Amazon

Nova Lite

AI model by Amazon. Real-time pricing and benchmark data.

Pricing (per 1M tokens)

Input$0.06
Output$0.24
Blended (3:1)$0.10

Source: Artificial Analysis

Performance

Output Speed151 tok/s
Time to First Token960ms

Median values from Artificial Analysis

Benchmarks

Editorial Analysis

Profile. Nova Lite is a budget-tier option from Amazon at $0.24/M output tokens. Despite the low price, it scores competitively on measurable benchmarks — making it a candidate for high-volume production workloads where unit cost dominates.

Latency. On latency, Nova Lite reports 151 tok/s output speed and 960ms time-to-first-token. Output speed is in the normal range — most chat and completion applications will be token-bound, not streaming-bound.

Cost model. For a workload of 1M input tokens + 100K output tokens, Nova Lite costs $0.08 per million input-equivalent requests. Multiply by your monthly request volume to project the bill, and compare against the speed/correctness profile above to decide if the trade-off is worth it for your workload.

Editorial summary generated from public pricing and benchmark data (Artificial Analysis API). All numbers are sourced — see the Artificial Analysis methodology for benchmark definitions. Last refreshed 2026-08-24.

Compare with similar models

ModelInputOutputSpeed
Nova LiteCurrent
$0.06$0.24151 tok/s
Qwen3.5 9B (Non-reasoning)
$0.17$0.2587 tok/s
Mistral 7B Instruct
$0.25$0.25122 tok/s
Granite 3.3 8B (Non-reasoning)
$0.03$0.2514 tok/s
Granite 4.0 H Small
$0.06$0.2525 tok/s
Llama 2 Chat 7B
$0.05$0.25

Example Costs

Single Request
$0.0002
1.0K in / 500 out
1K Requests/day
$0.1800
1.0M in / 500.0K out
10K Requests/day
$1.80
10.0M in / 5.0M out