Apac Amazon Nova Lite
Context window
This model accepts 300K tokens in one request (~225K words of text).
What fits in one request
- FitsShort documentAbout 1,500 words of text
- FitsLong documentAbout 37K words of text
- FitsSmall codebaseAbout 150K words of text
- Won't fitFull novelAbout 375K words of text
Specifications
Context size, pricing, and release info in one place.
- Context window
- 300,000 tokens (300K)
- Max output tokens
- 10,000 tokens (10K)
- Speed tier
- balanced
- Provider
- Amazon
- Input cost
- $0.063/M / 1M tokens
- Output cost
- $0.252/M / 1M tokens
Capabilities
See which features this model supports, such as vision, tools, and streaming.
- Vision
- Accepts image inputs alongside text
- Supported
- Tool use
- Can call external tools and APIs
- Supported
- Function calling
- Structured function call interface
- Supported
- Streaming
- Returns tokens as they are generated
- Supported
- Extended thinking
- Shows its chain-of-thought reasoning
- Not supported
- Web search
- Can browse the web during a request
- Not supported
- Batch API
- Process many requests asynchronously
- Not supported
- Prompt caching
- Reuse repeated prompt prefixes cheaply
- Not supported
Best for
Jump to a guide or ranking that matches each workload.
Compare Apac Amazon Nova Lite
Open a side-by-side comparison with one click.
- Apac Amazon Nova Lite vs Amazon Titan Text Express
Apac Amazon Nova Lite has 614% larger context window
- Apac Amazon Nova Lite vs Amazon Titan Text Lite
Apac Amazon Nova Lite has 614% larger context window
- Apac Amazon Nova Lite vs Amazon Titan Text Premier
Apac Amazon Nova Lite has 614% larger context window
- Apac Amazon Nova Lite vs Apac Amazon Nova 2 Lite
Apac Amazon Nova 2 Lite has 233% larger context window
- Apac Amazon Nova Lite vs Apac Amazon Nova 2 Pro Preview 20251202
Apac Amazon Nova 2 Pro Preview 20251202 has 233% larger context window
- Apac Amazon Nova Lite vs Amazon Nova Lite
Same context window size
Frequently asked questions
Short answers about context size and how this model behaves.
More from Amazon
Other models by Amazon in our catalog.
Powered by Mem0
Use a smaller model.
Get better results.
Mem0 gives your AI long-term memory so you stop re-sending context on every call. That means you can use a smaller, faster, cheaper model — and still get better answers.
Example: a multi-turn chat session
80% less to send — works with any model