Skip to content
CostPerPrompt

Nova Pro 1.0 API Pricing

Amazon · context window 300K · prices updated 2026-09-15

Input per 1M tokens
$0.8
Output per 1M tokens
$3.20
Cached input per 1M
No discounted cached tier on this model

Where Nova Pro 1.0 sits on price

At $3.20 per million output tokens, Nova Pro 1.0 is a mid tier model — 1.5× the median output price of $2.08, which puts it cheaper than 40% and pricier than 60% of the models we track. It sits 4th cheapest of the 5 Amazon models we track. Output costs 4.0× input, the usual spread — trim both, starting with the answer length.

Output tokens per $1
312,500
One full context fill
$0.24
Cheaper than
40% of tracked models

What real workloads cost on Nova Pro 1.0

These three workloads are the ones teams actually run on a mid-priced model — a $3.20/1M model is not bought for the same job as one ten times the price.

Workload Per request Per month
Support chatbot — 500 conversations/day (5K in / 1.4K out) Conversation history re-sent each turn — the classic prompt-caching win. $0.0085 $127
Document pipeline — 10K docs/day (3K in / 500 out) Batch-friendly: no user waiting, so a ~50% batch discount usually applies. $0.004 $1200
Small app — 1K requests/day (500 in / 150 out) The baseline most side projects actually run at. $0.0009 $26.40

Model your exact traffic in the API cost calculator — it preloads Nova Pro 1.0 with caching and batch options.

Nova Pro 1.0 price history

Nova Pro 1.0's price has not moved since we began tracking it on Aug 2, 2026 — 44 days of stability in a market where 78 of the 334 models we track have repriced over the same period. Amazon's lineup has held steady across the board.

Change-points from our daily price snapshots (tracking since Aug 2, 2026; intraday moves between snapshots are not captured).

Nova Pro 1.0 vs DeepSeek V4 Pro 0423

The closest-priced alternative from another vendor is DeepSeek V4 Pro 0423 (DeepSeek) — priced within a rounding error on output, with $0.8 more per million input tokens. When two models land this close on price, the decision is quality on your own workload, not the price sheet: run 50 real requests through both and compare.

See DeepSeek V4 Pro 0423 pricing →

Cheaper alternatives

More Amazon models

Frequently asked questions

How much does the Nova Pro 1.0 API cost?

Nova Pro 1.0 costs $0.8 per million input tokens and $3.20 per million output tokens and no discounted cached-input tier. That works out to roughly 312,500 output tokens per dollar.

What does the support chatbot workload cost on Nova Pro 1.0?

Support chatbot — 500 conversations/day (5K in / 1.4K out) costs about $0.0085 per request and $127 per month on Nova Pro 1.0. Conversation history re-sent each turn — the classic prompt-caching win.

What does it cost to fill Nova Pro 1.0's 300K context window?

Sending 300K of input in a single request costs $0.24 at $0.8 per million tokens — before any output. There is no cached-input tier on this model, so every repeat of that context is billed at full price. This is why large context windows are cheap to advertise and expensive to actually use.

Is Nova Pro 1.0 worth the price?

Nova Pro 1.0 sits in the middle of the market (4 of 5 by price within Amazon). The honest test is a routing experiment: send the same 200 real requests to this model and to a tier below, and compare failure rate against the price gap — most teams find a majority of traffic never needed the pricier model.