◉GEMINI LABJP
●SUNSET — Four days until the image models shut down: Imagen 4 and the Gemini 3 Image family stop on August 17, so line up your replacements now●FLASH — Gemini 3.6 Flash is generally available, with better token efficiency and stronger code and agentic planning at a lower price than 3.5 Flash●LITE — Gemini 3.5 Flash-Lite also reached GA as a low-latency, cost-conscious subagent option aimed at high-volume automation●OMNI — Gemini Omni Flash, a new video model, is now reachable from the Gemini app, Flow, AI Studio, and the Gemini API●LOGS — Developer logs now cover the Interactions API, with supported calls visible in the AI Studio dashboard●ROBOTICS — gemini-robotics-er-1.6-preview shuts down on August 31, so this is the window to plan the migration●SUNSET — Four days until the image models shut down: Imagen 4 and the Gemini 3 Image family stop on August 17, so line up your replacements now●FLASH — Gemini 3.6 Flash is generally available, with better token efficiency and stronger code and agentic planning at a lower price than 3.5 Flash●LITE — Gemini 3.5 Flash-Lite also reached GA as a low-latency, cost-conscious subagent option aimed at high-volume automation●OMNI — Gemini Omni Flash, a new video model, is now reachable from the Gemini app, Flow, AI Studio, and the Gemini API●LOGS — Developer logs now cover the Interactions API, with supported calls visible in the AI Studio dashboard●ROBOTICS — gemini-robotics-er-1.6-preview shuts down on August 31, so this is the window to plan the migration
TAG

gemini-3-5-flash

3 articles
← Back to all tags
Related:
production2agent1long-horizon1architecture1rag1cost-optimization1caching1gemini-embedding-21gemini1gemini-api1model-migration1
⬡ Gemini Advanced/2026-06-18Advanced

Restarting a Long Agent Run From Where It Broke — A Step-Ledger Design for Gemini 3.5 Flash Long-Horizon Tasks

Gemini 3.5 Flash is good at long-horizon tasks, but when a 40-step run dies on step 29, you usually start over. An append-only step ledger gives you resume, idempotency, and audit in one place. Here is the design with working Python and measured results.

◈ Gemini API/2026-06-13Advanced

Rebuilding a Three-Layer RAG Cache After Migrating to Gemini 3.5 Flash

When Gemini 2.0 Flash was retired, I rebuilt my RAG caching stack around 3.5 Flash. Here are the working implementations for response, semantic, and embedding caches, measured hit rates from production, and how self-managed caching divides the work with the API's Context Caching.

◈ Gemini API/2026-06-13Advanced

Where to Adopt Gemini 3.5 Flash GA First — Per-Workload Evaluation and a Staged Rollout with a Model Router

How I migrated production workloads to Gemini 3.5 Flash GA in stages: a per-workload evaluation harness, measured results, an env-based model router, and rollback design.