NOUMENOpen app
NOUMEN

amazon · Efficient

Amazon Nova 2 Lite

Added Jan 1, 2024

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Use in the app

A fast, cost-effective reasoning model with 1M token context. Supports extended thinking with adjustable depth levels and built-in web grounding and code interpreter tools.

Input
Text
Output
Text
Discovery tier
Efficient

Pricing

USD per 1M tokens
Input
$0.51
Output
$4.25

Reference prices as published by the model provider. API example

Specifications

Context window
1M
Max output
65.5K

Side by side

Amazon Nova 2 Lite compared

Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Amazon Nova 2 LiteamazonThis modelAmazon Nova Lite 1.0amazonRemove
Provideramazonamazon
Discovery tierEfficientEfficient
AddedJan 1, 2024Dec 3, 2024
Limits
Context window1MBest300K
Max output65.54KBest5.12K
Average output—44 tokens
Pricing, USD per 1M tokens
Input$0.51$0.0595Best
Output$4.25$0.24Best
Benchmark indexes
Intelligence Index8.7Best6.7
Math Index33.7Best7.0
Capabilities
Reasoning effort——

Public evaluations

Benchmarks

Independent evaluation results, with how each score ranks among the models in the Noumen catalog.

  • Amazon Nova 2 Lite
  • Amazon Nova Lite 1.0

Intelligence Index

  • Amazon Nova 2 Lite8.7
  • Amazon Nova Lite 1.06.7

Amazon Nova 2 Lite: Better than 15% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Math Index

    Composite of the math evaluations

    • Amazon Nova 2 Lite: 33.7Top
    • Amazon Nova Lite 1.0: 7.0

Document reasoning

  • AA-LCRv1.1

    Reasoning across long documents

    • Amazon Nova 2 Lite: 18.7%
    • Amazon Nova Lite 1.0: 19.0%Top

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Amazon Nova 2 Lite: 2.9%
    • Amazon Nova Lite 1.0: 4.3%Top

  • GPQA Diamond

    Graduate-level science questions

    • Amazon Nova 2 Lite: 60.3%Top
    • Amazon Nova Lite 1.0: 43.3%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • Amazon Nova 2 Lite: 74.3%Top
    • Amazon Nova Lite 1.0: 59.0%

  • IFBench

    Following precise output instructions

    • Amazon Nova 2 Lite: 40.5%Top
    • Amazon Nova Lite 1.0: 34.1%

Coding

  • LiveCodeBench

    Recent competitive programming problems

    • Amazon Nova 2 Lite: 34.6%Top
    • Amazon Nova Lite 1.0: 16.7%

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • Amazon Nova 2 Lite: 33.7%Top
    • Amazon Nova Lite 1.0: 7.0%

  • AIME

    Competition mathematics

    • Amazon Nova 2 Lite: —
    • Amazon Nova Lite 1.0: 10.7%

  • MATH-500

    Competition math problems

    • Amazon Nova 2 Lite: —
    • Amazon Nova Lite 1.0: 76.5%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Amazon Nova 2 Lite: 6.8%Top
    • Amazon Nova Lite 1.0: 0.8%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Amazon Nova 2 Lite: 62.0%Top
    • Amazon Nova Lite 1.0: 17.5%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Amazon Nova 2 Lite: 18.7%
    • Amazon Nova Lite 1.0: 19.0%Top

Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis

Developers

Use it through the API

Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart
curl https://www.noumen.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $NOUMEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "amazon/nova-2-lite-v1",
    "messages": [{ "role": "user", "content": "Explain this stack trace." }]
  }'
import os
from openai import OpenAI

client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
    model="amazon/nova-2-lite-v1",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

amazon

Other amazon models, starting with the same family.