Compare
Amazon Nova Lite vs Amazon Titan Text Lite
This page is context-first: how much text each model can take in one request. Full specs adds capabilities and limits; the pricing matrix below is only about $/million tokens from hosts that list both models.
Model
Amazon Nova Lite
Context window
300K
300,000 tokens · ~225K words
Context window · side by side
Bar length is relative to the larger of the two windows (100% = max of this pair). This is not pricing.
Amazon Nova Lite has about 7.1× the context window of the other in this pair.
Amazon Nova Lite has 614% more context capacity (300K vs 42K tokens). Amazon Nova Lite is 80% cheaper on input.
Quick verdicts
Short takeaways — validate with your own workloads.
Long document processing
Use Amazon Nova Lite. Its 300K context fits entire documents without chunking (vs 42K).
RAG / high-volume retrieval
Use Amazon Nova Lite. Input tokens are 80% cheaper — critical when sending large retrieved contexts.
Long output (reports, code files)
Use Amazon Nova Lite. Its 10K max output lets you generate complete artifacts in one request.
Full specs
Context, output, capabilities, and dates. Green highlights the favorable value where we compute a winner.
| Spec | Amazon Nova Lite | Amazon Titan Text Lite |
|---|---|---|
| Context window | 300,000 tokens (300K) | 42,000 tokens (42K) |
| Max output tokens | 10,000 tokens (10K) | 4,000 tokens (4K) |
| Speed tier | Balanced | Balanced |
| Vision | Yes | No |
| Function calling | Yes | No |
| Extended thinking | No | No |
| Prompt caching | No | No |
| Batch API | No | No |
| Release date | N/A | N/A |
Pricing matrix
Dollar rates only: hosts that list both models, per 1M tokens. For how much text fits, use the context section above — not this table.
| Provider | Amazon Nova Lite in | Amazon Nova Lite out | Amazon Titan Text Lite in | Amazon Titan Text Lite out |
|---|---|---|---|---|
| Aws Bedrock | $0.060/M | $0.240/M | $0.300/M | $0.400/M |
Frequently asked questions
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