Kimi K3 and Kimi K3 Fast now available on AI Gateway with US providers and ZDR

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 compliance requirements use the model on US infrastructure. Because AI Gateway serves the models from multiple providers, it automatically routes across them for failover, higher uptime, and more available throughput than any single provider offers. You call the same model ID, and the gateway handles provider selection and fallback.moonshotai/kimi-k3

Kimi K3 Fast trades a higher per-token cost for lower latency. Request it with the option on the base model, which stays on and falls back to standard speed when the fast tier is unavailable. Alternatively, use . The fast variant costs ~50% more than the base model. speedmoonshotai/kimi-k3moonshotai/kimi-k3-fast

To use Kimi K3, set to in the :modelmoonshotai/kimi-k3AI SDK

To route Kimi K3 requests to use only US data centers for inference, set . Regional pricing is ~10% more than the regular variant.inferenceRegion

Zero Data Retention for Kimi K3 is also available. Turn on Zero Data Retention for every request from the , or set it per request with :AI Gateway dashboard settingszeroDataRetention

To see every provider serving Kimi K3, along with per-provider pricing, supported parameters, uptime, throughput, and latency, call the model endpoints API:

Model prices vary by provider and variant type.

Run and select Kimi K3. This will detect the agents on your machine, provision an AI Gateway key, and write their config. See how to set it up via the .vercel ai-gateway coding-agents setupVercel CLI

Try Kimi K3 in the .model playground

Read more

US inference

Zero Data Retention

Providers and endpoints

Use Kimi K3 in your coding agent