Fieldbook to AIThe plain-English guide to which AI to use

Best of

Best AI for long documents

Most current top and fast models can read well over a thousand pages at once, so choose on price and quality: Claude Haiku 5.5 or DeepSeek V4.1 Flash for cheap passes, Claude Opus 5.5 for the hardest reading.

Last updated .

Costs here use the prices AI companies charge software developers, so they show relative cost, not your monthly bill. See what ChatGPT, Claude and Gemini charge you.

Model and our take (editorial)TypeSmartnessReads at once*EssayChatPDF
Claude Haiku 5.5
Made by Anthropic, the company behind Claude.The cheap and fast Claude. Great for summaries, quick questions and anything you do a lot of.
Everyday and cheap★★★★☆1,500 pages<1¢$0.13<1¢
DeepSeek V4.1 Flash
Made by DeepSeek.Very low price, can be downloaded and run yourself, and reads a very large amount at once. Hard to beat for big batches of work.
Everyday and cheapfree to download★★★☆☆1,570 pages<1¢$0.19$0.01
Gemini 3.8 Flash
Made by Google, the company behind Gemini.Google's best fast model: a middle ground between cheap and capable. It understands audio and video too.
Everyday and cheap★★★★☆1,570 pages$0.01$1.08$0.03
GPT-6.1 Sol
Made by OpenAI, the company behind ChatGPT.Good value from OpenAI: strong at programming and working through long documents, at a mid-range price.
Most capable★★★★★1,580 pages$0.01$2.62$0.07
Claude Sonnet 5.5
Made by Anthropic, the company behind Claude.The sensible default: close to the top tier for writing, fixing code and everyday work, at about half the price of Claude Opus 5.5.
Most capable★★★★★1,500 pages$0.01$2.62$0.07
Claude Opus 5.5
Made by Anthropic, the company behind Claude.The strongest all-round pick when quality matters more than cost, especially for big, complicated jobs like long coding projects.
Most capable★★★★★1,500 pages$0.03$5.25$0.15

Essay = a 1,000-word essay; Chat = a 100-message conversation; PDF = summarizing a 50-page PDF. *A rule of thumb: one page is about 500 words, and a model "reads" about 0.75 words per token. Smartness is our 1 to 5 banding of the Artificial Analysis Intelligence Index (how); "Not rated yet" means no score is available. Costs are computed from list prices using the assumptions on How we work.

How we chose: How much a model can read at once is a size limit, not a promise that it stays accurate on a huge document.

Why each one

Claude Haiku 5.5
The cheap and fast Claude. Great for summaries, quick questions and anything you do a lot of.
DeepSeek V4.1 Flash
Very low price, can be downloaded and run yourself, and reads a very large amount at once. Hard to beat for big batches of work.
Gemini 3.8 Flash
Google's best fast model: a middle ground between cheap and capable. It understands audio and video too.
GPT-6.1 Sol
Good value from OpenAI: strong at programming and working through long documents, at a mid-range price.
Claude Sonnet 5.5
The sensible default: close to the top tier for writing, fixing code and everyday work, at about half the price of Claude Opus 5.5.
Claude Opus 5.5
The strongest all-round pick when quality matters more than cost, especially for big, complicated jobs like long coding projects.