#gemini

Google has released Gemini 4 Hydrogen to replace Gemini 3.8 Flash. Its overall score is slightly above Argon, it runs about 2.5 times faster, and it has a free tier in AI Studio and the Gemini API, with paid use at $1.50 per million input tokens. We cover the benchmarks, pricing, where to use it, how to migrate from older models, and a prompt you can give your AI agent to switch models for you.

Google's Gemini Decisions API and the new Gemini Decision 1 model handle closed questions: yes or no, pick one, or score on a scale. Up to 1000 questions per request, about 0.2 seconds per response, and free output. Useful for choosing tools for an AI agent, routing requests, and running safety checks. Includes a prompt you can hand to your AI agent to try it.

Over two days I moved my Gemini subscription from Ultra down to Pro, then back up to the top tier because of Gemini 4 Carbon. What hit me hardest was how it writes copy without the AI feel. Includes a quick test for deciding whether to upgrade.

Gemini 4 Carbon is now open to everyone through the paid API and Google AI Ultra. It's built for long-running agent work and cybersecurity. Here's how it splits work with Argon, when the price doubles, and what Antigravity's /swarm does.

A beginner's guide: set a role and constraints first, describe the goal as the finished result, ask step by step, add a line against made-up facts, then have the AI score its own answer and revise it. All five rules come with copy-ready wording and one combined template.

A beginner tutorial: install the desktop app, set the working directory, permission mode and Browser Subagent before you start, then learn common commands like /plan, /boost and /browser, connect Notion and Obsidian, and use the Flash model to save quota.

A prompt I have refined over a long period on ChatGPT and Gemini. It makes the model give the answer first, attach conditions to its judgments, search first for time-sensitive information, and end with a next step. Includes a simplified full text and usage instructions.

Turn a 5-second talking-head line into a halftone paper-collage assembly animation: design the visual metaphor first, and leave the paid video generation to the end behind three checkpoints. Includes prerequisites, step-by-step instructions and FAQ.

Use when a user wants to turn a roughly 5-second spoken script line, an opinion, or an abstract concept into a paper collage animation with matching visuals. Based on the open-source gbro-collage-broll (MIT): enforces three confirmation gates, and only confirmed items go into video generation; the output is vertical, 5 seconds, and silent; video is billed per use to the user's own Gemini key. Use case: Have the agent turn a spoken line into a halftone paper-collage assembly animation B-roll: it proposes a metaphor first, then a still frame, and finally generates the video, with your confirmation at every step.

A breakdown by use of what Google AI Ultra bundles: Colab compute, monthly Cloud credits, Flow image and video quotas, Antigravity coding quotas, 30TB of storage and various memberships, plus how the quotas are calculated separately. The list comes from materials provided by users; the official plan page is the reference.