blog

Gemini 3.7 Flash offered for free

19 August 2026

Written when every reachpad was a pad. Pads are closed to new customers, and these models reach you through OpenCode, which ships on a pad. Signing up today gives you reachpad apps instead: your coding agent publishes a page, a document or a fetch handler, and each one is live at a link you decide who can open. See publishing an app.

Gemini 3.7 Flash is now included with every pad. It joins Gemma 4 31B and Gemini 3.6 Flash: three models in OpenCode, no provider account, no key to paste, usage included with the pad.

What you get

The OpenCode model picker shows Gemma 4 31B, Gemini 3.6 Flash, and Gemini 3.7 Flash on every pad.

How to use it

There is nothing to install and no provider key to paste. The models are ready before you open a shell. Ask OpenCode what the pad has:

$ opencode models

That prints one line per model, provider first. Run a one-shot against 3.7 with the same id:

$ opencode run -m reachpad-gemini-3-7/gemini-3-7-flash "explain this repo"

In the OpenCode TUI, /model opens the picker and the status bar shows which model is active. Check it before sending a prompt because each model is a separate entry. To pin a default, set model in ~/.config/opencode/opencode.json; a pad keeps that choice.

Claude Code and Codex are installed on every pad and keep using your own accounts. The included models are another option, not a replacement for an agent setup that already works for you.

What is included

There is no per-token charge and no separate model subscription. Usage is part of the pad, with a daily allowance that resets at midnight UTC so one runaway agent loop cannot consume an unbounded amount of inference. OpenCode surfaces a quota response if a pad reaches that ceiling.

Provider keys are never copied onto a pad. Usage is metered without storing prompts or responses.

The included models accept text today. Bring your own provider account when a task needs a different model or input type.