Amazon
Efficient

Nova Micro

Micro

Cheapest, fastest Nova, text-only model targeting bulk classification and routing inside Bedrock.

Nova Micro is a efficient AI model from Amazon. It costs $0.0350 per million input tokens and $0.1400 per million output tokens (blended $0.0665/M), with a 128,000-token context window.

RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.

INPUT
$0.0350/M
per million input tokens
OUTPUT
$0.1400/M
per million output tokens
BLENDED 70/30
$0.0665/M
unchanged since 3 May
CONTEXT
128,000
tokens

Hand-maintained from Amazon's published pricing; no check date on record.

What it is good at
  • Lowest Nova price
  • Sub-second latency
  • Bedrock-native
Typical use cases
  • Routing & classification
  • Bulk summarisation

Benchmarks

vs. best public score
MMLU77.6%
Multitask academic knowledge across 57 subjects. Source: Amazon (self-reported), MMLU, read 2026-11-10.
HumanEval81.1%
Python function synthesis from docstrings. Source: Amazon (self-reported), HumanEval (0-shot pass@1), read 2026-11-10.
LMArena Elo1241 Elo
Crowd-sourced head-to-head preference Elo rating. Source: LMArena (independent), LMArena Text Arena score, read 2026-11-10.
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources, treat as directional rather than authoritative.

More from Amazon

See all 10 →

Frequently asked questions

How much does Nova Micro cost?

Nova Micro costs $0.0350 per million input tokens and $0.1400 per million output tokens, for a blended reference rate of $0.0665 per million tokens.

What is Nova Micro's context window?

Nova Micro supports up to 128,000 tokens of context in a single request.

What is Nova Micro best for?

Nova Micro is well suited to Lowest Nova price, Sub-second latency and Bedrock-native.

Who makes Nova Micro?

Nova Micro is developed and served by Amazon.

Terms used on this page