Dedicated model · Available as managed deployment

Request a Kimi K3 deployment on your own system

Moonshot AI's Kimi K3 — an open-weight, natively multimodal agentic model at the trillion-parameter scale, built for long-horizon tasks, tool use and image understanding. Validated on AxForge hardware and deployed on a multi-GPU system sourced against your request for your traffic only — an OpenAI-compatible endpoint on hardware only you use, operated by AxForge in the EU.

eu-es-1 · Málaga Available as managed deployment Text + vision Quoted per deployment kimi-k3.axforge.ai
Request deploymentTalk to an engineerSign in Quoted per deployment Hardware rental plus a managed service quoted per deployment — both confirmed in writing before anything is billed.

Why AxForge

Why Kimi K3 as a managed deployment

Frontier scale, open weightsOne of the largest open models released: a mixture-of-experts at the trillion-parameter scale with text and image input.
Made for agentsLong-horizon tool use is what K3 is trained for — multi-step tasks, code, browsing-style workflows — served from a system only you use.
EU-hosted, not a cloud APIKimi K3 through a vendor API leaves the EU; a dedicated AxForge deployment keeps prompts, tools and outputs on hardware in Europe.

Specifications

What you get

ModelKimi K3 — moonshotai
ModalitiesText + vision — accepts image input
Sizes2.8T
LicenceCommercial licence needed — the model's own licence; AxForge handles the licence where one is required
HardwareMulti-GPU system (H100, H200 or B200 class) sourced against your request
Managed serviceQuoted per deployment
RegionEuropean region — placement confirmed with your request

Full details, benchmarks and FAQ on the Kimi K3 page. Prices exclude VAT.

How it works

From sign-in to running

1Request deployment — describe your traffic, context needs and rental term.
2You receive the configuration, hardware rental and managed-service price in writing before anything is billed.
3AxForge deploys Kimi K3 on a multi-GPU system sourced against your request reserved for you.
4Point your OpenAI SDK at your own endpoint with the model name you receive.
5Adjust the term — hour, week, month or year — as your workload settles.

Request deployment or sign in to start.

FAQ

Kimi K3 — common questions

Is Kimi K3 on the AxForge serverless API?

Not on the serverless API — it is available as a managed deployment: validated on AxForge hardware and deployed on a multi-GPU system sourced against your request for your traffic only. The serverless API serves Qwen3.8 27B.

What hardware does Kimi K3 need?

A multi-GPU system — H200 or B200 class — which AxForge sources against your request; the configuration and price are confirmed in writing before anything is billed.

What about the Kimi K3 licence?

Kimi K3 ships under Moonshot's own licence with conditions for large deployments. AxForge reviews it with you and deploys under it where it applies.

How fast is it on your hardware?

AxForge publishes only numbers it measures itself, and has not benchmarked this model on its nodes yet. For quality benchmarks, see the official model card.

What does EU Kimi K3 hosting cost?

Hardware and the managed service are quoted per deployment — both confirmed in writing before anything is billed.

Ready for Kimi K3 on your own machine?

Request deployment Sign in Talk to an engineer

Explore

More from AxForge

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms