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.
View API reference- Input and output price
- Input $0.06, Output $0.24, Per 1M tokens
- 24h uptime
- Loading AI Gateway uptime
import { streamText } from 'ai'
const result = streamText({ model: 'amazon/nova-lite', prompt: 'Why is the sky blue?'})Copy link to headingPlayground
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.
Nova Lite
Copy link to headingProviders
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.
| Provider |
|---|
Copy link to headingUptime24 hours
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
Copy link to headingThroughput24 hours
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
Copy link to headingLatency24 hours
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Getting started
Call Nova Lite through AI Gateway with the AI SDK generateText and streamText functions, or through the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs by changing the base URL. AI Gateway authenticates the request and routes it to an available provider.
Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the text generation quickstart.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'amazon/nova-lite', prompt: 'Why is the sky blue?', });
console.log(result.text);}
main().catch(console.error);Top-level parameters
The same Nova Lite request in each API format AI Gateway supports.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'amazon/nova-lite', system: 'You are a concise technical assistant.', prompt: 'Summarize the tradeoffs between static generation and SSR.', maxOutputTokens: 1024, temperature: 0.5, });
console.log(result.text);}
main().catch(console.error);Standard parameters like prompt, messages, temperature, and tools work as documented in the AI SDK docs. These are the parameters with model-specific behavior.
| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | Yes | Model ID in the form creator/model, e.g. amazon/nova-lite. AI Gateway routes the request to an available provider. |
maxOutputTokens | number | No | Hard cap on generated tokens. Nova Lite supports up to 8,192 output tokens. |
providerOptions | Record<string, JSONValue> | No | AI Gateway routing options under gateway, plus any provider-native options under the provider’s own namespace — see the table below. |
Input limits
| Input | Formats | Sources | Max count | Max size | Limits |
|---|---|---|---|---|---|
| Text | — | — | — | — | Prompt and response share the 300K-token context window |
| Image | — | URL, base64, Uint8Array | — | — | Sent as image parts in messages; counts as input tokens |
| — | URL, base64, Uint8Array | — | — | Sent as file parts in messages; counts as input tokens |
Provider options
Set AI Gateway routing options under providerOptions.gateway. For provider-specific options, pass them under the provider’s namespace as documented by the AI SDK.
Learn more in the AI SDK amazon-bedrock provider docs.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'amazon/nova-lite', prompt: 'Why is the sky blue?', providerOptions: { gateway: { only: ['bedrock'], }, }, });
console.log(result.text);}
main().catch(console.error);These AI Gateway routing options apply to every model. Provider-specific options pass through under the provider’s own namespace (for example providerOptions.anthropic) exactly as documented by the AI SDK.
| Parameter | Type | Required | Description |
|---|---|---|---|
providerOptions.gateway.only | string[] | No | Restrict routing to these provider slugs. Requests fail over only within the listed providers. |
providerOptions.gateway.order | string[] | No | Preferred provider order. Listed providers are tried first; unlisted providers remain available as fallbacks. |
providerOptions.gateway.sort | 'cost' | 'ttft' | 'tps' | No | Rank candidate providers by price, time to first token, or tokens per second instead of the default routing order. |
providerOptions.gateway.zeroDataRetention | boolean | No | Route only to providers with a zero-data-retention policy for this model. |
Routing across providers
AI Gateway serves the same model through multiple providers and fails over automatically. order expresses a preference while keeping every provider eligible; only is a hard allowlist — if none of the listed providers are available the request fails instead of falling back.
Options under a provider's own namespace (for example providerOptions.anthropic) are forwarded to that provider with the request. Providers ignore option namespaces that don't apply to them, so it is safe to set provider options alongside gateway routing options.
Image input
Send images alongside text as message parts. Images count as input tokens.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'amazon/nova-lite', messages: [ { role: 'user', content: [ { type: 'text', text: 'Describe this image.' }, { type: 'image', image: 'https://example.com/photo.jpg' }, ], }, ], });
console.log(result.text);}
main().catch(console.error);PDF input
Attach PDFs as file parts. Their contents count as input tokens.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'amazon/nova-lite', messages: [ { role: 'user', content: [ { type: 'text', text: 'Summarize this document.' }, { type: 'file', mediaType: 'application/pdf', data: 'https://example.com/document.pdf', }, ], }, ], });
console.log(result.text);}
main().catch(console.error);Tool calling
Expose tools the model can call. Define each tool’s inputs with a Zod schema.
import { generateText, tool } from 'ai';import { z } from 'zod';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'amazon/nova-lite', prompt: 'What is the weather in San Francisco?', tools: { getWeather: tool({ description: 'Get the current weather for a location', inputSchema: z.object({ location: z.string() }), execute: async ({ location }) => ({ location, temperatureC: 18 }), }), }, });
console.log(result.text);}
main().catch(console.error);Copy link to headingAbout 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.
Copy link to headingWhat 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: Zero Data Retention is available for this model. It is offered on a per-provider and model basis. See the documentation for details.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
Copy link to headingWhen 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
Copy link to headingConclusion
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.
Copy link to headingFrequently 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.