Kimi K2 Thinking
Kimi K2 Thinking (MoonshotAI, 2025) is an chat model. Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...
by MoonshotAI · 262K token context window
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use Kimi K2 Thinking in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your MoonshotAI API key. osFoundry discovers Kimi K2 Thinking automatically — assign it to a Maestro role (router, direct, orchestrator, or fallback) in the Pipeline tab and it is live in every chat. Your key, your provider account — no token markup.
Use it in a Room App
Room Apps declare AI features in their manifest, then call them with invokeAI:
import { invokeAI } from '@osfoundry/app-sdk'
// 'summarize' is an AI feature declared in your app manifest.
const result = await invokeAI('summarize', userText)
Call it from your own apps
Once a model is wired into your workspace you can host it as an API and reach it from your own services, scripts, or CI — outside osFoundry.
Run Kimi K2 Thinking yourself
Kimi K2 Thinking is also available as open weights — self-host it for full data control and no per-token cost. See that page for GPU requirements and a cost comparison against API pricing.
Kimi K2 Thinking vs similar models
Licence
Hosted — usage subject to provider terms — Hosted-only model — usage governed by the provider's API terms. Bring your own provider key.
No weights distributed; usage subject to provider terms.
Frequently asked about Kimi K2 Thinking
How much does Kimi K2 Thinking cost?
Kimi K2 Thinking is metered at $ 0.600 /1M for input, and $ 2.50 /1M for output. Bring your own MoonshotAI API key — osFoundry passes through provider pricing without markup.
Can I use Kimi K2 Thinking commercially?
Commercial use is allowed with conditions. Hosted-only model — usage governed by the provider's API terms. Bring your own provider key. No weights distributed; usage subject to provider terms.
What is the context window of Kimi K2 Thinking?
Kimi K2 Thinking supports a 262K token context window.
Can I run Kimi K2 Thinking locally?
No — Kimi K2 Thinking is hosted only and accessed via the MoonshotAI API. An open-weights equivalent is available to self-host — see the cross-link above.
What is Kimi K2 Thinking best at?
Kimi K2 Thinking is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use Kimi K2 Thinking in osFoundry?
Paste your MoonshotAI API key in the key dialog (or deploy the open weights for self-hostable models), assign Kimi K2 Thinking to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by MoonshotAI on November 6, 2025. Source: https://openrouter.ai/moonshotai/kimi-k2-thinking