Home / Models / Amazon / Nova Lite 1.0

Nova Lite 1.0 pricing and routing profile

Nova Lite 1.0 from Amazon lists at $0.06 per million input tokens and $0.24 per million output tokens, with a 300,000-token context window. Prices from OpenRouter's catalogue on 2026-09-28.

Input, per 1M tokens$0.06
Output, per 1M tokens$0.24
Context window300K
Confidence signalNot exposed

Tool calling

Cost per 1,000 requests

Request shapeList cost
Classification or routing (600 tokens in, 10 out)$0.0384
Chat reply (2,000 in, 400 out)$0.216
Retrieval-augmented answer (8,000 in, 500 out)$0.60

Before prompt caching. Try your own shape in the cost calculator.

Can Gimbix route to it first?

Not as a first-answer model through OpenRouter: no host returns token log probabilities for Nova Lite 1.0. It can still be the model Gimbix falls back to when a cheaper model is unsure.

Who serves Nova Lite 1.0

HostInput / output per 1MLog probabilitiesUptime, last 30 min
Amazon Bedrock$0.06 / $0.24no100.0%
Amazon Bedrock$0.06 / $0.24no100.0%

A host that lists log probabilities may still omit them; Gimbix checks each one before relying on it.

Cheaper models that can answer first

Models priced below Nova Lite 1.0 that expose a confidence signal. Whether they answer your traffic as well is what a Gimbix pilot measures.

ModelInput / output per 1MCheaper on a chat reply
Nemotron 3 Nano 30B A3B$0.05 / $0.2017%
Llama 3.1 8B Instruct$0.05 / $0.0839%
Qwen3.7 Flash$0.03 / $0.1348%
Granite 4.0 Micro$0.017 / $0.11264%
gpt-oss-20b$0.018 / $0.0967%
Ling 3.0 Flash$0.021 / $0.06369%

Compare Nova Lite 1.0

Questions

How much does Nova Lite 1.0 cost?

Nova Lite 1.0 lists at $0.06 per million input tokens and $0.24 per million output tokens on OpenRouter as of 2026-09-28. A typical chat reply of 2,000 input and 400 output tokens costs about $0.216 per 1,000 requests.

What is the context window of Nova Lite 1.0?

300,000 tokens.

Can a cheaper model replace Nova Lite 1.0?

Sometimes. Gimbix proves it on your own traffic before routing: the cheaper model must match Nova Lite 1.0 on one half of your requests and make at most three answers worse on the other.