amazon

Amazon: Nova Micro 1.0

Nova Micro 1.0 is a text-only model from Amazon with a 128,000-token context window and a 5,120-token output cap. It supports tool use but does not offer reasoning mode, and structured output support is unconfirmed. Because it accepts only text input, use cases involving images, audio, or documents will require a different model. At $0.035 per million input tokens and $0.14 per million output tokens, it sits at the cheaper end of the market, making it worth considering for high-volume text tasks like summarization, classification, or simple tool-calling pipelines where cost control matters. The tradeoff is uncertainty: there is currently no independent benchmark coverage, so quality comparisons against competing models at similar price points cannot be made from public data. Buyers who need validated performance before committing should treat it as unproven until that coverage appears.

Quality Score
80/100
price + capability + benchmarks
Input Price
$0.04
per 1M tokens
Output Price
$0.14
per 1M tokens
Context Window
128,000
tokens
Model ID
amazon/nova-micro-v1
Vendor
amazon
Released
December 2024
Tokenizer
Nova
Input Modalities
text
Output Modalities
text
Max Output
5,120 tokens
Tool Calling
✓ supported
Structured Output
not supported
Reasoning Mode
not supported
Vision
text only
Audio
no
Moderated
yes

What it costs in practice

Computed from the current $0.04/M input and $0.14/M output rates. Run your own numbers →

JobTokensCost
Summarize a 50-page report 30k in / 1.5k out under $0.01
Classify 1,000 customer emails 500k in / 50k out $0.02
A month of a busy support chatbot 5M in / 2M out $0.46

Similar models

Quick answers

How much does Amazon: Nova Micro 1.0 cost?
$0.04 per million input tokens and $0.14 per million output tokens.
What is Amazon: Nova Micro 1.0's context window?
128,000 tokens, roughly 192 pages of text in a single request.
Does Amazon: Nova Micro 1.0 support tool calling?
It supports tool calling.
Can Amazon: Nova Micro 1.0 process images?
No, it is text-only on the input side.