Nova 2 Lite
Amazon · released Dec 2, 2025
- Type
- Closed
- Input
- None held
- Output
- None held
- Cached
- None held
We don't hold a list price for this model yet · hosted only — we have no record of published weights
Our take
Written Sep 17, 2026Nova 2 Lite is a hosted-only model from Amazon: we list no download for it, so using it means choosing a host. Its only quality evidence is human preference on the text arena, where coding prompts rate above its creative-writing prompts, and that is a preference rating rather than a correctness measure.
Use it for everyday chat, drafting and document work where a large request capacity matters and the bill is predictable, or when a screenshot, a file or a clip arrives alongside the question. All three listed hosts charge the same rate, so picking one does not change the bill. Skip it if you need to run the model yourself, or if you need measured correctness on coding, maths or reasoning rather than a preference rating.
The case for it
- Long inputs need not be split up first: the request capacity takes a long report or a stack of documents beside the question, though reliable recall across all of it is unverified in our data.
- One rate across every listed host, so moving a workload between them does not change the bill.
- Text, image, file and video input with written output, so a screenshot, a document or a clip does not have to be described in words first.
The case against it
- No measured correctness anywhere: every score we hold is a human preference rating from the text arena, which records which answer people liked rather than whether it was right, so coding and maths need a trial on work you can check yourself.
- Creative writing is its weakest measured category, sitting below its own coding, maths, instruction-following and hard-prompt ratings on a board that records preference rather than prose craft.
- We list no download for it, so using it means choosing a host, and no licence is supplied, so nothing here tells you what you may do with its output.
How good is it?
A lightweight text model for chat and drafting, though it trails most models on everyday questions and prose.
- getting answers to everyday questionsArena Text (overall) · 133rd of 168
- drafts, rewrites and editingArena Creative Writing · 142nd of 168
EverydayGeneral questions and everyday reasoning
Arena Text (overall)133rd of 168 · 1335
CodingWriting and fixing code on its own
Arena Coding124th of 168 · 1393
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent.
WritingDrafting and rewriting prose
Arena Creative Writing142nd of 168 · 1269
Arena Creative Writing is the only board that has scored it for this.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done.
Every published score for this model6 scoresEvery figure we hold, from 6 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Where to rent it
Prices checked 4 hours ago — each listing carries its own date.
- per 1M tokens
- $0.30 in / $2.50 out
- Context served
- 1M
- Throughput
- ~104 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.30 / $2.50checked 4 hours ago | 1M | not measured | Unknown | Unknown | Unknown |
| Amazon BedrockThrough OpenRouter | $0.30 / $2.50checked 4 hours ago | 1M66K max reply | 104 tok/s | No | No | Confirmed |
| Amazon Bedrockeu-west-1Through OpenRouter | $0.30 / $2.50checked 4 hours ago | 1M66K max reply | 16 tok/s | No | No | Confirmed |
OpenRouterAcross the 3 listings we hold: 2 say they do not train on prompts, 0 say they do and 1 does not say. 2 appear in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✗ | ✗ |
| Amazon BedrockThrough OpenRouter | ✓ | ✗ | ✗ |
| Amazon Bedrockeu-west-1Through OpenRouter | ✓ | ✗ | ✗ |
Tool calling: 3 of 3 listings say yes. JSON output: 0 of 3 listings say yes, 3 say no. Strict schema: 0 of 3 listings say yes, 3 say no.
Models people weigh against Nova 2 Lite
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 3 listings does not say whether it trains on prompts.
- We don't hold a list price for this model yet — the gap is ours, not the lab's.
- We hold no cached-input rate for any of its listings.
- We hold no batch or off-peak rate for any of its listings.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
We hold no licence record for this model, and no record of published weights either — so we can neither summarise its terms nor point you at the weights.
Identifiers
- Takes in, gives back
- Text, images, video and documents in, text out
- Catalogue slug
- amazon-nova-2-lite