schema 200 OK

Field	Type	Description
result	string	Plain text response from ChatGPT
result_markdown	string	Markdown-formatted response
links	array	List of cited sources with URL and anchor text
search_queries	array	Internal queries ChatGPT used (query fan-out)
llm_model	string	Model used (e.g. gpt-4o)
credits_used	integer	Credits consumed by this request
elapsed_ms	float	Request duration in milliseconds

Use cases

Built for real-world workflows

Teams across marketing, SEO, research, and product use ScrapeLLM to get structured ChatGPT data at the scale that matters.

Brand mention monitoring AI SEO research Competitor tracking Content strategy Market intelligence

Why not the direct ChatGPT API?

Direct APIs don't return sources, citations, or the real UI response

Token-based pricing is unpredictable and expensive at scale

No multi-region support — can't request from specific geographies

With ScrapeLLM

Real UI responses with all sources, citations, and structured data

Flat credit pricing — predictable costs at any volume

Multi-region routing — request from any country in one API call