Kimi-K3 hosts appear locked into identical pricing as providers compete on latency
TheZachMueller · x · 2026-07-28
Last week’s warning about Kimi-K3 token pricing appears to have been accurate: large inference providers are all charging the same rates.
The claim is that Moonshot’s license requires separate agreements with large inference providers, including restrictions on the price they can offer the model at so they can’t undercut Moonshot. As a result, providers are competing on latency and throughput instead of price. The attached chart shows the same $3 input / $15 output pricing across multiple hosts, with different latency, throughput, and uptime numbers.
More from Infra
- Meta's open Muse Spark needs 493GB of memory — far beyond any consumer laptop — TejasKumar_ · 2026-10-16
- CoreWeave plunges 20% as credit markets price >60% default odds; is this dot-com all over again? — kimmonismus · 2026-10-16
- MiniCPM-V 4.7 35B-A3B hits 17+ tokens/s on iPad with ~3GB memory — techNmak · 2026-10-16
- China rolls out 'token factories' and a 2026-28 token economy action plan — nordicinst · 2026-10-16
- Vercel Sandbox Drives go GA: attach TBs of data in sub-second, fork instantly — cramforce · 2026-10-16
- NVIDIA launches RTX Spark for local AI on Windows PCs — ostrisai · 2026-10-16