API / SDK
Practical guides to the Gemini API and SDKs — quickstarts, Function Calling, structured output, streaming, cost optimization, and troubleshooting.
Classifying 8,000 App Reviews Overnight with Gemini Batch API — and Moving Polling to Webhooks
Implementation notes on clearing ~8,000 backlogged app reviews from six iOS/Android apps with the Gemini Batch API in a single night — now extended with the June 2026 event-driven Webhooks that replace the morning polling step. Real cost and runtime numbers, composite-key design, hung-job triage, and deprecation discipline, with working code.
Track Gemini API Costs in Production with usageMetadata — A Per-Request Logging Pattern That Reconciles With Your Bill
A production pattern for capturing Gemini API's usageMetadata per request to attribute spend by endpoint, user, and model — hardened for the 3.5 Flash GA era where the default model can shift under you. Covers pricing keyed on resp.model_version and a nightly audit that flags model drift and unknown models before the invoice does.
Gemini API Grounding × Structured Output Guide — Turn Web Search Results into Typed JSON Data
Combine Gemini API Grounding with Google Search and Structured Output to extract real-time web information as type-safe JSON data. Practical implementation patterns included.
Catching Gemini Model Deprecations in CI Before They Bite
Build a small guard that scans your codebase for hardcoded Gemini model IDs, cross-checks shutdown deadlines, and turns CI red before a model quietly disappears.
Building a Type-Safe AI Backend with Gemini API, tRPC v11, and Prisma — Real-Time Streaming, Auth Middleware, and Production Deployment
Learn how to integrate Gemini API streaming into tRPC v11 subscriptions, persist conversations type-safely with Prisma, and handle auth middleware, rate limiting, and common production pitfalls — all with working code examples.
Catch Near-Duplicate Images Before You Publish with gemini-embedding-2
This is about removing near-duplicates, not image search. Use gemini-embedding-2 multimodal embeddings to vectorize images, cluster them, and build a pre-publish gate — with working code and threshold guidance.
Generate Japanese and English in One Structured Call to Stop Term Drift
Generating Japanese and English versions separately makes terminology drift article by article. Pair both languages in one Gemini 3.5 Flash structured-output call, pin a glossary, and detect drift mechanically — with measured results.
When Your pgvector Search Quietly Gets Worse — Field Notes on Protecting Recall with Gemini Embeddings
A semantic search built on Gemini Embeddings and PostgreSQL pgvector tends to lose precision over months without throwing a single error. These are field notes on the real causes — model pinning, operator/index mismatch, HNSW reindexing, and recall collapse under filters — with working code.
Your Managed Agents Bill Has a Second Axis: Drawing a Budget Boundary Around Sandbox Runtime
Managed Agents in public preview bills for tokens and for how long its Google-hosted sandbox stays alive. A single hung run quietly drains your budget on that second axis. Here is a working Python design for wall-clock caps, idle teardown, and a concurrency ceiling.
Building location-aware AI with Gemini's Google Maps grounding: pricing and the source-display rules tutorials skip
How to ship a 'recommend something nearby' feature with Gemini API's Google Maps grounding, with the $25/1K cost design and the source-display obligations laid out for indie developers.
Switching Types Per Input Kind in Gemini Structured Output — Notes on anyOf Discriminated Unions
Classifying mixed input kinds through one endpoint leaves a flat schema full of nulls. Here is how I switch types per kind with an anyOf discriminated union and parse it safely with Pydantic and Zod.
Stop a Batch Before It Overspends — A Budget Gate Built on countTokens That Survives a Default-Model Swap
Nightly batches overspend because you only learn the cost after billing. Starting from countTokens, this guide builds a budget gate that folds in thinking tokens and keeps your estimate intact even when the default model changes underneath you.
When Revenue and Cost Don't Line Up in a Gemini-Powered Niche SaaS — Field Notes on Metering Usage and Reconciling with Stripe
In a niche SaaS built on the Gemini API, monthly revenue is visible but per-user usage cost is not, so your margin stays a mystery until month-end. These notes cover a metering layer that converts tokens to money in real time, monthly reconciliation against Stripe, early detection of unprofitable users, and idempotent webhooks.
Moving My Automation Off the Gemini CLI Before the June 18 Shutdown
On June 18, the Gemini CLI stops responding for hosted plans. Here is how I moved unattended scripts that called gemini from the shell over to the google-genai SDK, with structured output, retries, and cost measurement built in.
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.
Watching the 'Voice' of Generated Text: Catching a Silent Default-Model Swap Through Style Drift
When the default model changes over your head, the output can stay factually correct while its voice quietly shifts. This walks through fingerprinting the style of generated text and detecting drift statistically, with a dependency-free implementation you can drop into your pipeline.
Before You Let a Managed Agent Ship: Designing Your Own Acceptance Gate
Let the public-preview Managed Agents generate files and broken artifacts will flow straight into production. Here is how to build a verification gate that artifacts must pass before you accept them, with runnable Python and a rejection-feedback loop.
Wiring Gemini Managed Agents Into Your Automation: Keeping Conversation State and Environment State Apart
Managed Agents spin up a Linux sandbox, run an agent loop, and return a result in a single API call. The first thing that trips you up when moving off a hand-rolled loop is that conversation state and file state are two separate things. Here's that design, worked through live.
Don't Break When the Default Model Moves: A Startup Capability-Probing Layer for Gemini
Pinning a model name breaks on deprecation; trusting the default breaks when the weights swap silently. This is the design I settled on: probe what the served model can actually do at startup, then build every request from that answer. Includes runnable Python.
Your Gemini Live API session forgets the conversation every time it reconnects — field notes on token refresh and session resumption
Why a Gemini Live API WebSocket drops the conversation and the user's in-flight speech on every reconnect, and how to close the gap with single-use ephemeral tokens, session resumption handles, and the goAway warning.
Put Help Docs and Screenshots in One File Search Store and Return Answers That Cite the Image Too
Your text help docs and your screenshots live in separate stores, so a single question can never return both the steps and the matching screen. With gemini-embedding-2 going multimodal in File Search, here is how I merged them and returned the cited screenshot alongside the answer.
When the Default Model Silently Upgrades: Catching Prompt Regressions in Numbers
Gemini 3.5 Flash is now the default and you can no longer turn it off. Assuming your responses can shift without you touching the prompt, here is how to bundle prompt, model, and sampling into one variant and catch regressions with canaries and an LLM judge — in working code.
Defending Against Prompt Injection When You Pass External Text to the Gemini API
User reviews, scraped articles, and other untrusted text are the entry point for indirect prompt injection when you feed them to the Gemini API. Here is a prioritized, code-backed defense you can drop into a production pipeline: trust-boundary isolation, schema constraints, a two-stage screening pass, and output sanitization.
Permission-Aware RAG — Designing Gemini Search That Only Cites What the User Is Allowed to See
The day you add RAG to internal search, drafts and finance memos nobody should see start leaking into answers. This is a production design — metadata filtering, defense in depth, and audit logging — for letting Gemini search while respecting permissions, with working code.
How a Deep Think Verification Step Tripled My API Bill, and How thinking_level Got It Back
After wiring API-accessible Gemini 3 Deep Think into my output-verification step, my projected monthly cost jumped roughly 3x. Here is the implementation record of capping it with thinking_level and a cost guardrail, then settling on a two-stage design with Flash.
Generate With Flash, Escalate to Deep Think Only When Unsure: A Two-Stage Pipeline
With Deep Think opening up on the API, the move is not to route every request through the heavy model but to have Deep Think verify only when Flash's output looks shaky. Here is the cost reasoning and working code.
Keeping Gemini API's Default-Model Shift From Becoming an Incident — Pinning Model IDs and Detecting Silent Upgrades in Production
When the default model quietly moves up, your output length, reasoning behavior, and cost change with zero code edits. This guide shows how to pin model IDs in a single source of truth and verify the effective model from the response to detect default changes.
Controlling Image Tokens with the Gemini API media_resolution Setting — Tuning Batch Image Classification by Measurement
media_resolution, introduced in the Gemini 3 line, switches how many tokens an image input consumes across three levels. Through real batch-classification measurements, this guide shows how to balance cost and accuracy by assigning the right tier per task.
When Gemini API Cuts Your Response Off Mid-Sentence — Detecting finish_reason: MAX_TOKENS and Stitching the Continuation
Long-form generation that ends mid-sentence is usually finish_reason: MAX_TOKENS. This failure arrives as a quiet HTTP 200, no exception. Here is how to detect it, stitch a continuation to recover the full text, and avoid the thinking-token trap that makes it worse on 3.x models.
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.
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.
The Morning Gemini Generated Fine but the Publish Crashed — A 'Generation Outbox' So Expensive Output Is Never Lost
Generation succeeds, then the process dies right before publishing. The expensive output is gone, and you pay for the same generation again. Here is a 'generation outbox' that persists the output first and turns publishing into an idempotent follow-up, plus what it did for me during the June outage.
Reading a Night of Logs in Three Minutes — Building My Own Daily Brief for Ops With the Gemini API
Inspired by Gemini's Daily Brief, I built a pipeline that turns overnight operations logs into one morning email: collect, summarize with response_schema, render, deliver — with measured token counts and a fallback that kept working through the June outage.
Letting File Search's Multimodal Mode Find Wallpapers I Couldn't: A Field Report
I tested whether File Search's new multimodal retrieval (gemini-embedding-2) could replace category tags for finding one wallpaper among thousands. A 300-image trial, the walls I hit, and where semantic search actually fits — with working code.
Building an App Store Rejection Workflow with the Gemini API — From Structured Notices to Resolution Center Replies
How I use the Gemini API to parse App Store rejection notices into structured JSON, cross-check guidelines, draft Resolution Center replies, and run pre-submission checks as an indie developer.
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.
Retiring the Midnight Polling Loop — Rebuilding My Gemini Batch Monitoring Around Webhooks
A working log of migrating Gemini Batch API completion monitoring from 60-second polling to event-driven webhooks: static vs dynamic, signature verification, and real numbers.
Gemini's Preview Image Models Shut Down on June 25 — Code Diffs and Checks From an Actual GA Migration
How I moved my image pipeline off Gemini's preview image models before the June 25 shutdown — confirming GA model IDs, Python code diffs, regression checks, and a safe cutover order.
Gemini Interactions API: Fixing What Broke When the Legacy outputs Schema Was Removed on June 6
Google removed the Gemini Interactions API legacy outputs schema on June 6, 2026. A symptom-based walkthrough of migrating to steps and the new response_format.
Reverse-Engineering Empty Gemini API Responses with finish_reason — Triage, Retry Classification, and Monitoring
An empty response.text has three distinct failure layers — candidates, prompt_feedback, and finish_reason. Production code for detecting thinking-token starvation, classifying what is worth retrying, and monitoring your empty-response rate.