Skip to content
Dhanasvi
Sign inExplore
Nova Lite 1.0 logo

Nova Lite 1.0

Verified

Amazon's multimodal model for text and image processing with 300k context.

AmazonMultimodalClosed
Vision
Model page
Updated 2026-06-15

About Nova Lite 1.0

Nova Lite 1.0 uses a multimodal design that accepts both text and image data. Its 300,000-token context window supports lengthy combined inputs. As a proprietary model from Amazon, it is accessed only through hosted services rather than local weights.

The architecture prioritizes efficient handling of visual and textual information together. This enables coherent analysis across extended documents and associated images. Typical usage involves API calls for tasks that require synchronized understanding of both modalities.

Capabilities

Long-context reasoning
Multimodal text-image analysis
Vision understanding
Text generation and summarization
Contextual information extraction

How Nova Lite 1.0 compares

Nova Lite 1.0 (striped bar) vs other multimodal on intelligence, speed and price.

Price

USD per 1M output tokens · Lower is better · Nova Lite 1.0 ranks #12 of 155

$0.15
Gemma 3 12B
$0.16
Gemma 3 27B
$0.18
Llama Guard 4 12B
$0.20
Ministral 3 14B 2512
$0.20
Mistral Small 3.2 24B
$0.20
UI-TARS 7B
$0.24
Nova Lite 1.0
$0.26
Qwen3.5-Flash
$0.28
MiMo-V2.5
$0.30
Llama 4 Scout
$0.30
Seed 1.6 Flash
$0.30
Voxtral Small 24B 2507
$0.33
Gemma 4 26B A4B

Sources: Artificial Analysis (intelligence, speed) · OpenRouter (price).

Best for

Processing extensive multimodal documents

This model excels at long-context reasoning over 300,000 tokens combined with text-image analysis for tasks like reviewing large reports containing both text and visuals.

Vision-based information extraction

It performs contextual information extraction from images and surrounding text, ideal for analyzing infographics or illustrated guides within extended contexts.

Summarizing complex multimodal content

The model generates accurate summaries and performs text generation from lengthy inputs that include visual elements, leveraging its vision understanding capabilities.

Strengths & limitations

Strengths

  • +Very large 300k token context window
  • +Efficient multimodal processing
  • +Fast inference suitable for high-volume use

Limitations

  • –Lite model may trade depth for speed on complex tasks
  • –Supports only text and image modalities
  • –Less suited for highly specialized or creative domains

Cost calculator

Estimate what Nova Lite 1.0 would cost for your usage.

$0.00018
per request
$1.8
estimated / month

Based on Nova Lite 1.0's $0.06/1M input · $0.24/1M output. Estimate only — actual cost varies by provider and caching.

Quick start

OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. Only the model slug changes between models.

JavaScript · openai
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://openrouter.ai/api/v1",
  apiKey: process.env.OPENROUTER_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "amazon/nova-lite-v1",
  messages: [{ role: "user", content: "Hello!" }],
});

console.log(completion.choices[0].message.content);

Model slug: amazon/nova-lite-v1

Editor's verdict

Our take on Nova Lite 1.0

Nova Lite 1.0 is Amazon's proprietary multimodal with a 300K-token context window.

At $0.24 per 1M output tokens, it is very cost-efficient for its class.

It is available through Amazon's API and aggregators like OpenRouter.

Best suited to very large 300k token context window and efficient multimodal processing.

Did you find this helpful?

Frequently asked questions

Nova Lite 1.0 supports a context window of 300,000 tokens.

User reviews

Real, verified reviews from the community shape this model's rating.

Loading reviews…

Sign in to review

Other Nova models

Sibling versions in the Nova family from Amazon.

Promote Nova Lite 1.0

Add this badge to your website, or share the tool.

DFeatured on DhanasviNova Lite 1.0 1