GEMINI LABJP
NANOLITE — Nano Banana 2 Lite is here: Google's fastest and most cost-efficient Gemini Image model, made for running lightweight image generation cheaplyOMNIFLASH — Gemini Omni Flash is in public preview, a natively multimodal model that lets enterprises and developers build custom, dynamic video workflowsAGENTS — Managed Agents expand with background: true for async server-side runs and polling, remote MCP server integration, and refreshing credentials across interactionsMEMORY — The Memory Bank IngestEvents API is generally available, decoupling event ingestion from memory generation so you can stream content continuouslyTHROUGHPUT — Provisioned Throughput now lets you submit up to seven pending orders for the same model and regionDEPRECATE — Image generation models shut down on August 17, and the Grok 4.1 family on the Gemini Enterprise Agent Platform on August 20NANOLITE — Nano Banana 2 Lite is here: Google's fastest and most cost-efficient Gemini Image model, made for running lightweight image generation cheaplyOMNIFLASH — Gemini Omni Flash is in public preview, a natively multimodal model that lets enterprises and developers build custom, dynamic video workflowsAGENTS — Managed Agents expand with background: true for async server-side runs and polling, remote MCP server integration, and refreshing credentials across interactionsMEMORY — The Memory Bank IngestEvents API is generally available, decoupling event ingestion from memory generation so you can stream content continuouslyTHROUGHPUT — Provisioned Throughput now lets you submit up to seven pending orders for the same model and regionDEPRECATE — Image generation models shut down on August 17, and the Grok 4.1 family on the Gemini Enterprise Agent Platform on August 20
ARTICLES

All Articles

All (733) Gemini Basics (57) Dev Tools (106) API & SDK (405) Advanced (110) Workspace (37) Updates (18)
API & SDK/2026-03-19Advanced

Gemini 2.5 Pro × FastAPI: Building a Production-Ready AI Backend

Learn how to build a production-ready AI backend by combining Gemini 2.5 Pro with FastAPI, covering streaming, rate limiting, Function Calling, cost optimization, and Docker deployment.

API & SDK/2026-03-19Advanced

Google Personal Intelligence × Gemini API — Build Personalized AI Experiences

Personal Intelligence enables Gemini to access Gmail, Google Photos, Calendar data for personalized responses. Implement Grounding with Google Services for custom apps.

API & SDK/2026-03-14Intermediate

Estimating Gemini API Costs Before You Send — count_tokens in Practice

Use Gemini's free count_tokens call to measure input tokens and costs before each request, then cut spend with caching and model selection.

API & SDK/2026-03-14Advanced

Gemini Advanced Document Processing — PDF Analysis, Table Extraction & Automated Review

Advanced document processing with Gemini's multimodal capabilities. Covers full PDF analysis, table and chart extraction, multi-document comparison, automated contract and invoice review. Includes File API integration and context caching patterns.

API & SDK/2026-03-14Advanced

Gemini Code Execution API: to AI-Generated Code Execution

Master the Gemini Code Execution API. Execute Python code generated by AI in a secure sandbox, perform complex calculations, and automate data analysis tasks.

API & SDK/2026-03-14Advanced

Gemini 1M Token Long Context Strategies — Production Patterns for Large Document Processing

Master Gemini 2.5 Pro's 1M token context window for production workloads. Covers context caching, chunking strategies, RAG comparison, cost optimization, and real-world codebase + PDF corpus analysis.

API & SDK/2026-03-14Advanced

Fine-Tuning Gemini: Building Specialized Models for Domain-Specific Applications

Complete guide to fine-tuning Gemini models. Learn dataset preparation, training strategies, evaluation metrics, and production deployment for custom AI.

API & SDK/2026-03-12Intermediate

Reading Gemini API Logs by What Survived — Field Notes on Logging & Datasets

Use the Gemini API logging and datasets tool from a results-first angle — not token counts or latency, but whether each output actually survived to publication. Includes tying log review to spend caps and API key hygiene.

API & SDK/2026-03-11Intermediate

Gemini API Quickstart — Getting Started with Python and TypeScript

Step-by-step guide to set up and use Gemini API with Python and TypeScript SDKs