GEMINI LABJP
CLI — As of Jun 18, Gemini CLI and the Gemini Code Assist IDE extensions stop serving AI Pro/Ultra and free individual users; Antigravity CLI is the successorFLASH — The Gemini 3.5 series begins with 3.5 Flash, built for agents and coding with strength on long-horizon tasksDEEPTHINK — Gemini 3 Deep Think is rolling out to Google AI Ultra as the top reasoning mode for math, science, and logicAPP — The Gemini app gains a Daily Brief, a redesigned interface, the Gemini Omni video model, and a personal agent called Gemini SparkDESIGN — A new design language, Neural Expressive, rebuilds the experience for richer visuals and faster switching between modalitiesULTRA — Google AI Ultra bundles top model access, Deep Research, Veo 3 video, and a 1M-token context windowCLI — As of Jun 18, Gemini CLI and the Gemini Code Assist IDE extensions stop serving AI Pro/Ultra and free individual users; Antigravity CLI is the successorFLASH — The Gemini 3.5 series begins with 3.5 Flash, built for agents and coding with strength on long-horizon tasksDEEPTHINK — Gemini 3 Deep Think is rolling out to Google AI Ultra as the top reasoning mode for math, science, and logicAPP — The Gemini app gains a Daily Brief, a redesigned interface, the Gemini Omni video model, and a personal agent called Gemini SparkDESIGN — A new design language, Neural Expressive, rebuilds the experience for richer visuals and faster switching between modalitiesULTRA — Google AI Ultra bundles top model access, Deep Research, Veo 3 video, and a 1M-token context window
TAG

model-routing

1 articles
Back to all tags
Related:
gemini1gemini-api1shadow-evaluation1cost-optimization1production1
Gemini API/2026-06-17Advanced

Keep Your Flash-to-Pro Routing Threshold Honest with Shadow Re-evaluation

A Flash-generates, Pro-on-low-confidence router starts drifting the moment you hand-pick its threshold. This is a working build of a loop that samples your kept-Flash outputs, scores them against Pro, and recalibrates the threshold from a quality budget.