{"slug": "reachpad-now-includes-free-gemma-4-31b-and-gemini-3-6-flash", "title": "Reachpad now includes free Gemma 4 31B and Gemini 3.6 Flash", "summary": "Reachpad now includes free access to Gemma 4 31B and Gemini 3.6 Flash coding models on every pad, usable through OpenCode without an API key. The models are included with the pad, with a daily allowance resetting at midnight UTC, and the provider key is kept off customer machines via a revocable credential.", "body_md": "blog\n\n# Free coding models on every pad\n\nEvery reachpad now includes two models you can use through OpenCode without bringing an API key: Gemma 4 31B and Gemini 3.6 Flash. Model usage is included with the pad.\n\n## What is included\n\nOpenCode comes preconfigured with both models. Open it, choose the reachpad provider, and send a prompt. There is no Google account to connect and no model bill to set up.\n\n`Gemma 4 31B`\n\nis the default reachpad model in OpenCode.`Gemini 3.6 Flash`\n\nis available from the same model picker and uses the same included allowance.\n\nClaude Code and Codex are still installed and kept current. Those tools use your own accounts, as they did before. The two included models are another option, not a replacement for an agent setup that already works for you.\n\n## Why the pad includes models\n\nA development environment is not ready for an agent if the first task is provisioning a provider account and putting its key into a shell. That setup is reasonable when you have settled on a provider. It is a poor first five minutes when you want to hand an unfamiliar repository to a model and see what it does.\n\nThe included models make the first prompt part of the pad. Clone a repository and open OpenCode. Ask it to explain or change the code. If one model gets stuck, switch to the other without changing credentials or moving the working tree.\n\n## How the provider key stays off the pad\n\nWe do not copy a shared upstream key onto customer machines. Each pad receives a revocable credential scoped to its owner. OpenCode presents that credential to the reachpad model gateway, which checks the allowance and adds the upstream key only while relaying the request.\n\nThe gateway meters bytes at the pipe instead of parsing prompts or responses. That gives us a daily ceiling for a runaway agent loop without adding application code that reads the conversation. The upstream key remains at the gateway, and a credential can be revoked without rebuilding the pad.\n\n## What free means\n\nThere is no per-token charge for these two models. Usage is part of every pad and does not require a separate model subscription. A daily allowance resets at midnight UTC, so one broken loop cannot consume an unbounded amount of inference. OpenCode reports a quota response if the pad reaches that ceiling.\n\nThe included models accept text today. Bring your own provider account when a task needs a different model or input type.\n\n## Try it on a pad\n\nThe two models are available on new and existing pads. See the [pad and workspace trial details](/pricing), or [create an account](/sign-up) to start.", "url": "https://wpnews.pro/news/reachpad-now-includes-free-gemma-4-31b-and-gemini-3-6-flash", "canonical_source": "https://reachpad.dev/blog/free-models", "published_at": "2026-08-13 21:12:03+00:00", "updated_at": "2026-08-13 21:44:57.091806+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "generative-ai", "ai-products", "developer-tools"], "entities": ["Reachpad", "Gemma 4 31B", "Gemini 3.6 Flash", "OpenCode", "Claude Code", "Codex"], "alternates": {"html": "https://wpnews.pro/news/reachpad-now-includes-free-gemma-4-31b-and-gemini-3-6-flash", "markdown": "https://wpnews.pro/news/reachpad-now-includes-free-gemma-4-31b-and-gemini-3-6-flash.md", "text": "https://wpnews.pro/news/reachpad-now-includes-free-gemma-4-31b-and-gemini-3-6-flash.txt", "jsonld": "https://wpnews.pro/news/reachpad-now-includes-free-gemma-4-31b-and-gemini-3-6-flash.jsonld"}}