AxForge offering · Request
Moonshot AI's Kimi K3 is 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, as an OpenAI-compatible endpoint on hardware only you use, operated by AxForge in the EU.
Currently request-only. Add your request to the public forum; this is not a booking or a promised launch.
Why AxForge
| Frontier scale, open weights | One of the largest open models released: a mixture-of-experts at the trillion-parameter scale with text and image input. |
|---|---|
| Made for agents | Long-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 API | Kimi K3 through a vendor API leaves the EU; a dedicated AxForge deployment keeps prompts, tools and outputs on hardware in Europe. |
Specifications
| Model | Kimi K3 by moonshotai |
|---|---|
| Modalities | Text + vision, accepts image input |
| Sizes | 2.8T |
| Licence | Commercial licence needed (the model's own licence); AxForge handles the licence where one is required |
| Hardware | Multi-GPU system (H100, H200 or B200 class) sourced against your request |
| Managed service | Quoted per deployment |
| Region | European region, placement confirmed with your request |
Kimi K3 catalogue reference: specifications and requirements. List prices in EUR.
How it works
| 1 | Add a public request describing your workload, context needs and preferred rental term. A request does not reserve hardware or promise a deployment. |
|---|---|
| 2 | If AxForge can offer a deployment, agree the configuration, hardware rental, licence and managed-service price in writing before anything is billed. |
| 3 | Only after availability and terms are confirmed would AxForge provision the agreed dedicated system and model build. |
| 4 | After provisioning, point your OpenAI SDK at your own endpoint with the model name you receive. |
| 5 | After provisioning, adjust the term (hour, week, month or year) as your workload settles. |
Request model or sign in to start.
FAQ
This page describes the managed deployment option. Availability, the model build, hardware, licence and price must be agreed before a deployment can be offered. A public request does not provision or reserve a machine. Check the console for the current serverless offering list.
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.
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.
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.
For a deployment agreed after availability is confirmed: Hardware and the managed service are quoted per deployment. Both are confirmed in writing before anything is billed.