Claude Fable 5$22.000/MClaude Opus 4.8$11.000/MClaude Opus 4.7$11.000/MClaude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5.5$12.500/MGPT-5.2$5.425/MGPT-5.2-Codex$5.425/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 3.5 Pro$5.000/MGemini 3.1 Pro$5.000/MGemini 3 Pro$5.000/MGemini 2.5 Pro$3.875/MGemini 1.5 Pro$2.375/MGemini 1.0 Ultra$12.000/MGemini 1.0 Pro$0.800/MClaude Fable 5$22.000/MClaude Opus 4.8$11.000/MClaude Opus 4.7$11.000/MClaude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5.5$12.500/MGPT-5.2$5.425/MGPT-5.2-Codex$5.425/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 3.5 Pro$5.000/MGemini 3.1 Pro$5.000/MGemini 3 Pro$5.000/MGemini 2.5 Pro$3.875/MGemini 1.5 Pro$2.375/MGemini 1.0 Ultra$12.000/MGemini 1.0 Pro$0.800/M
BETA
Subscribe
← Back to Index·All Amazon models
Amazon
AmazonEfficient

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 $0.035 per million input tokens and $0.140 per million output tokens (blended $0.067/M), with a 128K-token context window.

Modalities textOfficial model page ↗Provider pricing ↗API docs ↗Compare with another model →Estimate monthly cost →
INPUT
$0.035/M
per million input tokens
OUTPUT
$0.140/M
per million output tokens
BLENDED 70/30
$0.067/M
default reference rate · how it's calculated →
CONTEXT
128K
128,000 tokens
What it's good at
  • Lowest Nova price
  • Sub-second latency
  • Bedrock-native
Typical use cases
  • Routing & classification
  • Bulk summarisation
Benchmarks
vs. best public score
MMLU67%
Multitask academic knowledge across 57 subjects.
HumanEval64%
Python function synthesis from docstrings.
LMArena Elo1138 Elo
Crowd-sourced head-to-head preference Elo rating.
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 →
Nova 2 Pro
Frontier · 1M ctx
in $0.800/Mout $3.200/M
Nova 2 Lite
Efficient · 1M ctx
in $0.300/Mout $2.500/M
Nova Premier
Top-tier · 300K ctx
in $2.500/Mout $12.500/M
Nova Pro
Frontier · 300K ctx
in $0.800/Mout $3.200/M
Nova Lite
Efficient · 300K ctx
in $0.060/Mout $0.240/M
Nova Canvas
Image Gen · — ctx
in $0.080/M
Frequently asked questions

How much does Nova Micro cost?

Nova Micro costs $0.035 per million input tokens and $0.140 per million output tokens, for a blended reference rate of $0.067 per million tokens.

What is Nova Micro's context window?

Nova Micro supports up to 128K tokens of context (128,000 tokens).

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.