进阶 docs.arcee.ai 2026-10-23 07:38:35 · 61 阅读

第1章 Trinity 模型家族

完整文档索引请见 llms.txt。本页面同时提供 Markdown 版本。

Trinity Family

Trinity-Large-Thinking 是唯一可通过 API 调用的 Arcee 模型。所有可用的开源模型请见定价页。

ModelTrinity-Nano (6B)Trinity-Mini (26B)Trinity-Large-Thinking (400B) StrengthLightweight, ultra-low latency model.Fast and cost-efficient model for well-defined tasks.Robust generalist model with strong performance across reasoning, coding, math, and complex task decomposition. Ideal DeploymentFully local on consumer GPUs, edge servers, and mobile devices. Tuned for offline operation.Serve customer-facing apps, agent backends, and high-throughput services in cloud or VPC.Advanced agents, reasoning systems, and developer tools. Deployed via hosted cloud endpoints or self-hosted in multi-GPU configurations. Active Parameters1B per token3B per token13B per token Context Window128k tokens128k tokens512k tokens (hosted at 128k) Knowledge Cutoff202420242024 Speed⚡⚡⚡ Instant⚡⚡⚡ Very Fast⚡⚡⚡ Very Fast API Model NameNot HostedNot Hostedtrinity-large-thinking

PreviousModel OverviewNextTrinity-Nano (6B)

Last updated 1 month ago

评论 (0)