Compare
Amazon Titan Text Express vs Trinity Large Preview
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
Trinity Large Preview
Context window
131K
131,000 tokens · ~98K 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.
Trinity Large Preview has about 3.1× the context window of the other in this pair.
Trinity Large Preview has 211% more context capacity (131K vs 42K tokens).
Quick verdicts
Short takeaways — validate with your own workloads.
Long document processing
Use Trinity Large Preview. Its 131K context fits entire documents without chunking (vs 42K).
Full specs
Context, output, capabilities, and dates. Green highlights the favorable value where we compute a winner.
| Spec | Amazon Titan Text Express | Trinity Large Preview |
|---|---|---|
| Context window | 42,000 tokens (42K) | 131,000 tokens (131K) |
| Max output tokens | 8,000 tokens (8K) | N/A |
| Speed tier | Balanced | Deep |
| Vision | No | No |
| Function calling | No | Yes |
| Extended thinking | No | No |
| Prompt caching | No | No |
| Batch API | No | No |
| Release date | N/A | Jan 2026 |
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 Titan Text Express in | Amazon Titan Text Express out | Trinity Large Preview in | Trinity Large Preview out |
|---|---|---|---|---|
| Aws Bedrock | $1.30/M | $1.70/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