Nova 2 Lite
Amazon · released Dec 2, 2025
- Type
- Proprietary
- Input
- None held
- Output
- None held
- Cached
- None held
We don't hold a list price for this model yet · hosted only — we hold no downloadable copy
Our take
Written Aug 3, 2026Nova 2 Lite is Amazon's hosted-only multimodal model that can handle up to one million tokens in a single request. It accepts text, images, files and video, and scores strongest on coding tasks while trailing on creative writing.
Pick this for long-document analysis or video understanding where you need a one-million-token request limit, or for coding assistance where its measured coding score is the relative bright spot. Use it if you are already running AWS-native workflows on Bedrock. Skip it if you need strong creative writing output, want to self-host or fine-tune, or need confirmed throughput outside Amazon's own platform.
The case for it
- One of the largest request limits in the catalogue, at one million tokens.
- Coding is its strongest measured skill, scoring 66.2 points above its overall text score.
- Arena Text scores were almost identical across two measured weeks, suggesting stable rather than volatile performance.
The case against it
- Creative writing is the lowest of its six measured categories, scoring 62.7 points below its overall text score.
- Throughput is only confirmed on Amazon Bedrock; the cheapest access route has no measured speed data.
- Hosted only with no published parameter count, so local deployment and fine-tuning are not possible.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)109th of 143 · 1336.6
CodingWriting and fixing code on its own
Arena Coding102nd of 143 · 1395.7
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Nobody we watch has scored Nova 2 Lite for this. We would take the rating from Arena Agent (IPS).
WritingWe do not rate this
Two boards come close and neither tests writing: Arena Creative Writing asks people which of two replies they prefer, and LiveBench Language tests whether a model understood a passage. So we show where Nova 2 Lite placed and give it no mark out of five.
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, which is why they get no rating.
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.
Or rent it from someone else
Cheapest of 3 live listings. Picked at the widest standard context we hold, within one quantisation slice, so the numbers beside it are a price one host actually charges.
- per 1M tokens
- $0.30 in / $2.50 out
- Context served
- 1M
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $0.30 / $2.50 | 1M | not measured | Unknown | Unknown | Unknown |
| Amazon Bedrockeu-west-1 | $0.30 / $2.50 | 1M | 43 tok/s | No | No | Confirmed |
| Amazon Bedrock | $0.30 / $2.50 | 1M | 25 tok/s | No | No | Confirmed |
Amazon BedrockAcross the 3 listings we hold: 2 say they do not train on prompts, 0 say they do and 1 do not say. 2 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✓ | ✗ | ✗ |
| Amazon Bedrockeu-west-1 | ✓ | ✗ | ✗ |
| Amazon Bedrock | ✓ | ✗ | ✗ |
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
Dates behind this page
Prices last checked 9d ago
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 do not say whether they train 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.
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
Commercial API terms. We hold no licence record for this model, so there is nothing to summarise here.
Identifiers
- Modality record
- text+image+file+video->text
- Catalogue slug
- amazon-nova-2-lite