Curated models for your best work

Join the waitlist
Log inGet API key

Amazon Nova Lite

  • Tool calling
  • Streaming
  • Runs on AWS Bedrock

Model id

amazon/nova-lite
APITry this model
Context window
300K
tokens
Input price
$0.06
per 1M tokens
Output price
$0.24
per 1M tokens
Max output
5K
tokens

Provider list price

Pricing

USD / 1M tokens

Input$0.06 / M tokens
Output$0.24 / M tokens
Cache read$0.015 / M tokens
Cache write$0 / M tokens
Context window300K tokens
RoutingFree

Provider list price. BYOK bills your provider; managed credits draw down at these rates. No markup or request fee. Every request is metered per engineer and joined to shipped work.

Registry 2026-10-31.2 · effective 9/17/2026 · Amazon Bedrock pricing

Registry contract

Capabilities

Protocols
3
Chat · Responses · Messages · streaming
Tools
2
Chat · Messages
JSON Schema
None
Not supported
Vision
No
Not supported
Reasoning
None
No public control
Output limit
5,000
tokens

canonical amazon/nova-lite · revision amazon/nova-lite · aliases amazon.nova-lite-v1:0, nova-lite

First request

Run it

Python · TokenSpend SDK
from tokenspend import TokenSpend

client = TokenSpend()
resp = client.chat.completions.create(
    model="amazon/nova-lite",
    messages=[{"role": "user", "content": "hello"}],
)
TypeScript · TokenSpend SDK
import { TokenSpend } from "@tokenspend/sdk";

const client = new TokenSpend();
const resp = await client.chat.completions.create({
  model: "amazon/nova-lite",
  messages: [{ role: "user", content: "hello" }]
});
curl
curl https://api.tokenspend.dev/v1/chat/completions \
  -H "content-type: application/json" \
  -H "Authorization: Bearer $TOKENSPEND_API_KEY" \
  -d '{"model":"amazon/nova-lite","messages":[{"role":"user","content":"hello"}]}'
Claude Code integration
export ANTHROPIC_BASE_URL=https://api.tokenspend.dev
export ANTHROPIC_API_KEY=$TOKENSPEND_API_KEY
export ANTHROPIC_MODEL=amazon/nova-lite

One request shape reaches every model. Claude Code connects as an integration with two environment variables. TokenSpend never stores prompts or responses.

Questions

Who runs Amazon Nova Lite?

AWS Bedrock runs it, at the list price above. A request that fails there fails with an error, because there is no second provider to move to.

What does Amazon Nova Lite cost?

$0.06 per 1M input tokens and $0.24 per 1M output tokens. TokenSpend adds no markup and no per-request fee. If you pay with managed credits, buying them carries a 5% fee.

What can I do with Amazon Nova Lite through TokenSpend?

Chat and streaming, plus tool calling (Chat, Messages). It does not support JSON schema output and image input here. Tool calling and JSON schema are enabled per provider, only after that provider passes our tests, so a provider chosen by hand may lack them.

How long can my prompt be?

300K tokens of context, prompt and reply together, with up to 5,000 tokens in a single reply.

Does prompt caching make Amazon Nova Lite cheaper?

Yes, when the provider caches a repeated prompt prefix. Cached input is billed at $0.015 per 1M tokens instead of $0.06, and writing to the cache costs $0.00 per 1M tokens.

How current is this pricing?

It follows rate card 2026-10-31.2, effective 9/17/2026. Source: Amazon Bedrock pricing.