输入价格
公开资料未说明
输出价格
公开资料未说明
端侧部署低成本推理Agent
官方模型目录与价格对比
找模型，不只看名字，还要看 能力和价格
按模型类型、上下文、价格和厂商整理官方模型目录，方便你快速筛出适合写代码、做推理、跑视觉或搭 Agent 的那一批模型。
先缩小候选，再进详情页看接口、计费和能力边界。
已收录模型
1,303
覆盖厂商
63
带价格信息
355
语言模型Arcee AI稳定版
Trinity Large Thinking
Pricing Integration List chevron-right Language Models chevron-right Trinity-Nano (6B) Trinity-Mini (26B) Trinity-Large-Preview Trinity-Large-Thinking API Reference chevron-right Your First API Call Chat Completion Usage Models Capabilities chevron-right Streaming Messages Multi-Turn Conversations Function Calling Structured Outputs Reasoning Traces Quick Deploys chevron-right Download Models arrow-up-right Hardware Prerequisites Consumer Hardware chevron-right Inference Engines chevron-right Policies chevron-right Deprecation Policy chevron-up chevron-down gitbook Powered by GitBook gitbook xmark block-quote On this page xmark xmark copy Copy chevron-down block-quote On this page block-quote Language Models Trinity-Large-Thinking Overview Trinity-Large-Thinking is a reasoning-optimized variant of Arcee AI's Trinity-Large family — a 398B-parameter sparse Mixture-of-Experts (MoE) model with approximately 13B active parameters per token. Built on Trinity-Large-Base and post-trained with extended chain-of-thought reasoning and agentic RL, Trinity-Large-Thinking delivers state-of-the-art performance on agentic benchmarks while maintaining strong general capabilities. Trinity-Large-Thinking generates explicit reasoning traces wrapped in <think>...</think> blocks before producing its final response. This thinking process is critical to the model's performance — thinking tokens must be kept in context for multi-turn conversations and agentic loops to function correctly.
输入价格
公开资料未说明
输出价格
公开资料未说明
多步推理Reasoning TraceAgent 工作流
语言模型DeepCogito预览版
Cogito V2 Preview Llama 109B MoE
DeepCogito v2 Preview 的 109B MoE 开放权重混合推理模型，兼顾复杂推理、代码任务与超长上下文实验。
输入价格
公开资料未说明
输出价格
公开资料未说明
推理任务代码开发研究实验