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 modelGemini 2.0 Pro 0205GoogleRemove
ProvideramazonGoogle
Discovery tierEfficientBalanced
AddedJan 1, 2024Feb 5, 2025
Limits
Context window1M2.1MBest
Max output65.54KBest8.19K
Pricing, USD per 1M tokens
Input$0.51Best$1.99
Output$4.25Best$7.96
Cache read—$0.50
Benchmark indexes
Intelligence Index8.78.7
Coding Index—25.5
Math Index33.7—
Capabilities
VisionNoYes
Audio inputNoYes
Reasoning effort——

Public evaluations

Benchmarks

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

  • Amazon Nova 2 Lite
  • Gemini 2.0 Pro 0205

Intelligence Index

  • Amazon Nova 2 Lite8.7
  • Gemini 2.0 Pro 02058.7

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

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Amazon Nova 2 Lite: —
    • Gemini 2.0 Pro 0205: 25.5

  • Math Index

    Composite of the math evaluations

    • Amazon Nova 2 Lite: 33.7
    • Gemini 2.0 Pro 0205: —

Document reasoning

  • AA-LCRv1.1

    Reasoning across long documents

    • Amazon Nova 2 Lite: 18.7%
    • Gemini 2.0 Pro 0205: —

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Amazon Nova 2 Lite: 2.9%
    • Gemini 2.0 Pro 0205: 6.2%Top

  • GPQA Diamond

    Graduate-level science questions

    • Amazon Nova 2 Lite: 60.3%
    • Gemini 2.0 Pro 0205: 62.2%Top

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • Amazon Nova 2 Lite: 74.3%
    • Gemini 2.0 Pro 0205: 80.5%Top

  • IFBench

    Following precise output instructions

    • Amazon Nova 2 Lite: 40.5%
    • Gemini 2.0 Pro 0205: —

Coding

  • LiveCodeBench

    Recent competitive programming problems

    • Amazon Nova 2 Lite: 34.6%
    • Gemini 2.0 Pro 0205: 34.7%Top

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • Amazon Nova 2 Lite: 33.7%
    • Gemini 2.0 Pro 0205: —

  • AIME

    Competition mathematics

    • Amazon Nova 2 Lite: —
    • Gemini 2.0 Pro 0205: 36.0%

  • MATH-500

    Competition math problems

    • Amazon Nova 2 Lite: —
    • Gemini 2.0 Pro 0205: 92.3%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Amazon Nova 2 Lite: 6.8%
    • Gemini 2.0 Pro 0205: —

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Amazon Nova 2 Lite: 62.0%
    • Gemini 2.0 Pro 0205: —

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Amazon Nova 2 Lite: 18.7%
    • Gemini 2.0 Pro 0205: —

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.