Kimi K3 and Kimi K3 Fast with ZDR and US-based providers now on AI Gateway
Quick Answer
Moonshot AI's Kimi K3 and Kimi K3 Fast are now available via US-based providers on AI Gateway, supporting Zero Data Retention (ZDR).
Quick Take
Kimi K3 Fast offers lower latency at a ~50% higher cost per token, while the AI Gateway ensures automatic failover and optimal throughput across multiple providers.
Key Points
- Kimi K3 Fast reduces latency at a ~50% higher cost per token.
- Zero Data Retention can be enabled for all requests via AI Gateway.
- AI Gateway routes requests for higher uptime and throughput.
- Regional pricing for US inference is approximately 10% higher.
- Access provider details and pricing through the model endpoints API.
Source Excerpt
Kimi K3 and Kimi K3 Fast from Moonshot AI are now available on AI Gateway with Zero Data Retention, served by US-based providers including Baseten and Fireworks, with automatic failover for higher uptime and a faster serving path for lower latency.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from Vercel AI
See more →
The Agent Stack
The Agent Stack by Vercel AI provides essential building blocks for creating production-grade agents, enabling seamless integration across multiple AI models and secure operations. It features components like AI Gateway for model routing, Workflow SDK for durable execution, and Vercel Connect for scoped access, streamlining agent development and deployment across various platforms.
