Skip to content

Amazon · Chat

Nova 2 Lite

Amazon 🇺🇸ChatNova familyOne of its sources says the weights aren't publicly available.
From Empiriolabs's listing:
Fast, cost-effective multimodal reasoning model for text, images, documents, and video on a 1M context (long docs and ~90 min clips).
llminfo IQ
112.6
Maker's price
$0.85 blended / 1M
Max context
1M
Listings
25

Evidence and sources

llminfo IQ 112.6, ranked among chat models. From 78 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 94.4, 95% interval 53–136. From 5 benchmark families across 3 sources. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.How Coding IQ is computedPoor value (38.2). Costs more per task than its benchmark results predict. From 1 benchmark with measured task costs. Little data behind it, so treat it as a rough estimate.How Value for money worksReleased 2 Dec 2025Maker HQ: US (according to Amazon Web Services's own website)
All rankings: #26 in Google Trends interest this week #228 on OpenRouter this week #276 on OpenRouter this month #334 on OpenRouter today #456 on NanoGPT recentlyAll rankings: #26 in Google Trends interest this week #228 on OpenRouter this week #276 on OpenRouter this month #334 on OpenRouter today #456 on NanoGPT recentlySources: LMArena data, AWS Bedrock Runtime data, EmpirioLabs data, Models.dev data, llminfo researchPrimary data from LMArena from AWS Bedrock Runtime: name from EmpirioLabs: primary mode, description from Models.dev: weights availability from llminfo research: release date
Tags from its sources:instructtoolsvisionreasoningdocumentproprietarymultimodalvideolong-contextprompt-caching

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Trade-offs

No open weights

The weights aren't public, so you can't run it yourself.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 9 maker's prices; 1 market median price.

Input & output

as stated by the model's providers
Text
Images
Video
Files
Text

Capabilities

Supported operations and provider-stated features

VisionReasoningFunction callingStructured outputPrompt cachingPDF inputBatch API

Listings

 Amazon Web Servicesamazon.nova-2-lite-v1:0Sources: AWS Bedrock Runtime data, LiteLLM data, Models.dev data1M$0.30cache read $0.075batch $0.15$2.50batch $1.25——
 Flowdotamazon/nova-2-lite-v1Source: FlowDot data1M$0.30$2.50——
 Kiloamazon/nova-2-lite-v1Sources: Kilo AI Gateway data, Models.dev data1M$0.30$2.50——
 Nous Portalamazon/nova-2-lite-v1Source: Nous Portal Inference Gateway data1M$0.30$2.50——
 OpenRouterInference by Amazon Web Servicesamazon/nova-2-lite-v1 · eu-west-1Source: OpenRouter data docs1M$0.30$2.50121665ms
 Vercelamazon/nova-2-liteSources: Models.dev data, Vercel AI Gateway data1M$0.33cache read $0.0825$2.75——
 HerokuRegions: 🇺🇸 usnova-2-liteSources: Heroku Managed Inference data, Heroku Managed Inference PricingNot published by the provider$0.33$2.75——
 Neosantaraamazon-nova-2-liteSource: Neosantara Inference data1M$0.33cache read $0.0825$2.75cache write $0.33——
 Cortecs AInova-2-liteSources: Cortecs EU Router data, Models.dev data1M——
 Empiriolabsnova-lite-2Sources: EmpirioLabs data, LiteLLM data1M$0.38cache read $0.2128$3.16——
Show all 20 listings

Showing 10 of 20: the maker's own listing first, then the cheapest per 1M input tokens from each provider.

Also sold by Eurouter, NanoGPT.

5 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Human preference

Arena ELO42 related benchmarks · 42 results

Coding

Reported by Amazon Web Services, Amazon AGI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Amazon Nova 2 Lite official launch chart / technical report · high reasoning · 2024-07-01 through 2025-01-01, v1
Reported by Amazon AGI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Reasoning effort · Amazon Nova 2 technical report · 2024-07-01 through 2025-01-01, v1
Amazon Nova 2 technical report · reasoning disabled · 2024-07-01 through 2025-01-01, v1
Reported by Amazon Web Services, Amazon AGI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Amazon Nova 2 Lite official launch chart / technical report · inference-time scaling · internal agentic scaffold, v1
Reported by Amazon AGI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Amazon Nova 2 technical report · standard inference, v1
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Agentic

BFCL-V42 results
Reported by Amazon Web Services, Amazon AGI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Amazon Nova 2 Lite official launch chart / technical report · Overall FC, v1
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
MCP Atlas2 results
Reported by Amazon Web Services, Amazon AGI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Amazon Nova 2 Lite official launch chart / technical report · blind evaluation · pass rate, v1
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Tau2Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Vision

MMMU-Pro2 results
Reported by Amazon Web Services, Amazon AGI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Amazon Nova 2 Lite official launch chart / technical report · accuracy, v1
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
QVHighlights2 results
Reported by Amazon Web Services, Amazon AGI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Amazon Nova 2 Lite official launch chart / technical report · R@1 · IoU 0.5, v1
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
ScreenSpot2 results
Reported by Amazon Web Services, Amazon AGI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Amazon Nova 2 Lite official launch chart / technical report · point accuracy, v1
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Instruction following

IFBench2 results
Reported by Amazon Web Services, Amazon AGI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Amazon Nova 2 Lite official launch chart / technical report · prompt-loose accuracy, v1
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Reported by Amazon Web Services, Amazon AGI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Amazon Nova 2 Lite official launch chart / technical report · accuracy, v1
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Math

AIME 20252 results
Reported by Amazon Web Services, Amazon AGI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Amazon Nova 2 Lite official launch chart / technical report · accuracy, v1
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Knowledge

MMLU-Pro2 results
Reported by Amazon Web Services, Amazon AGI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Amazon Nova 2 Lite official launch chart / technical report · accuracy, v1
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

OCR

OCRBench_V22 results
Reported by Amazon Web Services, Amazon AGI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Amazon Nova 2 Lite official launch chart / technical report · average accuracy, v1
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Science

GPQASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Other

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links. · Data by LLM Stats · LMArena, CC BY 4.0 (licence) · EQ-Bench (Samuel J. Paech) — cite paech2023eqbench

Also known as: amazon-nova-2-lite, amazon.nova-2-lite-v1:0, amazon.nova-2-lite-v1:0:256k, amazon/nova-2-lite, amazon/nova-2-lite-v1, apac.amazon.nova-2-lite-v1:0, bedrock/ap-east-2/global.amazon.nova-2-lite-v1:0, bedrock/ap-northeast-1/amazon.nova-2-lite-v1:0, bedrock/ap-northeast-1/global.amazon.nova-2-lite-v1:0, bedrock/ap-northeast-2/global.amazon.nova-2-lite-v1:0, bedrock/ap-south-1/global.amazon.nova-2-lite-v1:0, bedrock/ap-southeast-1/global.amazon.nova-2-lite-v1:0, bedrock/ap-southeast-2/global.amazon.nova-2-lite-v1:0, bedrock/ap-southeast-3/global.amazon.nova-2-lite-v1:0, bedrock/ap-southeast-4/global.amazon.nova-2-lite-v1:0, bedrock/ap-southeast-5/global.amazon.nova-2-lite-v1:0, bedrock/ap-southeast-6/global.amazon.nova-2-lite-v1:0, bedrock/ap-southeast-7/global.amazon.nova-2-lite-v1:0, bedrock/ca-central-1/amazon.nova-2-lite-v1:0, bedrock/ca-central-1/global.amazon.nova-2-lite-v1:0, bedrock/ca-west-1/amazon.nova-2-lite-v1:0, bedrock/ca-west-1/global.amazon.nova-2-lite-v1:0, bedrock/eu-central-1/amazon.nova-2-lite-v1:0, bedrock/eu-central-1/global.amazon.nova-2-lite-v1:0, bedrock/eu-north-1/amazon.nova-2-lite-v1:0, bedrock/eu-north-1/eu.amazon.nova-2-lite-v1:0, bedrock/eu-north-1/global.amazon.nova-2-lite-v1:0, bedrock/eu-south-1/amazon.nova-2-lite-v1:0, bedrock/eu-south-1/eu.amazon.nova-2-lite-v1:0, bedrock/eu-south-1/global.amazon.nova-2-lite-v1:0, bedrock/eu-south-2/amazon.nova-2-lite-v1:0, bedrock/eu-south-2/eu.amazon.nova-2-lite-v1:0, bedrock/eu-south-2/global.amazon.nova-2-lite-v1:0, bedrock/eu-west-1/amazon.nova-2-lite-v1:0, bedrock/eu-west-1/eu.amazon.nova-2-lite-v1:0, bedrock/eu-west-1/global.amazon.nova-2-lite-v1:0, bedrock/eu-west-2/global.amazon.nova-2-lite-v1:0, bedrock/eu-west-3/amazon.nova-2-lite-v1:0, bedrock/eu-west-3/eu.amazon.nova-2-lite-v1:0, bedrock/eu-west-3/global.amazon.nova-2-lite-v1:0, bedrock/il-central-1/global.amazon.nova-2-lite-v1:0, bedrock/us-east-1/amazon.nova-2-lite-v1:0, bedrock/us-east-2/amazon.nova-2-lite-v1:0, bedrock/us-west-1/amazon.nova-2-lite-v1:0, bedrock/us-west-1/global.amazon.nova-2-lite-v1:0, bedrock/us-west-1/us.amazon.nova-2-lite-v1:0, bedrock/us-west-2/amazon.nova-2-lite-v1:0, empiriolabs/nova-lite-2, eu.amazon.nova-2-lite-v1:0, global.amazon.nova-2-lite-v1:0, jp.amazon.nova-2-lite-v1:0, nova-2-lite-v1, nova-lite-2, regional.amazon.nova-2-lite-v1:0, us.amazon.nova-2-lite-v1:0

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works