OAI-SearchBot user agent string
Surfaces websites in ChatGPT search. Sites that block it are left out of ChatGPT search answers but can still appear as navigational links. Below is the exact string it sends, what each part means, and how to allow or block it.
Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36; compatible; OAI-SearchBot/1.4; +https://openai.com/searchbot
At a glance
| Type | AI crawler |
| Operator | OpenAI |
| Purpose | Indexes sites for ChatGPT search |
| Version | 1.4 |
| robots.txt token | OAI-SearchBot |
Allow or block it in robots.txt
Block OAI-SearchBot from the whole site
User-agent: OAI-SearchBot
Disallow: /Allow it again
User-agent: OAI-SearchBot
Allow: /String breakdown
| Fragment | Meaning |
|---|---|
Mozilla/5.0 | Historical compatibility token. Nearly every browser claims "Mozilla/5.0" so that old servers do not serve it broken pages. |
Macintosh | Mac computer. |
Intel Mac OS X 10_15_7 | macOS 10.15.7. Newer systems freeze this at 10.15.7, and Apple Silicon Macs still report "Intel". |
AppleWebKit/537.36 | WebKit rendering engine, build 537.36. Chromium browsers keep this token for compatibility. |
KHTML, like Gecko | Compatibility note: the engine descends from KHTML and behaves like Gecko. Kept for legacy browser sniffers. |
Chrome/131.0.0.0 | Chrome (or a Chromium-based browser), version 131.0.0.0. |
Safari/537.36 | Safari/WebKit build 537.36 — a compatibility token, not the Safari version. Chromium browsers send it too. |
compatible | Compatibility token — historically sent by IE, now mostly by bots. |
OAI-SearchBot/1.4 | OAI-SearchBot 1.4 — an automated crawler/bot, not a real browser. |
+https://openai.com/searchbot | Info page the bot operator publishes for webmasters. |
Use it in code
curl
curl -A "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36; compatible; OAI-SearchBot/1.4; +https://openai.com/searchbot" https://example.comPython (requests)
import requests
requests.get("https://example.com", headers={"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36; compatible; OAI-SearchBot/1.4; +https://openai.com/searchbot"})Playwright (Node.js)
const context = await browser.newContext({ userAgent: "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36; compatible; OAI-SearchBot/1.4; +https://openai.com/searchbot" });Source: Overview of OpenAI Crawlers · checked September 2026