Meterary
Start free

Amazon (Nova)

Amazon Nova Pro (Latency Optimized) API Pricing

Latency-optimized inference variant of Nova Pro. US East (N. Virginia) on-demand pricing.

Verified against Amazon (Nova)’s pricing page on 2026-07-02.

View source ↗

Facts

Specs

  • FamilyNova
  • API IDamazon.nova-pro-v1:0
  • ModalityMultimodal
  • Context window—
  • Max output—
  • Release dateNot published

Pricing (per 1M tokens)

  • Input$1.00 / 1M tokens
  • Output$4.00 / 1M tokens
  • Cached input—
  • Cache write—
  • Batch discount—

Capabilities

vision

Notes

Latency-optimized inference variant of Nova Pro. US East (N. Virginia) on-demand pricing.

Worked cost examples

Estimated monthly cost on three common usage shapes

WorkloadEst. monthly cost

Chatbot

800 input / 200 output tokens per request, 100,000 requests/month

$160.00

RAG pipeline

6,000 input / 700 output tokens per request, 30,000 requests/month

$264.00

Batch summarization

20,000 input / 1,500 output tokens per request, 5,000 requests/month

$130.00

Price history

Changes we have documented since we began tracking

No price changes recorded since we began tracking.

Amazon Nova Pro (Latency Optimized) pricing FAQ

How much does Amazon Nova Pro (Latency Optimized) cost per 1M tokens?
Amazon Nova Pro (Latency Optimized) costs $1.00 per 1M input tokens and $4.00 per 1M output tokens.
How much does Amazon Nova Pro (Latency Optimized) cost per request?
A typical request of 800 input and 200 output tokens costs about $0.0016 on Amazon Nova Pro (Latency Optimized).
Is Amazon Nova Pro (Latency Optimized) cheaper than Amazon Nova 2.0 Lite?
Amazon Nova Pro (Latency Optimized) is more expensive than Amazon Nova 2.0 Lite on input tokens, by about 203%.
Does Amazon Nova Pro (Latency Optimized) have cache pricing?
No cache discount is documented for Amazon Nova Pro (Latency Optimized) on the provider's pricing page.

Keep exploring

Estimate my usage