ModelPriceWatch.com
Last scan 2026-09-22 Models tracked 267 Providers 35 Cheapest paid Granite 4.0 H Micro $0.017/Mtok in Every price links to its source

Nova Premier

by Amazon

Retired flagship mid tier
Retired on . No longer served on the endpoint we price — the figures below are kept for historical reference only. Full retirement status & replacements →
Availability: AWS retired amazon.nova-premier-v1:0 on 2026-09-14: the model had been Bedrock Legacy since 2026-03-13, and both AWS surfaces re-read on 2026-09-09 — the Model lifecycle (Legacy) table and the Nova Premier model card ("Model EOL date: September 14, 2026") — carried that date unchanged, so the flip was scheduled to land on it. Two things AWS never said. First, this row's public-extended-access start date stayed empty, so the higher extended-access pricing AWS describes for Legacy models was never announced for Nova Premier, and $2.50/$12.50 is the last rate AWS published for it — what the model last cost, not a rate you can buy today. Second, AWS names no replacement, neither in the lifecycle table nor on the model card, and Bedrock's Amazon catalogue offers Nova 2 Lite and Nova 2 Sonic but no Nova 2 flagship, so there is no vendor-named successor to link. The nearest tracked Amazon alternative is Nova Pro at $0.80/$3.20 per 1M, which is our comparison, not AWS's designation.

Today's price · per 1M tokens

Input

$2.50

per 1M tokens

Output

$12.50

per 1M tokens

Blended

$5.00

blended $/1M — 3:1 weighted input:output

Source: official Amazon pricing · read MODELPRICEWATCH.COM · 2026-09-22

Price receipt

Historical price.This model is retiredwithdrawn on so the provider no longer sells it and its page can no longer confirm this number: a price for a model no longer on sale is unconfirmable by definition, not missing. The figures above are the last prices we recorded for this model, kept as a historical record rather than a live quote.

Overview

Retired from Amazon Bedrock on 2026-09-14, the end-of-life date AWS set for amazon.nova-premier-v1:0 in us-east-1, us-east-2 and us-west-2; requests to it now fail. AWS named no replacement. Last listed at $2.50/$12.50 per 1M tokens.

Capabilities

struck through = not supported
Input 3/4
Text Image Audio Video
Output
Text
Features 2/9
Prompt caching Reasoning Coding Fast inference Long context Open weights Multimodal Web search Realtime

Benchmark performance

accuracy % · higher is better
GPQA Diamond vendor
55%
SWE-Bench Verified vendor
30%
Humanity's Last Exam vendor
18%
ARC-AGI 2 vendor
15%
AIME 2025 vendor
50%
MMMLU vendor
76%
BFCL vendor
62%
HumanEval vendor
80%
MATH 500 vendor
68%

Every per-benchmark score we hold for this model is reported by its own vendor, so none is counted toward an accuracy average or any ranking.

80 tokens/sec output

Source: AWS model card · updated · See full rankings →

Specifications

Provider
Amazon
Context window
1M tokens
Modality
text, image, video
Parameters
Proprietary
Open source
No — proprietary
Released
Status
Retired ended
Last updated
Tags
flagshipmultimodalretired

Availability verified: per Amazon's own deprecation notice