OpenRouter's new routing algorithm cuts GLM 5.3 Flash TTFT 40% and price 17%
AccBalanced · x · 2026-11-12
OpenRouter reports one-month results from its new routing algorithm: GLM 5.3 Flash users saw TTFT drop 40%, throughput rise 10%, and price per 1M tokens fall 17%.
Co-founder Alex Atallah explains the algorithm rewards providers with better inference quality by sending them more traffic — and argues that, counter to popular belief, routing actually increases reliability rather than hurting it. The post includes an animation of cost and speed improving over time.
Related event: OpenRouter's New Routing Algorithm Cuts GLM 5.3 Flash Latency and Price(2 posts)→
More from Infra
- Big AI conflates scale with innovation as voters reject data center ballot measures — DavidLinthicum · 2026-11-12
- Musk says SpaceX targets 1TW/year from Earth, rising to 1PW/year from the Moon — ns123abc · 2026-11-12
- Where does Claude's cost really go? Running build tools may quietly add up — IgorBrigadir · 2026-11-12
- Int8 AVX512 VNNI quantization cuts CPU inference to 34ms vs 90ms fp32—2.6x faster — wavefnx · 2026-11-12
- H100 rental rates run 54% above straight-line depreciation, a16z finds — a16z · 2026-11-12
- Apple trains small offline nets to route RAG queries, trading upfront cost for faster retrieval — petrusenko_max · 2026-11-12