Trinity Large Thinking
Arcee AI
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.
Software & IT Services
#153 · top 39%
Medicine & Healthcare
#153 · top 42%
Entertainment, Sports, & Media
#155 · top 40%
Life, Physical, & Social Science
#156 · top 40%
Performance
Median latency and throughput measured across recent requests.
Throughput197 tok/s
Latency