Skip to content

Every host for Nova Premier 1.0

Per 1M tokens
HostBlendedInputOutputCachedPrecisionUptime
Amazon Bedrock
$5.00
$2.50$12.50$0.625—0.0%
Amazon Nova
$5.00
$2.50$12.50———
Blended price: three input tokens for every output token, per 1M tokens.

Cheapest price over time

Per 1M tokens
Cheapest input and output price for Nova Premier 1.0 over timeFree$5.00$10.00$15.006 Dec6 Dec7 Dec$12.50$2.50
  • Input
  • Output
The cheapest list price at any host on each day it changed.

What your workload costs

A month, at every host
Cheapest a month
$2,000
Amazon Bedrock
  • Amazon Bedrock
    $2,000
  • Amazon Nova
    $2,000

Rent GPUs or pay per token?

Break-even
Renting the GPUs
$16,878/mo
Break-even volume
3.4B tokens/mo
Needed around the clock
1.3K tok/s

8 × H100 cost $16,878 a month. The cheapest API (Amazon Bedrock) charges $5.00 per 1M blended tokens, so the GPUs only pay off above 3.4B tokens a month: the box must serve 1.3K tokens a second, every second.

GPU price: cheapest on-demand offer per GPU-hour × 730 hours. No throughput is assumed: it depends on the model size, precision, batch size and serving software, so measure yours. Power, storage, egress and engineering time are not included.

More from Amazon

Blended, per 1M tokens

Quality data: LMArena (CC BY 4.0), Epoch AI (CC BY 4.0). Prices: OpenRouter, LiteLLM (MIT), provider pages. List prices in US dollars before discounts and taxes; other currencies converted at the European Central Bank reference rate. The figures on these pages are free to reuse under CC BY 4.0 with a link to this page.