I aimed to optimize the usage limit by using Haiku for simple questions and Sonnet for complex analysis—while maintaining the conversation context. I created a simple tool that lets me switch models within the same chat. The screenshot shows it in action: Claude correctly identifies itself as Haiku after switching from Sonnet mid-conversation.
https://imgur.com/a/sYRHjHC
Use cases:
- Drop to Haiku for quick clarifications and edits - Use Sonnet for in-depth analysis and complex code - Stay within rate limits by selecting the appropriate model per turn
Keeping it private for now to gauge interest. Would this be useful to others?