Last verified
FAST MULTIMODAL1M CONTEXTTEXT + VISIONON BEDROCKNO CACHE ROW

Amazon Nova 2 Lite API Pricing

Amazon Nova 2 Lite is Amazon's price-performance Nova 2 tier for high-volume multimodal apps: text, image and video input with a 1M-token context. On Amazon Bedrock global cross-region inference it lists $0.30/M input and $2.50/M output. Single-region (Geo) inference is higher. Pulled from the Bedrock pricing page.

Input - per 1M tokens
$0.30/M
Geo in-region is $0.525/M global
Output - per 1M tokens
$2.50/M
Geo in-region is $4.375/M global
Cache N/A
$0.30/M
Cache no public row not listed
Effective - agentic blend
$0.48/M
92/8 split - no cache discount
§ 01 / TERMINAL

Run the numbers.

Live calculator pre-loaded with Nova 2 Lite global cross-region rates. Switch to single-region (Geo) numbers in the FAQ if your workload pins one region.

$ /mo
Workload split
Prompt cache hit rate
Tokens you can process
Words equivalent (English)
Effective rate
Open full calculator (all models · share URL · CSV) →
§ 02 / SCENARIOS

Real-world presets.

§ 03 / TOKENIZER

Paste text. See tokens. See cost.

Estimate · amazon-nova-tokenizer-estimate · ≈3.85 chars/token Auto-counts as you type

This is a chars-per-token approximation, not a real tokenizer. Actual tokens vary by language, code density, and tool-call overhead — counts are typically ±10–20% off for English prose, more for code or non-Latin scripts. For exact billing, use the vendor's official tokenizer.

Characters 602
Words 95
Tokens (estimated) 156 tokens
Cost as input · uncached $0.000047 USD
Cost as output · uncached $0.000390 USD
Cost as cached input $0.000047 USD
§ 04 / SHELF

Up against the shelf.

All models →
Model Input /M Output /M Effective blended Context Best for
Amazon Nova 2 Lite Current $0.30 $2.50 $0.48 agentic 92/8, no cache 1M High-volume multimodal on AWS
Gemini 2.5 Flash $0.30 cache $0.03 $2.50 $0.27 same list, has cache discount 1M Multimodal with prompt caching
GPT-5.4 mini $0.75 cache $0.07 $4.50 $0.54 pricier frontier-mini 400K Lower-latency OpenAI subagents
Gemini 2.5 Flash-Lite $0.10 cache $0.01 $0.40 $0.06 cheaper budget tier 1M Cheapest Google multimodal
DeepSeek V4 Flash $0.14 cache $0.00 $0.28 $0.05 cheapest raw tokens 1M Bulk low-cost traffic

Frequently asked.

Practical Amazon Nova 2 Lite pricing questions, with Bedrock's published rates kept separate from workload assumptions.

Q · 01 What is Amazon Nova 2 Lite priced at? +
On Amazon Bedrock global cross-region inference, Nova 2 Lite is $0.30/M input and $2.50/M output. Single-region (Geo) inference is higher at about $0.525/M and $4.375/M. Verified on the Bedrock pricing page 2026-07-11.
Q · 02 What is the difference between global and Geo pricing? +
Global cross-region inference lets Bedrock route your request to the cheapest available region and is the lower rate ($0.30/$2.50). Single-region (Geo) pins one region for data-residency and is roughly 1.75x more expensive. This page uses the global rate as the baseline.
Q · 03 Does Nova 2 Lite have a prompt-cache discount? +
Amazon does not publish a separate cache-read token price for Nova 2 Lite, so this calculator keeps cached input equal to base input ($0.30/M) instead of assuming a discount. Bedrock does offer a Batch mode at roughly 50% of on-demand price.
Q · 04 What context window does it support? +
Nova 2 Lite supports a 1M-token context window and up to 64K output tokens, with text, image and video input, per its Bedrock model card.
Q · 05 How does it compare with Gemini 2.5 Flash? +
Gemini 2.5 Flash lists the same $0.30/$2.50 token price but adds a cache-read discount, so its blended cost is lower. Nova 2 Lite's edge is native AWS hosting, data residency and Bedrock integration.