Context Window

Compare

Nova Lite 1.0 vs Trinity Large Thinking (free)

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.

Amazon

Model

Nova Lite 1.0

Image inputTool calling

Context window

300K

300,000 tokens · ~225K words

Model page
Arcee Ai

Model

Trinity Large Thinking (free)

Tool calling

Context window

262K

262,144 tokens · ~197K words

Model page

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.

Nova Lite 1.0300K
Trinity Large Thinking (free)262K

Nova Lite 1.0 has about 1.1× the context window of the other in this pair.

Token calculator →Memory savings →

Nova Lite 1.0 has 14% more context capacity (300K vs 262K tokens).

Quick verdicts

Short takeaways — validate with your own workloads.

  • Long document processing

    Use Nova Lite 1.0. Its 300K context fits entire documents without chunking (vs 262K).

  • Long output (reports, code files)

    Use Trinity Large Thinking (free). Its 80K 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.

SpecNova Lite 1.0Trinity Large Thinking (free)
Context window300,000 tokens (300K)262,144 tokens (262K)
Max output tokens10,000 tokens (10K)80,000 tokens (80K)
Speed tierBalancedDeep
VisionYesNo
Function callingYesYes
Extended thinkingNoYes
Prompt cachingNoNo
Batch APINoNo
Release dateDec 2024Apr 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.

ProviderNova Lite 1.0 inNova Lite 1.0 outTrinity Large Thinking (free) inTrinity Large Thinking (free) out
Amazon$0.060/M$0.240/M——

Frequently asked questions

Nova Lite 1.0 has a larger context window: 300K tokens vs 262K. For long documents, large codebases, or extended agent sessions, the larger context window reduces the need to chunk inputs or summarize history.

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.

Calculate your savingsLearn about Mem0

Example: a multi-turn chat session

Without Mem0~128K tokens sent
Full history
Repeated info
Old context
With Mem0~20K tokens sent
Key memories
Current turn

80% less to send — works with any model