Nova Premier 1.0

Amazon · released Oct 31, 2025

ProprietaryTool useVision

Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.

Compare this model Source listing

Specification

Context window: 1M
Max output: 32K
Knowledge cutoff: Not stated
Parameters: Undisclosed
Licence: Proprietary
Serving providers: 1
Moderated: Yes
Uptime: 100.0%

Intelligence

—

Not benchmarked

Coding

—

Coding Index

Agentic

—

Agentic Index

Output speed

36 t/s

Median across providers

Latency

416ms

Time to first token

Cost per task

$0.44

Estimated

Benchmarks

Where the score comes from

The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.

Evaluation scores

This model has not been put through the benchmark suite. Its speed, latency and pricing figures below are still measured.

Against its peers

Intelligence Index · this model highlighted, nearest peers in grey

Claude Opus 5Anthropic
63.1
Claude Fable 5Anthropic
62.1
GPT-5.6 SolOpenAI
60.9
Kimi K3Moonshot AI
59.7
Qwen3.8 MaxQwen
58.1
Claude Opus 4.8Anthropic
57.3
Muse Spark 1.2Meta
56.8

Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.

View as table

Model	Intelligence
Claude Opus 5	63.1
Claude Fable 5	62.1
GPT-5.6 Sol	60.9
Kimi K3	59.7
Qwen3.8 Max	58.1
Claude Opus 4.8	57.3
Muse Spark 1.2	56.8

Percentile among all indexed models

Arena Elo4th

Pricing

What it costs to run

List prices per million tokens, plus what one representative task works out to.

List price

Input / 1M tokens: $2.5
Output / 1M tokens: $12.5
Cached input / 1M: $0.625
Blended 3:1: $5

One task, estimated

$0.44

Input tokens: 50,000
Output tokens: 25,000
Profile: Standard

Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).

Serving providers

Amazon Bedrock

Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.

Arena

Head-to-head generation quality

Elo from pairwise judgements, broken out by the kind of thing the model was asked to build.

Overall Elo: 858
Win rate: 26.2%
Strongest at: Websites
Tournaments: 386

Elo by category

Dot position on a 850–875 scale · Elo has no meaningful zero

Websites
858

850875

Agent categories (full-stack apps, mobile apps) are only scored for models tested in agent harnesses.