Save Claude Code Tokens with Smart Routing

3 comments

• nithiink 6 hours ago
  How do you handle prompt caching? A lot of cost savings for a single model chat come from cache hits on the conversation context, and switching models invalidates that cache — the new model has to reprocess everything at full input price.
• patch_dev 5 hours ago
  What does this solve that well used subagents doesn't solve already?
  [-]
  • FrancescoMassa 5 hours ago
    On our tests subagents & well used workflows are 20-30% more expensive for context & token efficiency