Ctrl K
Back to models

Amazon

Nova Premier

  • Released
  • Closed weights
Compare
Intelligence Index

Standard setting

9.2
Estimated · Artificial Analysis v4.3.2
API price from
$2.50 in / $12.50 out / 1M tokOpenRouter · Amazon Bedrock
Context window
1M tok

Performance profile

ReasoningRank #90 of 107
56.9%
GPQA Diamond

Capabilities

Context window

Modalities

Measured setting

Integration

Reasoning trade-offs

Source (opens in a new tab)
Intelligence Index v4.3.2
StandardEstimated
Intelligence Index
9.2

Pricing & access

API route
OpenRouter · Amazon BedrockAPI
Tier & contextStandard

USD per 1M tokens

Input
$2.50
Output
$12.50
Cached input
$0.625

Benchmarks

Full leaderboardSource (opens in a new tab)

Humanity’s Last Exam

Frontier reasoning

Nova Premier · Standard#121 of 126

  1. 1Claude Opus 5.5Max61.4%
  2. 2Claude Fable 5.1Max59.1%
  3. 3Gemini 4 ArgonHigh57.1%
  5. 118Phi-4 Mini InstructStandard4.5%
  6. 119Reka Flash 3Reasoning4.4%
  7. 120Ministral 3 8BStandard4.3%
  8. 121Nova PremierStandard4.2%
  9. 122Command AStandard4.0%
  10. 123Granite 4.0 H SmallStandard3.8%
  11. 124Llama 4 ScoutStandard3.8%

Peers use their best measured result on this benchmark.