Earlier this year we wrote about generating hundreds of pages of documents and presentations. Being able to ask for a 100-page report is one thing. Getting all 100 pages, every time, with page 87 as good as page 3, turned out to be a harder problem, and one that produced the most frustrating bug reports we had this year: a document that looked finished and stopped on page 14.
This post explains how long generation works, what we changed in v1.11.1, and how to get the best result when you need a very long document.
NextDocs does not ask one model to write 100 pages in one breath. Three roles share the work:
Each role runs on the model best suited to it. The router is small and fast. The create model is chosen by your plan and mode: GPT-5.6 Luna on the fast lane, Gemini 3.8 Flash on quality, Claude Sonnet 4.6 on premium. The ladder post explains the choices.
A model writing a long document has a budget: NextDocs allows about eleven minutes for a creation and six for an update. Some models write at a steady pace from the first page to the last. Others start fast and slow down as the document grows. On a long document, the slow ones run out of budget, the stream ends, and, this was the bug, the half-finished document was saved as if it were complete. No error, no warning, just a report that ended mid-sentence.
We found it by replaying a real 22-page request from production against every model we use. The pattern was unmistakable once we could see it, and it is now the first thing we test for. Five models went through that replay; two of them did not get a lane because of it.
Three things.
A stream that ends early is now a failure, not a document. If a model stops before it is done, NextDocs refuses to save the truncated result and tells you what happened, so you can retry rather than discover the problem in a meeting.
An interrupted run keeps what it finished. This is the other side: if your connection drops or you close the tab during a long generation, the pages that completed are kept, and you can continue from there rather than starting over. Silent truncation is a failure; a deliberate stop is not.
Every model on the ladder has passed a long-document gate. No model gets a lane, however new or however good its benchmarks, until it has finished the 22-page replay within budget. Gemini 3.8 Flash passed within a day of its release and was promoted on 3 September. Claude Sonnet 5 stopped at 16 pages and was not.
A long document from NextDocs now ends in one of two ways: complete, or with a clear message that it is not and why. There is no third state. That sounds like a small thing. If you have ever presented from a report that stopped on page 14, you know it is not.
Generate a long document in NextDocs
The NextDocs Team

You can now generate larger AI documents and presentations in NextDocs, with page limits of up to 92 pages per document depending on your plan. See page limits by plan and how to split longer outputs across multiple documents.
Read more
Before a model gets a lane in NextDocs it has to finish a real 22-page document from production. Here is how the gate works, what GPT-5.6 Luna, Gemini 3.5 and 3.8 Flash, Claude Sonnet 4.6 and Claude Sonnet 5 did on it, and why the newest model is not always the one you want writing your report.
Read more
A catch-up on everything that shipped between June and September, bring your own fonts, Word export, long documents that finish, richer canvas text, new models on every lane, AI Memory, and a support desk that reaches a person, plus a short note on what is new at Shyne.
Read more