RespanAI 发布 Span-01 与 Span-01 Lite，上线 OpenRouter
RespanAI 出了两个专给 Agent 轨迹打分的分类模型，判断用户情绪、工具调用安全性这类行为，Lite 版免费，比 Jev 还准。
RespanAI 推出面向 Agent 行为分析的决策模型 Span-01 和 Span-01 Lite，已在 OpenRouter 上线。
输入一段 Agent 执行轨迹和关注的行为，模型返回每个行为存在的概率，例如用户是否不满、某次工具调用是否安全可执行。Span-01 在 Behavior Benchmark 上排名第一，价格比 Jev 低 2 倍、成绩高 18%，比 GPT-6 Luna 便宜 700 倍、高 4%。
Span-01 Lite 成绩超过 Jev，完全免费。
Span-01 and Span-01 Lite from @RespanAI are live on OpenRouter. They're decision models for agent traces. Send a span and the behaviors you care about, and get back the probability each one is present, like "is the user frustrated?" or "is this tool call safe to run?" Respan @RespanAI Introducing Span-01, the first hyper-parallel reasoning classifier built for unseen challenges (RLAIF). 2x cheaper, 18% better than Jev. 700x cheaper, 4% better than GPT-6 Luna. Frontier reasoning for every behavior, at classifier speed. • Span-01: #1 on Behavior Benchmark • Span-01 Lite: Better than Jev and completely free! 🔗 View Quoted Tweet📊 5 ⚡
This report is categorized under AITOP's "Models" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Span-01, RespanAI, OpenRouter, 智能体.
Source attribution: curated from OpenRouter (@OpenRouterAI).
