Trinity Large Thinking is a reasoning-focused variant in Arcee AI's Trinity Large family: a 398B-parameter sparse mixture-of-experts model with about 13B active parameters per token, built on Trinity Large Base and emphasizing extended chain-of-thought reasoning.
import { streamText } from 'ai'
const result = streamText({ model: 'arcee-ai/trinity-large-thinking', prompt: 'Why is the sky blue?'})Trinity Large Thinking is a 398B-parameter sparse mixture-of-experts model with about 13B active parameters per token. It is built on Trinity Large Base and emits intermediate reasoning in the output when the task calls for it.
Use it when you need audit-friendly, stepwise reasoning more than the shortest possible reply. Choose Trinity Large Preview when you do not need trace-heavy output.
Check https://docs.arcee.ai/language-models/trinity-large-thinking for the latest capabilities, limits, and rates. Reasoning depth trades off against speed and token count, so validate latency and cost on your prompts before you commit to architecture.