I am wondering if people check their use case in ask before deciding which model to be used? Feels like hyping on whatever is being released by one of the big players
Works for me in Claude Code and in the chat interface /w a personal Max subscription. The message I'm getting is that it's available "through" July 7th, which probably means for the rest of the day?
When the business model rewards higher token usage, almost any good optimization technique should save you money. So I tried one.
Fabric indexes your repo first, finds the files relevant to the task, and gives them to Claude Code before it starts searching.
My tests show up to 62% lower token usage.
Test it here: github.com/hailmarylabs/fabric