Before you start
You need:- A Moonshot AI account.
- An API key from the dashboard:
- International: platform.moonshot.ai — base URL
https://api.moonshot.ai/v1 - China: platform.moonshot.cn — base URL
https://api.moonshot.cn/v1
- International: platform.moonshot.ai — base URL
- Sufficient credit on your Moonshot account.
Keys from the international portal and the China portal are not interchangeable. Pick the one that matches the base URL you use.
Add Kimi in Rumus
1
Open the model settings
Go to Settings → AI → Models and click Add Model.
2
Pick the provider
Set Provider to Kimi.
3
Paste your API key
Paste the key into API Key. It’s stored encrypted in your local vault.
4
Base URL
Default is
https://api.moonshot.ai/v1 (international). If you’re using a China-portal key, change it to https://api.moonshot.cn/v1.5
Pick a model
Choose from the list, or toggle Enter custom ID to type a model ID manually.
6
Capabilities
Capability flags are pre-set for the built-in models. For a custom model, mirror what Moonshot’s docs say it supports.
7
Save
The model appears in the picker under Custom Models.
Recommended models
For the full lineup, see the Moonshot AI docs.
Tips
- Pick K2.5 first. It’s the most capable everyday model — strong at tool use, supports vision, and handles long context.
- K2 Thinking drops vision but spends more on reasoning. Reach for it on tricky multi-step problems where extra deliberation helps.
- Moonshot V1 is older. Useful if a workflow specifically depends on it; otherwise prefer K2.5.
Troubleshooting
Model not in the list
Model not in the list
Toggle Enter custom ID and paste the exact model ID (e.g.
kimi-k2.5).High latency on first response
High latency on first response
Streaming first-token latency depends on region. Pick the portal that’s closer to you.
Hit a snag we didn’t cover? Ask in the Rumus community.
Next steps
Other providers
Anthropic, OpenAI, Google, Z.AI, DeepSeek, Ollama, OpenAI-compatible.
Built-in models
Use Rumus’s bundled Kimi without managing a key yourself.