Trinity Large Thinking
Arcee AI馃嚭馃嚫
arcee-ai/trinity-large-thinkingTrinity-Large-Thinking is Arcee AI's open-source frontier reasoning model, a 399B-parameter sparse mixture-of-experts model (about 13B active per token) with a 512K-token context window, released under Apache 2.0. It generates explicit chain-of-thought reasoning traces and is built for complex, long-horizon agentic tasks and long-document analysis.
Cost rate
0.2x
Context
262K
Released
Apr 1, 2026
Input
Text
Output
Text
Support
ReasoningTool callingStructured outputs
Best at
The categories where this model ranks highest.
Life, Physical, & Social Science
#192 路 top 46%
Medicine & Healthcare
#194 路 top 50%
Mathematical
#195 路 top 49%
Business, Management, & Finance
#198 路 top 48%
Performance
Median latency and throughput measured across recent requests.
Throughput362 tok/s
Latency