---
title: "Nova Lite — LLM-TEST.com"
url: /models/nova-lite/
canonical_url: https://llm-test.com/models/nova-lite/
language: en
type: model
summary: "A fast, very low-cost multimodal model for high-volume Bedrock workloads where Nova Pro would be overkill."
last_updated: "2026-11-05"
---

# Nova Lite

_Amazon · Balanced_

A fast, very low-cost multimodal model for high-volume Bedrock workloads where Nova Pro would be overkill.

## At a glance

- Released: Apr 22, 2026
- Provider: Amazon
- Context window: 300,000 tokens
- Max output: 16,000 tokens
- Modalities: Text + image + video → text
- Knowledge cutoff: February 2026
- API model ID: `nova-lite-v1`
- License: Proprietary (API-only via AWS Bedrock)

## Pricing

- Standard: $0.06 input / $0.24 output per 1M tokens
- Batch: $0.03 input / $0.12 output per 1M tokens
- Example: a 1,500-token prompt + 650-token answer ≈ $0.0002 (standard)

## What's new vs Nova Lite (2024) (December 2024)

- Better instruction following and multimodal grounding
- Lower latency at scale
- Still noticeably weaker than Nova Pro on complex reasoning

## Best use cases

- **High-volume classification** — Routes, tags, and triages large request streams at minimal per-call cost.
- **Chat assistants** — Powers responsive customer-facing assistants with image understanding.
- **Content summarization** — Condenses long documents and transcripts quickly and cheaply.

## Strengths

- Very cheap
- Low latency
- Multimodal input

## Limitations

- Limited depth on hard reasoning
- API-only

## Where to get access

- API: the Amazon Bedrock console — https://console.aws.amazon.com/bedrock
- Also available: Amazon Bedrock only
- Docs: https://docs.aws.amazon.com/bedrock

Full comparison and live pricing: https://llm-test.com/ · directory: https://llm-test.com/models/