GEMINI LABJP
2.5ONLY — From the September 18 changelog: access to the 2.5 models is now limited to people who have actively used them. They are not deprecated and the API keeps serving them, while new projects are pointed at 3.5 Flash-Lite or 3.8 Flash3.8LIVE — Gemini 3.8 Live and 3.8 Live Extended Thinking went GA on September 15. Both are audio-to-audio models for the Live API, and the second keeps reasoning in the background during the call09/30 — gemini-omni-flash-preview shuts down on September 30, seven days away. Its successor, gemini-omni-1.1-flash, went GA on August 27ONCE — A report that "allow for this session" only lasts one call when the command contains a path has drawn 159 comments. The question underneath is how approvals should be scoped at allNEW — When a function call comes back as plain text, suspect the property names in your tool declaration firstHISTORY — Writing just three things outside the tool — what you settled on, the instructions you used, and why you redid something — keeps past work from disappearing with a model2.5ONLY — From the September 18 changelog: access to the 2.5 models is now limited to people who have actively used them. They are not deprecated and the API keeps serving them, while new projects are pointed at 3.5 Flash-Lite or 3.8 Flash3.8LIVE — Gemini 3.8 Live and 3.8 Live Extended Thinking went GA on September 15. Both are audio-to-audio models for the Live API, and the second keeps reasoning in the background during the call09/30 — gemini-omni-flash-preview shuts down on September 30, seven days away. Its successor, gemini-omni-1.1-flash, went GA on August 27ONCE — A report that "allow for this session" only lasts one call when the command contains a path has drawn 159 comments. The question underneath is how approvals should be scoped at allNEW — When a function call comes back as plain text, suspect the property names in your tool declaration firstHISTORY — Writing just three things outside the tool — what you settled on, the instructions you used, and why you redid something — keeps past work from disappearing with a model
TAG

Indie development

45 articles
Back to all tags
Related:
Gemini API33Gemini7Cost Optimization5Structured Output3File Search3Android3Python2operations2Memory Bank2Memory profiles2Model Routing2Image Generation2
Gemini API/2026-06-12Intermediate

Is Anyone Actually Using Your Gemini Feature? Measuring Acceptance, Regeneration, and Edit Distance

Token charts will not tell you whether users embrace a Gemini-powered feature. A practical design for measuring acceptance rate, regeneration rate, and edit distance with Swift and BigQuery, with two weeks of real numbers.

Gemini Advanced/2026-06-04Intermediate

Pre-Screening Wallpaper App Submissions with Gemini Vision: A Two-Week Field Memo

Before submitting a new batch of wallpapers, I spent two weeks running Gemini's image understanding as a first-pass filter for store review risk. What it caught, what it missed, and where a human still has to decide.

Gemini API/2026-06-03Beginner

Gemini Live API Audio Sounds Sped Up — Fixing the Sample Rate Mismatch

When Gemini Live API responses sound high-pitched and sped up, or come back full of noise, the cause is almost always that the 24kHz output is being played at a different sample rate. Here are the concrete fixes for both the browser and iOS.

Gemini API/2026-06-03Advanced

Reconciling Orphaned Gemini Files API Uploads Across a Fleet of Apps

Files API uploads quietly expire after 48 hours. Here's how I keep orphaned files and quota under control across six apps, using reconciliation against my own database and a scheduled cleanup job — written up as production notes from running wallpaper apps.

Gemini Dev/2026-06-03Intermediate

Three Weeks After Moving Firebase from CocoaPods to SPM with Gemini 3 Pro

Notes from migrating Firebase dependency management from CocoaPods to Swift Package Manager across my indie iOS apps. Where Gemini 3 Pro helped, where it did not, and how the setup felt after three weeks in production.

Gemini Advanced/2026-05-20Intermediate

Two Months With Gemini 2.5 Pro's 1M Context: What It's Actually Good (and Bad) At

An honest two-month review of using Gemini 2.5 Pro's 1M-token long context window on real work — organizing 12 years of indie-developer notes, cross-checking large MDX archives, and learning where short prompts still beat long ones.

Gemini API/2026-05-14Intermediate

3 Months Using Gemini API as My App Backend — An Indie Developer's Honest Review

I adopted Gemini API as the backbone for a new app and ran it in production for three months. Here is what the costs, latency, and quality actually looked like — and how I split work across Gemini, Claude, and GPT-4o.

Gemini API/2026-05-06Intermediate

One Month with Gemini 2.5 Flash: An Indie Developer's Honest Cost and Performance Report

Real cost, speed, and quality data from running Gemini 2.5 Flash across three indie apps for a full month. Includes free-tier usage patterns, Flash vs Pro decision criteria, and cost-minimizing Python code.

Gemini Advanced/2026-03-20Intermediate

Putting Gemini and Google Workspace to Work — Docs, Sheets, Drive, and an Apps Script That Actually Runs

Field notes on running Gemini inside Google Workspace as a daily process rather than a feature tour: where the side panel earns its keep, where you should drop down to the API, a working Apps Script that summarizes a Drive folder, and the checks that keep generated numbers out of your decisions.