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 Lite

Closed weightsSupersededproprietary

First-generation low-cost multimodal Nova model, superseded by Nova 2 Lite.

AA Intelligence
6.7#125 of 142
Input / output per 1M
$0.06/ $0.24
Output speed
168tok/s
Context window
300K tokens

Composite indexes

  • Artificial Analysis Intelligence Index#125 of 142
    7independentIntelligence Index v4.3; non-reasoning; estimatedArtificial Analysis: Nova Lite ↗

    Leader: Claude Opus 5.5 at 58

Coding

  • LiveCodeBench#52 of 56
    16.7%independentnon-reasoningArtificial Analysis: Nova Lite ↗

    Leader: Fugu at 92.9%

Agents and tool use

  • τ²-Bench#69 of 88
    17.5%independenttelecom; non-reasoningArtificial Analysis: Nova Lite ↗

    Leader: GLM-5.2 at 99.1%

Reasoning and knowledge

  • GPQA Diamond#132 of 142
    43.3%independentnon-reasoningArtificial Analysis: Nova Lite ↗

    Leader: GPT-6 Astra at 96.1%

  • Humanity’s Last Exam#134 of 147
    4.3%independentno tools; non-reasoningArtificial Analysis: Nova Lite ↗

    Leader: Claude Opus 5.5 at 61.4%

  • CritPt#119 of 139
    0%independentnon-reasoningArtificial Analysis: Nova Lite ↗

    Leader: GPT-5.6 Sol at 32.3%

Vision and long context

  • AA Long Context Reasoning#118 of 139
    19%independentnon-reasoningArtificial Analysis: Nova Lite ↗

    Leader: Kimi K3 at 88.7%

  • MMMU-Pro#70 of 72
    37.8%independentnon-reasoningArtificial Analysis: Nova Lite ↗

    Leader: Claude Opus 5.5 at 87.7%

Other published results

ResultScoreReported bySource
aime-2025 · AIME 2025; non-reasoning7%independentArtificial Analysis: Nova Lite ↗
Terminal-Bench Hard (AA) · non-reasoning0.8%independentArtificial Analysis: Nova Lite ↗
IFBench · non-reasoning34.1%independentArtificial Analysis: Nova Lite ↗
AA-Omniscience Index · non-reasoning-42.2 indexindependentArtificial Analysis: Nova Lite ↗

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
$0.015 / 1M
Blended 70/30
$0.114 / 1M
First token
0.95s
  • Price: Amazon Bedrock pricing ↗ Bedrock on-demand rate; cache read $0.015/M.
  • Speed: Artificial Analysis leaderboard (Nova Lite, median across providers or first-party as shown) ↗

Will it fit your budget?

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

Plan a stack →

Compare with

  • Ai2Olmo 3.1 32B Instruct6.5
  • AmazonAmazon Nova Pro7
  • CohereCommand A7
  • Ai2Olmo 3.1 32B Think7.1