Encited logo
PricingTalk to sales
All Crawler Simulators
ChatGPT Fetch
Crawler simulator

ChatGPT Crawler Simulator & GPTBot Tester

Last updated

Simulate a ChatGPT or GPTBot visit to any URL on your website. Crawl the page and inspect the HTML OpenAI's bots get, so ChatGPT can read and cite it.

SIMULATE

Simulate a ChatGPT Fetch visit

Enter any URL on your website to crawl it as ChatGPT Fetch and inspect the HTML it gets.

How it works

How to use the ChatGPT Fetch simulator

  1. Step 1

    Enter a URL

    Paste the full URL of any page on your website, such as a product page, a blog post, or the home page.

  2. Step 2

    Select the ChatGPT Fetch user agent

    The tester sends the request with the ChatGPT Fetch user-agent string, so your server answers the way it answers a real ChatGPT Fetch visit.

  3. Step 3

    Run the crawl

    The simulator requests the page as ChatGPT Fetch and follows redirects, the same way the crawler does.

  4. Step 4

    Inspect the HTML

    Check the status code, redirects, response headers, raw HTML, word count, and Open Graph tags ChatGPT Fetch gets. If your main content is missing from the HTML, ChatGPT Fetch cannot read it.

Overview

What is ChatGPT Fetch?

ChatGPT uses several crawlers to access web content: GPTBot for training data collection, ChatGPT-User for real-time web browsing in ChatGPT Plus, and OAI-SearchBot for SearchGPT. When users ask ChatGPT questions, it may fetch your website content to provide accurate, up-to-date answers. If your site blocks these crawlers or serves JavaScript-only content, ChatGPT won't be able to cite your website in its responses.

Why allow it

Why allow ChatGPT Fetch?

Get cited in ChatGPT answers when users ask relevant questions
Appear in SearchGPT results (OpenAI's search engine)
Enable ChatGPT Plus users to browse and summarize your content
Contribute to OpenAI's training data (if desired)
Improve visibility in AI-powered search experiences
Robots.txt

ChatGPT Fetch robots.txt configuration

Control how ChatGPT Fetch crawls your website using robots.txt directives. Add these rules to your robots.txt file at the root of your domain, then run the simulator again on the same URL to confirm the change.

Allow ChatGPT Fetch

# Allow ChatGPT and OpenAI crawlers
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

Block ChatGPT Fetch

# Block ChatGPT and OpenAI crawlers
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

User-Agent String: Mozilla/5.0 (compatible; ChatGPT-User/1.0; +https://openai.com/)

ChatGPT Fetch simulator FAQ

Enter any URL from your website in the tester above and run the crawl. The simulator requests the page with the ChatGPT Fetch user-agent string and shows the status code, response headers, and raw HTML it gets. Inspect the HTML to confirm your main content, title, and meta tags are there before any JavaScript runs.

GPTBot is OpenAI's web crawler used for collecting training data to improve AI models. ChatGPT-User is the user-agent used when ChatGPT Plus subscribers use the 'Browse with Bing' feature to fetch real-time web content. OAI-SearchBot is used specifically for SearchGPT, OpenAI's search engine product.

To be cited by ChatGPT: 1) Ensure your robots.txt allows ChatGPT-User and OAI-SearchBot, 2) Make sure your content is in the HTML (not just JavaScript), 3) Have clear, authoritative content that answers common questions, 4) Use proper meta tags and structured data. Our crawler simulator helps you verify ChatGPT can access your content.

It depends on your goals. Allow GPTBot if you want: AI assistants to cite your content, visibility in AI search, and to contribute to AI training. Block GPTBot if you: have premium content you don't want used for training, or have concerns about AI using your content. Note: blocking GPTBot doesn't prevent ChatGPT from citing cached or previously scraped content.

ChatGPT's crawlers fetch raw HTML without executing JavaScript. If your website is a single-page application (SPA) built with React, Vue, or Angular, the crawlers may only see an empty page. Use pre-rendering or server-side rendering to make your content visible to ChatGPT's crawlers.

OpenAI doesn't publish exact crawl frequencies. GPTBot crawls for training purposes periodically, while ChatGPT-User fetches pages in real-time when users request web browsing. OAI-SearchBot crawls more frequently for search index freshness. Ensure your server can handle crawler traffic.
Google
Gemini
ChatGPT
Claude
Grok
Meta
Perplexity

Make your site crawlable

JavaScript sites often have indexing issues. Encited pre-renders your SPA into crawler-friendly HTML so ChatGPT Fetch and other bots can read your content.

All crawlers
Avatar
How can we help?
Get instant answers to your questions or leave a message for an engineer will reach out
Ask AI about Encited
See our docs
Contact support
Leave a message
We'll get back to you soon
Avatar
Ask AI about Encited
Product questions, troubleshooting and
Thinking
Preview
Drop an image to attach
Powered by ReplyMaven