Skip to main content
managed-models

Connect to different large language models (brains) with your own API key—giving you full control over your AI capabilities.

​
Managed Models BYOK

Managed models allow you to select AI models based on your needs using your API key, such as:
  • Fast and cost-effective (Claude Haiku 3.5)
  • Balanced (Claude Sonnet 4)
  • High intelligence (Claude Opus 4.1)
To connect:
  1. Get an API key from Anthropic
  2. Paste the key into the field that starts with sk-ant-...
This option gives you full ownership and flexibility, with no AI Thing plan required.
Join the Waitlist for fully managed models that don’t require your own API keys.

​
Model Settings

In Settings → Preferences, you can fine-tune how models behave:

​
Prompt Cache

Reuses common parts of a prompt to speed up responses and lower costs during long or repetitive conversations. For one-time or short queries, caching may actually be more expensive — it’s most useful when a conversation is expected to continue over many turns. Read more.

​
Output Tokens

Set the maximum length of responses. Useful for keeping outputs concise or allowing longer, more detailed answers.