Checked against the OpenRouter public models feed. Prices are copied, not estimated.

The Best Model ForWhich AI model to use, from ten labs.

Amazon (Nova)

Short answer

Amazon's generative rows here are the Nova family. Premier is the expensive reasoning model. Nova 2 Lite is the everyday model and is the one that lists video input. Nova Micro is text-only and the cheapest reviewed Nova. Titan rows are embedding models, not chat.

Lab site · Filter the full catalogue to Amazon (Nova)

What the top models are good for

1. Nova Premier 1.0

Flagship · $2.50 in · $12.50 out · 1,000,000 tokens

Guide note · 19 Nov 2026

OpenRouter calls Nova Premier the most capable Amazon multimodal model for complex reasoning, and a teacher for distilling custom models. Text and image in, text out, a million-token window. The feed has no third-party index for it. This guide does not invent one. The row does not list video input.

  • Hard reasoning inside Amazon's catalogue
  • Image input and a long window
  • Named as a distillation teacher

What it is good for

The hard reasoning job you are already running on Amazon

Stay on Premier when the task is genuinely hard and the rest of the system is on Amazon. There is no index on the feed to compare it with GPT or Claude. Judge it on your prompts.

Nova Premier 1.0 is listed at $2.50 input and $12.50 output per million tokens, with a 1,000,000-token context window.

Teacher for a smaller custom model

The listing names distillation. That is a specific reason to pay Premier's rate: generate the training signal, then serve traffic on a cheaper Nova.

Nova Premier 1.0 is listed at $2.50 input and $12.50 output per million tokens, with a 1,000,000-token context window.

The tasks are editorial illustrations, not measured benchmarks. The prices in them are read from today's feed.

2. Nova 2 Lite

Everyday · $0.30 in · $2.50 out · 1,000,000 tokens

Guide note · 19 Nov 2026

OpenRouter describes Nova 2 Lite as the fast, cost-effective reasoning model for everyday work that can read text, images, and video. It is the reviewed Amazon default, and the Nova model to use when the input is a clip.

  • Everyday multimodal model
  • Video as well as images
  • Far cheaper than Premier

What it is good for

Analyse a photo of a receipt

Image in, text out, everyday price. Ask for merchant, date, total, and tax. Reject replies that invent a line the photo does not show.

Nova 2 Lite is listed at $0.30 input and $2.50 output per million tokens, with a 1,000,000-token context window.

A short screen recording of a bug

Video input is listed here and not on Premier or Micro. A thirty-second recording plus 'what did the user hit' is a Lite job.

Nova 2 Lite is listed at $0.30 input and $2.50 output per million tokens, with a 1,000,000-token context window.

The tasks are editorial illustrations, not measured benchmarks. The prices in them are read from today's feed.

3. Nova Micro 1.0

Budget · $0.035 in · $0.14 out · 128,000 tokens

Guide note · 19 Nov 2026

Nova Micro is text-only. The listing calls it the lowest-latency Nova, at a very low cost, with a knowledge cutoff of 2024-10-31. Use it for short text. Do not use it for a photo, a video, or a question about this month's news.

  • Lowest reviewed text rate in the Nova family
  • Short classifications
  • Latency, per the listing

What it is good for

Route a subject line

A subject line and a menu of folders is the whole task. Micro is enough. The cutoff does not matter because the text is in the prompt.

Nova Micro 1.0 is listed at $0.035 input and $0.14 output per million tokens, with a 128,000-token context window.

Cheap high-volume automation that is only text

Extract a date, pick a label, draft a status line. Sample the stream. The moment a message arrives with a picture, this model is the wrong one.

Nova Micro 1.0 is listed at $0.035 input and $0.14 output per million tokens, with a 128,000-token context window.

The tasks are editorial illustrations, not measured benchmarks. The prices in them are read from today's feed.

Every current row

8 Amazon (Nova) rows on the feed.
ModelKindContextInputOutputListedGuide
Nova 2 Lite Chat 1,000,000 $0.30 $2.50 2 Dec 2025 Reviewed
Nova Lite 1.0 Chat 300,000 $0.06 $0.24 5 Dec 2024 New, not yet reviewed
Nova Micro 1.0 Chat 128,000 $0.035 $0.14 5 Dec 2024 Reviewed
Nova Premier 1.0 Chat 1,000,000 $2.50 $12.50 31 Oct 2025 Reviewed
Nova Pro 1.0 Chat 300,000 $0.80 $3.20 5 Dec 2024 New, not yet reviewed
Titan Multimodal Embeddings G1 Embeddings 128 $0.80 $0 26 Oct 2026 New, not yet reviewed
Titan Embeddings G1 - Text Embeddings 8,192 $0.10 $0 26 Oct 2026 New, not yet reviewed
Titan Text Embeddings V2 Embeddings 8,192 $0.02 $0 26 Oct 2026 New, not yet reviewed

Questions

Which Amazon (Nova) model should I start with?

For most people, start with Nova Premier 1.0, then drop to the next model on this page when the task is routine. Read the cheaper-model note under each example.

Are the examples benchmarks?

No. They are concrete tasks used to explain fit. The prices next to them are live figures from the feed. The judgment is a guide note.