Amazon models

This model takes in plain text of about 8.1 pages at a time and gives back a numeric code for it, not written words. A buyer sits down with it to sort a large pile of articles or reports by subject, or to match a question to the right passage in a long file. Unlike the picture-matching model in its family, it takes in no photos or captions and is built for whole long documents. It stops where a job needs a written reply, since it only produces codes that computers compare, so that kind of work needs a different kind of model.

This model takes a piece of text of up to about eight pages and turns it into a numeric code that computers can compare, so it finds and groups similar writing rather than writing anything itself. Sit down with it to sort thousands of documents by topic, power a search that matches a question to the right passage, or flag near-duplicate text. Unlike its family's picture-matching sibling, which reads only a caption's worth of text, it digests full long documents in one go. It never composes answers or prose, so any job that needs a written reply needs a different kind of model.

This model takes a short piece of text, a picture, or both together, and turns them into a matching code that computers can compare. It reads about a tenth of a page at a time, so it suits short captions, product names, and single photos rather than long documents. Its strength is finding things that are alike: a shopper's words can be matched to product photos, or one picture to similar pictures, because text and images end up in the same shared space. It does not write text or answers, so any job that needs a written reply needs a different kind of model.

Amazon Nova Micro 1.0 takes text and gives back text, and it is the quickest to respond in the Nova family, reading up to about 128 pages. Send it text to summarise, translate, sort or brainstorm over, or a quick chat turn; it handles simple maths and basic code. Replies stop at about 5 pages.

Nova 2 Lite reads text, images, video and files, answers in text, can think step by step before replying, and keeps about 1,000 pages in mind at once. Give it documents to pull facts from, video to extract details from, code to write, or a multi-step task that uses the tools you connect to it. Nova Lite 1.0 reads only text and images, about 300 pages, and Nova Premier handles the hardest reasoning.

Amazon's first-generation Lite model for quick multimodal jobs: live customer chats, reading documents and answering questions about pictures, with room for many images or half an hour of video in one input

Nova Pro 1.0 reads text and images, up to about 300 pages, and replies in text. It is Amazon's middle model, balancing accuracy, speed and cost, and it is strong at answering questions about pictures and at analysing financial documents. Replies stop near 5 pages, and this version does not take video.

Nova Premier is the top of Amazon's Nova line for complex reasoning. It reads text and images, keeps about 1,000 pages in mind, and replies in text up to about 32 pages. Use it for hard multi-step analysis over long documents, and as the teacher when you train a smaller custom model from its answers. For routine chat, pulling out details or questions about images, Nova Pro or Nova Lite 1.0 do the job at a lighter size.