Kimi K3 and Kimi K3 Fast with ZDR and US-based providers now on AI Gateway
Moonshot's Kimi K3 now runs on US infrastructure. For teams with compliance requirements, that changes the calculus on which models you can actually deploy.
Why it matters
Moonshot AI's Kimi K3 is expanding availability through Vercel's AI Gateway with US-based inference, Zero Data Retention support, and a faster variant—lowering friction for enterprise adoption in regulated markets where data residency is non-negotiable.
The key facts
7 to knowKimi K3 and Kimi K3 Fast now available via Baseten and Fireworks on Vercel AI Gateway
Zero Data Retention (ZDR) supported for both model variants
US data center inference available at ~10% premium over standard variant
Kimi K3 Fast costs ~50% more per token for lower latency
Multi-provider routing enables automatic failover and higher uptime
Available through Vercel CLI for coding agents with one-command setup
Published July 27, 2026
Go to the source
Vercel Blogvercel.com
Publisher excerpt: and its faster serving path, , are now available from US-based providers on AI Gateway, including Baseten and Fireworks. (ZDR) is also supported for both models. Kimi K3 from Moonshot AIKimi K3 FastZero Data Retention Running Kimi K3 on US-based providers lets teams with data residency and…