Nova Lite
Nova Lite brings multimodal understanding of text, images, and up to 30 minutes of video to a context of 300K tokens at low per-token rates, making vision-enabled production pipelines practical at scale.
import { streamText } from 'ai'
const result = streamText({ model: 'amazon/nova-lite', prompt: 'Why is the sky blue?'})Playground
Try out Nova Lite by Amazon. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.
Providers
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
More models by Amazon
| Model |
|---|
| 300K | 0.4s | 135tps | $0.80/M | $3.20/M | — | — |  | 12/03/2024 | |||||
| 1M | 0.4s | 218tps | $0.30/M | $2.50/M | Read:$0.07/M Write:— | — | — | | 12/01/2024 | ||||
| $0.02/M | — | — | | 04/01/2024 | |||||||||
| 128K | 0.3s | $0.04/M | $0.14/M | — | — | |
About Nova Lite
Nova Lite launched on December 3, 2024 as the budget multimodal option in Amazon's first-generation Nova family. Its defining trait is breadth of input. Text, images, and video (up to 30 minutes per request) all flow into a single context window of 300K tokens. No other model in the original Nova lineup combines that input flexibility with comparable pricing.
Video is the headline capability. A compliance team can feed in an entire training session recording and get a structured summary. A media company can batch-process hours of lecture footage overnight. A customer support platform can accept screen recordings from users and extract the relevant issue automatically. These workflows become economically viable because Nova Lite treats video as a first-class input modality at a cost tier built for volume, not occasional use.
Images receive the same treatment. Multiple images can accompany text in a single prompt. This enables side-by-side document comparison, multi-page form extraction, product catalog enrichment, and UI screenshot analysis. The model is tuned for fast, cost-efficient classification and extraction from visual inputs rather than deep analytical reasoning. That tradeoff is deliberate. It keeps latency low and throughput high for the batch-oriented pipelines where Nova Lite excels.
What To Consider When Choosing a Provider
- Configuration: Spikes hurt less than on premium tiers. AI Gateway retries and routes traffic so you don't hand-tune failover when load jumps.
- Zero Data Retention: AI Gateway supports Zero Data Retention for this model via direct gateway requests (BYOK is not included). To configure this, check the documentation.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
When to Use Nova Lite
Best For
- Long video summarization: Meetings, lectures, and webinars using the 30-minute video input capacity
- Batch image classification: Throughput and cost matter more than nuanced reasoning for visual extraction workloads
- Content moderation pipelines: Evaluate both text and visual media at high volume
- Customer-facing media uploads: Accept image or video uploads without incurring premium per-token costs
Consider Alternatives When
- Purely text-based workloads: Nova Micro costs less and responds faster for text-only tasks
- Multi-step reasoning needed: Nova 2 Lite adds extended thinking and agentic tool use capabilities
- High-accuracy structured documents: Nova Pro is tuned for precision on financial or legal documents
Conclusion
Nova Lite keeps multimodal inputs affordable at scale. Image and video stay in budget for batch and customer-facing flows. If you need visual understanding without deep reasoning, it's a sensible default.
Frequently Asked Questions
How much video can Nova Lite handle in a single request?
Up to 30 minutes of video content per request, processed within the context window of 300K tokens. This covers most meeting recordings, lecture segments, and training videos without splitting.
What visual tasks is Nova Lite well suited for?
Extraction and classification tasks. Examples include pulling structured data from screenshots, categorizing product photos, reading forms and receipts, and flagging content in moderation pipelines. It's optimized for speed and volume rather than complex visual reasoning.
Can I mix images and text in the same prompt?
Yes. Nova Lite accepts multiple images alongside text within a single request, which is useful for comparing two documents side by side, processing multi-page forms, or enriching product listings with photo analysis.
Does Nova Lite produce any visual output?
No. Nova Lite generates text output only. It analyzes visual inputs but does not create them.
How does the pricing compare to other multimodal models in the Nova family?
Current pricing is shown on this page. AI Gateway routes across providers, and rates may vary by provider.
What is the tradeoff compared to Nova Pro for image analysis?
Nova Lite prioritizes throughput and cost; Nova Pro prioritizes accuracy. If your images contain dense tables, fine-print legal text, or complex diagrams requiring precise interpretation, Pro produces more reliable results. For routine classification and extraction, Lite is the more efficient choice.