●SEARCH — File Search grounding now adds media_id for visual citations and page numbers, so you can trace the exact source●API — Event-driven Webhooks replace polling for the Batch API and long-running operations●DEPRECATION — Two image preview models (e.g. gemini-3.1-flash-image-preview) shut down June 25; migrate dependent automation now●MODEL — Gemini 3.5 Flash is GA, beating 3.1 Pro on nearly every benchmark while running 4x faster●AGENTS — Managed Agents are in public preview on the Gemini API, running autonomous agents in isolated Linux sandboxes●STUDIO — Google AI Studio can now generate Android apps from natural-language prompts●SEARCH — File Search grounding now adds media_id for visual citations and page numbers, so you can trace the exact source●API — Event-driven Webhooks replace polling for the Batch API and long-running operations●DEPRECATION — Two image preview models (e.g. gemini-3.1-flash-image-preview) shut down June 25; migrate dependent automation now●MODEL — Gemini 3.5 Flash is GA, beating 3.1 Pro on nearly every benchmark while running 4x faster●AGENTS — Managed Agents are in public preview on the Gemini API, running autonomous agents in isolated Linux sandboxes●STUDIO — Google AI Studio can now generate Android apps from natural-language prompts

TAG

subrequest

1 articles

← Back to all tags

gemini-api¹ cloudflare-workers¹ edge-runtime¹ observability¹

◈ Gemini API/2026-06-24Advanced

When Gemini API Quietly Dies on the Edge from Subrequest Limits — Field Notes on Budgeting What's Left

Running Gemini API on Cloudflare Workers is calm until traffic rises or a tool chain deepens, and then it fails on the subrequest limit. Here are the instrumentation patterns I use to measure per-request consumption and treat it as a budget, drawn from the sites I run as an indie developer.