创建

登录 ReadmeX

或

了解我们如何处理你的信息: 隐私政策

ReadmeX

陪你读懂 AI 动态

今天,想先了解什么?

选一份动态总结,或直接聊聊你的问题。

社区和关注动态总结只属于你自己。

资讯

OpenRouter重构默认提供商路由

AI 总结

OpenRouter表示,重建的默认路由算法不再主要依据输入token价格,而是综合评估有效价格、延迟、吞吐、错误率、可靠性和回答质量。其现场实验显示,首字延迟改善16.9%,吞吐提升16.3%,容量错误率下降67%,但每请求成本增加6.0%。该系统已面向符合条件的默认路由请求启用,无需更改API密钥、请求或模型ID,但显式排序和提供商控制仍可绕过新算法。

深度见解

OpenRouter称此次更新让默认路由能够响应提供商的实时表现和质量,无需改代码即可获得更快、更可靠的推理。

How we rebuilt provider routing for better, faster inference

Scott Morse ·10/28/2026

How we rebuilt provider routing for better, faster inference

Today we’re announcing the biggest improvement to our provider routing algorithm since the founding of OpenRouter.

Until now, our default router mostly rewarded providers for one thing: a low price. The new router rewards the inference that is actually best for you: cheap, but also fast, high-throughput, and reliable. Providers that deliver more value automatically win more traffic, so every provider has a reason to keep improving. That means the inference you get through OpenRouter keeps getting faster, more reliable, and more cost-effective, and you don’t have to change a line of code.

It’s already working. The new algorithm has unlocked significant improvements in TTFT (16.9%), throughput (16.3%) and capacity errors (a remarkable 67% reduction!), with only minor increases in cost (6.0%). That’s before providers have had any time to optimize for the new algorithm. See our full experimental results for more details.

#OpenRouter

原文约 9 分钟读完阅读原文
群聊

还没有评论,来说说你的看法。