Open-weight large language models (LLMs) are usually named as model artifacts, but production users often consume them as hosted API services. This paper argues that the operational unit is a service object: a provider-specific, time-varying endpoint defined by model variant, protocol behavior, context capacity, listed price, latency and throughput distribution, reliability, and task feasibility. Using sampled request logs, provider metadata, compatibility probes, pricing snapshots, and continuous latency measurements collected by AI Ping during Q4 2025, we study how this service layer changes the meaning of "the same model." Three empirical patterns emerge. First, observed demand is concentrated but persistent across versions: in the displayed family aggregate, the largest family carries 32.0% of relative demand and the top five carry 87.4%, with a Gini coefficient of 0.693, while older variants remain active after newer releases. Second, supply and use separate: provider listing breadth does not imply realized adoption, and listed prices are more anchored than latency, throughput, context length, protocol support, and error semantics. Third, task mix matters: applications induce different token-length regimes, so provider choice is a constrained decision over provider-model-task-time tuples rather than a lookup by model name. In two representative counterfactuals under observed feasibility constraints, routing lowers Qwen3-32B cost by 37.8% and raises DeepSeek-V3.2 average throughput by about 90% relative to direct official access. The results support a measurement view of hosted open-weight LLMs as heterogeneous services, not static catalog entries.

翻译：开源权重大语言模型（LLMs）通常以模型制品命名，但生产用户往往通过托管API服务消费它们。本文论证运作单元本质上是服务对象：一种由模型变体、协议行为、上下文容量、标价、延迟与吞吐量分布、可靠性及任务可行性定义的、随提供者随时间变化的端点。基于AI Ping在2025年第四季度收集的采样请求日志、提供者元数据、兼容性探测、定价快照及连续延迟测量，我们研究这一服务层如何改变"相同模型"的含义。三个经验性模式浮现。首先，观测需求虽高度集中但跨版本持续：在显示族聚合中，最大族承载32.0%的相对需求，前五族承载87.4%，基尼系数达0.693，而旧变体在新版本发布后仍保持活跃。其次，供给与使用分离：提供者列出的广度不意味着实际采纳，标价相对锚定程度高于延迟、吞吐量、上下文长度、协议支持及错误语义。第三，任务组合至关重要：应用产生不同令牌长度区间，因此提供者选择是提供者-模型-任务-时间四元组上的约束决策，而非单纯按模型名称查询。在观测可行性约束下的两个代表性反事实情景中，相较于直接官方访问，路由使Qwen3-32B成本降低37.8%，使DeepSeek-V3.2平均吞吐量提升约90%。研究结果支持将托管开源权重LLMs视为异构服务而非静态目录条目的测量视角。