◉GEMINI LABJP
●SUNSET — The image generation models shut down tomorrow, August 17: imagen-4.0-generate-001, ultra, fast, and the Gemini 3 Image family, and calls will fail with a hard error●GA — Gemini 3.7 Flash reached general availability on August 13, with substantial gains in software engineering, web development, and agentic work at an introductory price through December 31●APPS — On August 12 Google widened the set of apps you can connect to Gemini, adding Granola, Otter.ai, and Wix alongside OpenTable, Ticketmaster, iHeartRadio, and Pandora●SAMPLING — The temperature, top_p, and top_k sampling parameters are now deprecated, so migrating to a newer model means revisiting those assumptions●ROBOTICS — Gemini Robotics ER 2 is in public preview, and the older gemini-robotics-er-1.6-preview shuts down on August 31●NOTEBOOK — NotebookLM Enterprise has been renamed Gemini Notebook Enterprise, and the Gemini Enterprise mobile app is now generally available●SUNSET — The image generation models shut down tomorrow, August 17: imagen-4.0-generate-001, ultra, fast, and the Gemini 3 Image family, and calls will fail with a hard error●GA — Gemini 3.7 Flash reached general availability on August 13, with substantial gains in software engineering, web development, and agentic work at an introductory price through December 31●APPS — On August 12 Google widened the set of apps you can connect to Gemini, adding Granola, Otter.ai, and Wix alongside OpenTable, Ticketmaster, iHeartRadio, and Pandora●SAMPLING — The temperature, top_p, and top_k sampling parameters are now deprecated, so migrating to a newer model means revisiting those assumptions●ROBOTICS — Gemini Robotics ER 2 is in public preview, and the older gemini-robotics-er-1.6-preview shuts down on August 31●NOTEBOOK — NotebookLM Enterprise has been renamed Gemini Notebook Enterprise, and the Gemini Enterprise mobile app is now generally available
TAG

Model selection

5 articles
← Back to all tags
Related:
Gemini API3Pricing1Cost design1Indie development1Gemini 3.5 Flash1model routing1cost optimization1automation1indie developer1Gemini 3 Pro1Gemini 2.5 Pro1Indie Developer1
◈ Gemini API/2026-08-16Intermediate

Moving to the Batch Tier Cancels Out the Gemini 3.7 Flash Price Increase Exactly

Introductory pricing for Gemini 3.7 Flash ends on December 31, 2026, and the rate doubles the next day. Here is which models are affected, which are not, and how to project your January bill from the usage you already have.

⟐ Gemini Dev/2026-06-20Intermediate

Routing Gemini by Pipeline Stage: Draft on Flash, Finish on the Top Tier

A record of reworking which Gemini model handles which stage of an automation pipeline, prompted by the general availability of Gemini 3.5 Flash and the rollout of 3.1 Flash-Lite. Includes a small router that splits work into draft, classify, and finalize stages, how the cost picture changes, and the guardrails I settled on.

⬡ Gemini Advanced/2026-05-28Intermediate

Three Weeks of Running Gemini 3 Pro and 2.5 Pro Side by Side on Wallpaper Category Classification — An Implementation Memo

Notes from running Gemini 3 Pro and 2.5 Pro in parallel for three weeks on the image classification pipeline of my iOS and Android wallpaper apps — cost, accuracy, and latency observations from an indie developer.

◈ Gemini API/2026-04-24Advanced

gemini-2.5-pro-latest— Model Aliases, Parameters, and Production Patterns

A deep practical guide to calling the Gemini API with the `gemini-2.5-pro-latest` alias. Covers model pinning, parameter tuning, timeouts, streaming, structured output, and a production-grade checklist.

◉ Gemini Basics/2026-03-14Beginner

Choosing a Gemini Model Without Second-Guessing — A Cost, Speed, and Quality Framework

How to pick between Gemini 2.5 Pro / Flash / Flash Lite / Gemini 3 Pro / Flash across cost, speed, and quality. Includes correct google-genai SDK code and the decision rules I use when running automation in production.