Trinity-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.
费用比率
0.2x
上下文
262K
发布日期
2026年4月1日
输入
Text
输出
Text
支持
推理工具调用结构化输出
性能
根据近期请求测得的中位延迟和吞吐量。
吞吐量337 tok/s
延迟1.16s