Auto selection now picks models by task intent and real-time health instead of forcing manual choice, using HyDRA routing that achieves 72.5% cost savings while maintaining quality.
Summary
Eliminates model selection friction in long agentic sessions and cuts token waste by matching task complexity to model capability. Prompt caching and deferred tool loading mean your context budget goes toward actual work, not repeated definitions.
Why it matters
Eliminates model selection friction in long agentic sessions and cuts token waste by matching task complexity to model capability. Prompt caching and deferred tool loading mean your context budget goes toward actual work, not repeated definitions.
Implementation verdict
Replaces manual model picker with automatic routing already live in VS Code, github.com, and mobile. Requires no developer action to enable—Auto is the default. Worth using now; Free and Student plans consolidating around it as only option. Cache-aware routing prevents mid-conversation thrashing that would negate savings.
Sources
Dev Signal
Get briefs like this in your inbox — free, 3x a week.
100+ sources compressed into one 4-minute read. Ranked, cited, implementation-ready.