Home / Models / Amazon / Nova Micro 1.0

Nova Micro 1.0 pricing and routing profile

Nova Micro 1.0 from Amazon lists at $0.035 per million input tokens and $0.14 per million output tokens, with a 128,000-token context window. Prices from OpenRouter's catalogue on 2026-09-28.

Input, per 1M tokens$0.035
Output, per 1M tokens$0.14
Context window128K
Confidence signalNot exposed

Tool calling

Cost per 1,000 requests

Request shapeList cost
Classification or routing (600 tokens in, 10 out)$0.0224
Chat reply (2,000 in, 400 out)$0.126
Retrieval-augmented answer (8,000 in, 500 out)$0.35

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 Micro 1.0. It can still be the model Gimbix falls back to when a cheaper model is unsure.

Who serves Nova Micro 1.0

HostInput / output per 1MLog probabilitiesUptime, last 30 min
Amazon Bedrock$0.035 / $0.14no20.8%
Amazon Bedrock$0.035 / $0.14no100.0%

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 Micro 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
Qwen3.7 Flash$0.03 / $0.1311%
Granite 4.0 Micro$0.017 / $0.11237%
gpt-oss-20b$0.018 / $0.0943%
Ling 3.0 Flash$0.021 / $0.06347%
Ling 3.0 Flash VL$0.021 / $0.061647%
Mistral Nemo$0.019 / $0.0360%

Compare Nova Micro 1.0

Questions

How much does Nova Micro 1.0 cost?

Nova Micro 1.0 lists at $0.035 per million input tokens and $0.14 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 $0.126 per 1,000 requests.

What is the context window of Nova Micro 1.0?

128,000 tokens.

Can a cheaper model replace Nova Micro 1.0?

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