How do I control extended thinking?

Under `providerOptions.bedrock.reasoningConfig`, set `maxReasoningEffort` to `low`, `medium`, or `high`. Extended thinking is off by default, so you avoid reasoning-token charges until you enable it.

What does web grounding do?

The model can search the public web during a request and ground answers in what it finds, with citations when the provider returns them. Use it when answers need current facts, not only the training snapshot.

How large is the context window compared to first-gen Nova models?

1M tokens. That's more than three times the 300K-token context in Nova Lite and Nova Pro, and nearly eight times Nova Micro's 128K.

Can Nova 2 Lite run code during a conversation?

Yes. Amazon documents code execution for Nova 2 models so the model can run code as part of the response flow. Use it for calculations, data transforms, and similar tasks the provider supports.

How are reasoning tokens billed?

Reasoning tokens are billed at the output token rate. With thinking disabled (the default), you pay only standard input and output costs.

Is Nova 2 Lite a direct replacement for first-gen Nova Lite?

No, it's a successor but not a drop-in replacement. Nova 2 Lite has different pricing and a different capability profile. For simple multimodal tasks where first-gen Nova Lite performs well, upgrading may not cut costs. The value lies in the reasoning, grounding, and code execution features the original lacked.

Amazon

Nova 2 Lite

Nova 2 Lite is a second-generation multimodal reasoning model with a context window of 1M tokens. It supports configurable extended thinking, web grounding, and code execution at a cost tier built for everyday production use.

View API reference

Input and output price: Input $0.30, Output $2.50, Per 1M tokens
24h uptime: Loading AI Gateway uptime

Get API key Read the docs

import { streamText } from 'ai'

const result = streamText({
  model: 'amazon/nova-2-lite',
  prompt: 'Why is the sky blue?'
})

Read docs

Overview Playground Providers Uptime Status Throughput Latency API Similar About FAQ

Copy link to headingPlayground

Try out Nova 2 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 2 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

Context	Max Output	Latency	Throughput	Input	Output	Cache	Web Search	Capabilities	ZDR	No Training	Regional Inference	Free Tier	Release Date

Bedrock

Legal:Terms•Privacy

0.4 s

204 tps

$0.30/M+1 more

$2.50/M+1 more

Read$0.08/M

—

12/02/2025

Getting started

Call Nova 2 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.

index.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'amazon/nova-2-lite',
    prompt: 'Why is the sky blue?',
  });

  console.log(result.text);
}

main().catch(console.error);

Top-level parameters

The same Nova 2 Lite request in each API format AI Gateway supports.

top-level-params.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'amazon/nova-2-lite',
    system: 'You are a concise technical assistant.',
    prompt: 'Summarize the tradeoffs between static generation and SSR.',
    maxOutputTokens: 1024,
  });

  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-2-lite`. AI Gateway routes the request to an available provider.
`maxOutputTokens`	`number`	No	Hard cap on generated tokens. Nova 2 Lite supports up to `1,000,000` output tokens. Reasoning tokens count toward this limit.
`reasoning`	`'provider-default' \| 'none' \| 'minimal' \| 'low' \| 'medium' \| 'high' \| 'xhigh'`	No	Provider-agnostic reasoning effort, available in AI SDK 7 or later. Maps to the provider’s native reasoning configuration; reasoning settings under `providerOptions` take precedence when both are set. See the Reasoning section below.
`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 1M-token context window
Image	—	URL, base64, Uint8Array	—	—	Sent as image parts in messages; counts as input tokens
PDF	—	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.

provider-options.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'amazon/nova-2-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.

Reasoning

AI Gateway bridges reasoning across every API format. The AI SDK exposes a provider-agnostic top-level reasoning level (none, minimal, low, medium, high, or xhigh); the Chat Completions and Responses formats take the same effort under reasoning.effort; and the Anthropic Messages format uses a native thinking token budget. Whichever you send, the gateway maps it to the target model’s native configuration, converting between effort levels and token budgets as needed. Reasoning-related settings under providerOptions take full precedence over the top-level reasoning value and are never merged. Reasoning tokens typically count toward your output-token usage, though how they’re reported and billed varies by provider.

Learn more in the AI Gateway reasoning guide.

reasoning.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'amazon/nova-2-lite',
    prompt: 'Explain the Monty Hall problem step by step.',
    reasoning: 'high',
  });

  console.log(result.text);
}

main().catch(console.error);

Image input

Send images alongside text as message parts. Images count as input tokens.

image-input.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'amazon/nova-2-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.

pdf-input.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'amazon/nova-2-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.

tool-calling.ts

import { generateText, tool } from 'ai';
import { z } from 'zod';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'amazon/nova-2-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 headingMore models by Amazon

Model

Context	Latency	Throughput	Input	Output	Cache	Web Search	Capabilities	Providers	ZDR	No Training	Free Tier	Release Date

amazon/nova-lite

300K

0.3 s

134 tps

$0.06/M

$0.24/M

—

12/03/2024

amazon/nova-micro

128K

0.4 s

$0.04/M

$0.14/M

—

12/03/2024

amazon/nova-pro

300K

0.4 s

140 tps

$0.80/M

$3.20/M

—

12/03/2024

amazon/titan-embed-text-v2

—

$0.02/M

—

04/30/2024

Copy link to headingAbout Nova 2 Lite

Nova 2 Lite is the cost-focused model in Amazon's second-generation Nova family. The context window moves from 300K tokens on first-gen Nova Lite and Nova Pro up to 1M tokens. Extended thinking lets the model run deliberate multi-step reasoning before it answers. You set it to low, medium, or high. It stays off by default when you don't need it.

Amazon pairs Nova 2 Lite and Nova 2 Pro with built-in web grounding and code execution: the model can pull current public information and run code so answers stay tied to fresh data, not only to training cutoffs.

Inputs include text, images, video, and documents (including PDFs) within the window of 1M tokens. That covers long documents with images, video with transcripts, and similar mixed workloads that first-generation Nova models handle with tighter limits.

Copy link to headingWhat To Consider When Choosing a Provider

Configuration: When extended thinking is on, reasoning tokens are billed at the output token rate. If you use medium or high thinking budgets often, monitor output token spend in the AI Gateway cost dashboard.
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 2 Lite

Best for

Mixed-format document processing: Combine PDFs, images, and text in a single long-context request
Current information workflows: Web grounding provides up-to-date information with citations when the provider returns them
Agentic task orchestration: The model calls external tools across multiple steps
Selective extended thinking: Toggle deeper reasoning on analytical tasks and use fast extraction by default
Unified video and document analysis: Video and image analysis combined with document comprehension in a single context of 1M tokens

Consider alternatives when

Text-only cost-focused workloads: Nova Micro remains cheaper and faster for pure text processing
Simple multimodal tasks: First-generation Nova Lite handles simpler vision tasks at lower cost without reasoning overhead
Highest structured-document accuracy: Evaluate Nova Pro when second-gen reasoning features aren't required

Copy link to headingConclusion

Nova 2 Lite pairs a large multimodal context with optional extended thinking, web grounding, and code execution. You pay extra reasoning tokens only when you turn thinking on. Teams that hit limits on first-generation Nova Lite often move here before jumping to the highest-cost tiers.

Copy link to headingFrequently Asked Questions

How do I control extended thinking?
Under providerOptions.bedrock.reasoningConfig, set maxReasoningEffort to low, medium, or high. Extended thinking is off by default, so you avoid reasoning-token charges until you enable it.
What does web grounding do?
The model can search the public web during a request and ground answers in what it finds, with citations when the provider returns them. Use it when answers need current facts, not only the training snapshot.
How large is the context window compared to first-gen Nova models?
1M tokens. That's more than three times the 300K-token context in Nova Lite and Nova Pro, and nearly eight times Nova Micro's 128K.
Can Nova 2 Lite run code during a conversation?
Yes. Amazon documents code execution for Nova 2 models so the model can run code as part of the response flow. Use it for calculations, data transforms, and similar tasks the provider supports.
How are reasoning tokens billed?
Reasoning tokens are billed at the output token rate. With thinking disabled (the default), you pay only standard input and output costs.
Is Nova 2 Lite a direct replacement for first-gen Nova Lite?
No, it's a successor but not a drop-in replacement. Nova 2 Lite has different pricing and a different capability profile. For simple multimodal tasks where first-gen Nova Lite performs well, upgrading may not cut costs. The value lies in the reasoning, grounding, and code execution features the original lacked.

Your use is subject to Amazon's Terms & Privacy Policies.

Agent Stack

Core Platform

Tools

Learn

Build

Explore

Nova 2 Lite

Copy link to headingPlayground

Copy link to headingProviders

Copy link to headingUptime24 hours

Copy link to headingThroughput24 hours

Copy link to headingLatency24 hours

Getting started

Top-level parameters

Input limits

Provider options

Routing across providers

Reasoning

Image input

PDF input

Tool calling

Copy link to headingMore models by Amazon

Copy link to headingAbout Nova 2 Lite

Copy link to headingWhat To Consider When Choosing a Provider

Copy link to headingWhen to Use Nova 2 Lite

Best for

Consider alternatives when

Copy link to headingConclusion

Copy link to headingFrequently Asked Questions