Artificial Analysis 上线各服务商缓存命中率与单任务成本数据
Cache hit rates and Cost per Task by provider are now live on Artificial Analysis: Cost per Task for GLM-5.3 (max) varies ~9x across providers, driven by a comb
Artificial Analysis 上线按服务商统计的缓存命中率与单任务成本数据，缓存命中率覆盖全部第一方和第三方端点，单任务成本则面向开源权重模型按各服务商价格与实测命中率计算。GLM-5.3 (max) 的单任务成本在服务商间相差约 9 倍，从 Makora 的 $0.92 到 Nebius 的 $8.68，两者缓存命中率分别为 98% 和 100%、输出价格同为 $4.40 per 1M tokens，差距来自输入定价：Makora 缓存输入为 $0.10 per 1M tokens，Nebius 的共享 serverless 端点不提供缓存输入折扣，全部按 $1.40 计费。21 家服务商（25 个端点）的缓存命中率在 41% 至 100% 之间，其中 15 个端点达到 98% 以上，Modal、DeepInfra、Parasail、Together AI、DigitalOcean、Nebius、Novita 和 Z AI 第一方 API 等 8 个端点为 100%，Multiverse Computing 最低为 41%，Bitdeer 为 50%。
推荐理由
AI 评分 54
Artificial Analysis 公开各服务商的缓存命中率与单任务成本，读者可据此比较同一模型在不同端点上的实际开销差异。
主题
正文
当前显示原文，中文全文译文尚未就绪。
Cache hit rates and Cost per Task by provider are now live on Artificial Analysis: Cost per Task for GLM-5.3 (max) varies ~9x across providers, driven by a combination of cache hit rate and token pricing
Agentic workloads resend the full conversation history every turn, so most input tokens are cacheable, and cache pricing and cache hit rates drive most of the gap in Cost per Task. We already use measured cache hit rates to calculate Cost per Task, and are now publishing them for each model endpoint we track.
What's new: ➤ Cache hit rates are now visible for all first-party and third-party endpoints, measured by running multi-turn agentic coding tasks and reading cached tokens from each provider's usage response. Cache hit rate is the share of cacheable input tokens served from cache. ➤ Cost per Task is now available by provider for open weights models, calculated from each provider's input, output, cache hit and cache write prices, applied at its measured cache hit rate. To standardize across providers for a given model, we use the same input, output and cacheable token counts from the model's Intelligence Index run.
Key takeaways: ➤ Cost per Task on GLM-5.3 (max) spans ~9x across providers, from $0.92 on Makora to $8.68 on Nebius. Both serve nearly all cacheable input from cache (98% and 100%) and charge the same output price ($4.40 per 1M tokens), so the gap comes from input pricing: Makora charges $0.10 per 1M cached input tokens, while Nebius offers no cached input discount on its shared serverless endpoints and bills all input at the full $1.40. ➤ Cache hit rate ranges from 41% to 100% across 21 providers (25 endpoints). 15 endpoints are at 98% or above, and eight are at 100%: Modal, DeepInfra, Parasail, Together AI, DigitalOcean, Nebius, Novita and Z AI's first-party API. Multiverse Computing is lowest at 41%, followed by Bitdeer at 50%.