Nova Pro 1.0
Amazon · released Dec 5, 2024
- 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 2, 2026Nova Pro is Amazon's hosted-only text-and-image model that can handle up to 300,000 tokens in a single request. Its measured coding skill sits well above its other Arena scores, while creative writing and maths trail behind.
Pick this for long-context document and image analysis where 300,000 tokens are needed, or for coding tasks where its measured coding score leads its own profile. Use it if you are already inside the Amazon Bedrock ecosystem. Skip it if you need strong creative writing, want to self-host, or need consistent throughput — two Bedrock offers run at different speeds with no explained reason.
The case for it
- Coding is its strongest measured skill by a wide margin: 52.9 points above its own overall Arena baseline.
- Substantial request limit for document and image workloads, at 300,000 tokens.
- Uniform pricing across all three tracked offers.
The case against it
- Creative writing lags its own coding strength by over 100 points on the Arena leaderboard.
- Maths is its weakest measured category, sitting 21.1 points below its overall score.
- Throughput varies at identical pricing with no explained differentiation: 72 tokens per second versus 61 on two Bedrock offers.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)127th of 143 · 1290.1
CodingWriting and fixing code on its own
Arena Coding123rd of 143 · 1343
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Nobody we watch has scored Nova Pro 1.0 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 Pro 1.0 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
- $0.80 in / $3.20 out
- Context served
- 300K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $0.80 / $3.20 | 300K | not measured | Unknown | Unknown | Unknown |
| Amazon Bedrock | $0.80 / $3.20 | 300K | 111 tok/s | No | No | Confirmed |
| Amazon Bedrockeu-west-1 | $0.80 / $3.20 | 300K | 103 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 Bedrock | ✓ | ✗ | ✗ |
| Amazon Bedrockeu-west-1 | ✓ | ✗ | ✗ |
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.
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->text
- Catalogue slug
- amazon-nova-pro-1-0