- [ Home ](/) / - Does ChatGPT use llms.txt? # Does ChatGPT use llms.txt? The honest answer in 2026: no major AI provider has confirmed reading llms.txt to answer questions. Here is what each has said, and where the file is genuinely read. Last updated: June 5, 2026 ## The short answer **As of 2026, no major AI provider has officially confirmed that its assistant reads llms.txt at inference time.** That includes OpenAI (ChatGPT), Anthropic (Claude), and Perplexity, all of which are sometimes assumed to use it. This does not make the file useless. It means the value of llms.txt today comes from the tools that do read it (agent frameworks, RAG pipelines, MCP integrations), not from the consumer chatbots. ## OpenAI and ChatGPT OpenAI has not published anything stating that ChatGPT, or its GPTBot and OAI-SearchBot crawlers, parse llms.txt or treat it as a special input. When ChatGPT browses the web to answer a question, it retrieves and reads pages; there is no public commitment that it preferentially loads your llms.txt first or uses it as a site map. ## Fetching is not the same as using Site owners sometimes see AI crawlers requesting `/llms.txt` and `/llms-full.txt` in their server logs, including bots from OpenAI and Microsoft. It is tempting to read that as proof the file is being used. It is not. ℹ What a log hit really tells you A crawler fetching your llms.txt confirms the file is reachable and that bots are exploring it. It does not prove the content is parsed, prioritized, or used to shape an answer. Treat log hits as interest, not as confirmation of structured use. ## Anthropic and Perplexity Anthropic publishes a clean llms.txt and llms-full.txt for its own documentation, and Perplexity, an AI search engine, publishes one too. Neither has confirmed that its assistant consults llms.txt when responding to users. Publishing a file for your docs is a separate decision from reading other sites' files at inference time. Anthropic does operate documented crawlers (for example ClaudeBot for training data and a separate user-triggered fetcher), which respect robots.txt like any well-behaved bot. That governs access, not whether llms.txt is treated as a curated signal. ## Where llms.txt does get read The receiving side that actually reads llms.txt today is the developer-tooling layer: - **Agent coding tools** such as Cursor and Windsurf can fetch llms.txt to load project or library context before helping a developer. - **RAG pipelines** built in-house often use llms.txt as a curated reading list to decide which pages to ingest. - **MCP integrations** and documentation platforms increasingly generate and consume the file as part of their workflows. This is why developer-facing companies adopt it: their users ask AI tools technical questions, and a good llms.txt makes those answers more accurate. ## What to do today - Publish llms.txt if you run docs, an API, a developer tool, or technical SaaS. The cost is low and the tooling upside is real. - Do not expect consumer chatbots to read it yet, and do not market it as if they do. - Measure what you can: server-log hits from AI bots, referrals from AI products, and manual spot-checks of how assistants describe your product. See [does llms.txt work?](/does-llms-txt-work/) for the full method. ## FAQ **Does ChatGPT read llms.txt?** OpenAI has not announced that ChatGPT or its crawlers parse it. Fetching the file is not the same as using it. **Does Claude or Perplexity use llms.txt?** Not confirmed at inference time, even though both publish their own llms.txt for documentation. **So why publish it?** Because agent frameworks, MCP integrations, and RAG pipelines do read it, and that is where the value is in 2026. ## Next steps - [Does Google use llms.txt?](/does-google-use-llms-txt/) - [AI crawlers explained](/llms-txt-ai-crawlers/): GPTBot, ClaudeBot, PerplexityBot. - [How to create an llms.txt file](/how-to-create/). - [Generator](/generator/): build one from your sitemap. ## Sources - [ llmstxt.org, official specification ](https://llmstxt.org/) - [ Mintlify: the value of llms.txt, hype or real? ](https://www.mintlify.com/blog/the-value-of-llms-txt-hype-or-real) - [ Anthropic crawler documentation (ClaudeBot, Claude-User, Claude-SearchBot) overview ](https://almcorp.com/blog/anthropic-claude-bots-robots-txt-strategy/) On this page - [ The short answer ](#short-answer) - [ OpenAI and ChatGPT ](#openai) - [ Fetching is not the same as using ](#fetch-vs-use) - [ Anthropic and Perplexity ](#anthropic-perplexity) - [ Where llms.txt does get read ](#where-it-is-read) - [ What to do today ](#what-to-do) - [ FAQ ](#faq)