Skip to contentT/TTokens or Towers

Compare

LeaderboardEvery tracked model, ranked and priced side by sideBenchmarksWhat each test measures and who leads itPricesAPI, media, and hardware rates with a cost calculator

Plan

Stack plannerSix questions to a priced local and hosted stackShortlistOur picks for subscriptions, APIs, and hardwareEnterpriseSeat plans against self-hosting for a whole team

Build

HardwareGPUs and workstations, and which models they fitHostsWhere to rent open-weight inference, and for how muchHarnessesCoding agents and the models they drive

Lab

FindingsResults from our own evaluationsScanAudit a repo’s AI usage in the browserMethodWhere the numbers come from and how we check them
Data checked September 25, 2026
Data checked September 25, 2026
Plan a stack
T/TTokens or Towers

An independent guide to AI models, what they cost, and the hardware to run them. No account, no API key, no sponsors.

Compare

  • Leaderboard
  • Benchmarks
  • Prices

Plan

  • Stack planner
  • Shortlist
  • Enterprise

Build

  • Hardware
  • Hosts
  • Harnesses

Lab

  • Findings
  • Scan
  • Method
Data checked September 25, 2026 · Every number links to its sourceRSS · Source on GitHub
Leaderboard/Amazon
Amazon

Amazon · Nova

Amazon Nova Pro

Closed weightsSupersededproprietary

First-generation Nova multimodal Pro tier, superseded by Nova 2 Lite/Pro but still sold on Bedrock.

AA Intelligence
7#123 of 142
Input / output per 1M
$0.80/ $3.20
Output speed
—
Context window
300K tokens

Composite indexes

  • Artificial Analysis Intelligence Index#123 of 142
    7independentIntelligence Index v4.3; non-reasoning; estimatedArtificial Analysis: Nova Pro ↗

    Leader: Claude Opus 5.5 at 58

Coding

  • LiveCodeBench#48 of 56
    23.3%independentnon-reasoningArtificial Analysis: Nova Pro ↗

    Leader: Fugu at 92.9%

Agents and tool use

  • τ²-Bench#75 of 88
    14%independenttelecom; non-reasoningArtificial Analysis: Nova Pro ↗

    Leader: GLM-5.2 at 99.1%

Reasoning and knowledge

  • GPQA Diamond#126 of 142
    49.9%independentnon-reasoningArtificial Analysis: Nova Pro ↗

    Leader: GPT-6 Astra at 96.1%

  • Humanity’s Last Exam#147 of 147
    3.2%independentno tools; non-reasoningArtificial Analysis: Nova Pro ↗

    Leader: Claude Opus 5.5 at 61.4%

  • CritPt#118 of 139
    0%independentnon-reasoningArtificial Analysis: Nova Pro ↗

    Leader: GPT-5.6 Sol at 32.3%

Vision and long context

  • AA Long Context Reasoning#115 of 139
    21%independentnon-reasoningArtificial Analysis: Nova Pro ↗

    Leader: Kimi K3 at 88.7%

  • MMMU-Pro#68 of 72
    44.3%independentnon-reasoningArtificial Analysis: Nova Pro ↗

    Leader: Claude Opus 5.5 at 87.7%

Other published results

ResultScoreReported bySource
aime-2025 · AIME 2025; non-reasoning7%independentArtificial Analysis: Nova Pro ↗
Terminal-Bench Hard (AA) · non-reasoning6.1%independentArtificial Analysis: Nova Pro ↗
IFBench · non-reasoning38.1%independentArtificial Analysis: Nova Pro ↗
AA-Omniscience Index · non-reasoning-47.7 indexindependentArtificial Analysis: Nova Pro ↗

Specs

Released
December 3, 2024
Parameters
Undisclosed
Size class
Undisclosed
Input
text, image, video
Output
text
Context
300K tokens
Max output
Not published
Cached input
$0.20 / 1M
Blended 70/30
$1.52 / 1M
  • Price: Amazon Bedrock pricing ↗ Bedrock on-demand rate; cache read $0.20/M. Still sold, but Artificial Analysis marks it deprecated in favor of Nova 2.

Will it fit your budget?

The planner prices this model against local hardware and other APIs for your workload.

Plan a stack →

Compare with

  • CohereCommand A7
  • Ai2Olmo 3.1 32B Think7.1
  • Liquid AILFM2.5-8B-A1B7.2
  • AmazonAmazon Nova Lite6.7