Amazon
Amazon

Nova 2 Lite pricing & price history

visionvideoreasoningtoolsamazon/nova-2-lite-v1

Nova 2 Lite by Amazon costs $0.30 per 1M input tokens and $2.50 per 1M output tokens, with a 1M token context window. The cheapest provider currently charges $0.30 input / $2.50 output.

$0.30Input / 1M tokens
$2.50Output / 1M tokens
1MContext window
—Intelligence index · coding 23

Price history

$0.00$1.44$2.88 2026-09-24today input /1M output /1M

No price changes since tracking began on 2026-09-24. We check every 10 minutes.

No real-traffic data for Amazon's own API on this model (it may not be served directly); the table below covers third-party hosts and says nothing about the official API.

Which platform runs Nova 2 Lite most reliably

1 platforms

By 30-day real-traffic success rate, Amazon Bedrock is the most stable and also the cheapest.

PlatformLast 30 daysStability24 h30 minIn / out
Amazon Bedrock most stableOccasional issues (2 d)avg 99.74%100%100%$0.30 / $2.501M

Success rates come from real API traffic routed to each platform (public OpenRouter data), not our probes; each daily bar is the average of that day's samples. Green ≥ 99.5 %, yellow ≥ 97 %, orange ≥ 90 %, red < 90 %. Updated 28m ago.

Cost calculator

Cheaper alternatives to Nova 2 Lite

ModelInputOutputContextIntel.
Z.ai (Zhipu)
GLM 5.3 Flash
Z.ai (Zhipu)
$0.0399$0.07841M27.8compare
$0.022$0.401M—compare
$0.098$0.291M28.6compare
Meta Llama
Llama 4 Scout
Meta Llama
$0.10$0.301.3M—compare
$0.14$0.281.1M26.7compare
$0.18$0.18164K—compare
$0.10$0.501M36.5compare
$0.10$0.501.1M—compare

Using a relay or third-party API?

Check for free whether it really serves Nova 2 Lite: output fingerprint, tokenizer and billing evidence, results in 1–3 minutes.

Check authenticity →

About Nova 2 Lite

Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing...

FAQ

How much does Nova 2 Lite cost?

Nova 2 Lite by Amazon costs $0.30 per 1M input tokens and $2.50 per 1M output tokens, with a 1M token context window. The cheapest provider currently charges $0.30 input / $2.50 output. A typical request with 2,000 input and 500 output tokens costs about $0.0019.

What is the context window of Nova 2 Lite?

Nova 2 Lite supports up to 1,000,000 tokens of context and up to 65,535 output tokens per request.

Has Nova 2 Lite’s price changed?

No price changes recorded since ModelBank started tracking it on 2026-09-24.

Is Nova 2 Lite being deprecated?

No retirement date has been announced for Nova 2 Lite as of 2026-11-12.

What are cheaper alternatives to Nova 2 Lite?

Cheaper options include GLM 5.3 Flash ($0.0399/$0.0784), DeepSeek V4.1 Flash ($0.022/$0.40), DeepSeek V4.1 Flash 1017 ($0.098/$0.29), Llama 4 Scout ($0.10/$0.30).