ModelPriceWatch.com
Last scan 2026-08-09 Models tracked 198 Providers 30 Cheapest paid Granite 4.0 Micro $0.017/Mtok in Every price links to its source

Nova Micro

by Amazon

Current budget cheap tier

Today's price · per 1M tokens

Input

$0.035

per 1M tokens

Output

$0.140

per 1M tokens

Blended

$0.061

blended $/1M — 3:1 weighted input:output

Source: official Amazon pricing · read Jun 25, 2026 MODELPRICEWATCH.COM · 2026-08-09

Overview

Smallest, cheapest Nova model. $0.035/$0.14 per 1M tokens. Text only.

Capabilities

struck through = not supported
Input 1/5
Text ✓ Image Audio Video PDF
Output 1/5
Text ✓ Image Audio Video Embedding
Features 2/9
Prompt caching Reasoning Coding Fast inference ✓ Long context ✓ Open weights Multimodal Web search Realtime

Benchmark performance

accuracy % · higher is better
Avg benchmark score40%
Perf per $/Mtok653.1
GPQA Diamond
40%
SWE-Bench Verified vendor
10%
Humanity's Last Exam vendor
5%
ARC-AGI 2 vendor
4%
AIME 2025 vendor
20%
MMMLU vendor
62%
BFCL vendor
42%
HumanEval vendor
68%
MATH 500 vendor
42%
How it stacks up
  • Ranks #65 of 67 benchmarked models by average score
  • Ranks #138 of 150 comparably-measured models by percentile score, across 1 independent measurement
  • Ranks #32 of 150 comparably-tested models by normalized performance per dollar
  • Strongest at GPQA Diamond — 40%, #54 of 56

300 tokens/sec output 0.3s latency to first token (TTFT)

Source: Vellum LLM Leaderboard · updated Aug 9, 2026 · See full rankings →

Specifications

Provider
Amazon
Context window
128K tokens
Modality
text
Parameters
Proprietary
Open source
No — proprietary
Released
Dec 3, 2024
Status
Current
Last updated
Jun 25, 2026
Tags
budgetfast

Availability verified: Jul 25, 2026 — listed on Amazon's own page