Run an AI Assistant on Your Claude Subscription
Most AI assistants assume you'll paste in a pay-per-token API key and watch a meter run. But if you're a developer, you may already pay a flat monthly fee for a Claude plan.Jarvis AI Assistant can run on that subscription directly — so your assistant uses the plan you've already got, with no separate API bill.
Using the CLI you already have
Claude ships a command-line agent, Claude Code, and Jarvis can drive it as a model backend. When you route to it, the request goes through that CLI on your machine — authenticated by your existing login — instead of a metered API endpoint. No key to paste, no per-token charge.
- Claude Code — runs on your Claude subscription (e.g. a Max plan).
To keep it fast, Jarvis holds a warm process so there's no cold-start penalty every time you ask — the CLI is already up and waiting.
Mix subscriptions, keys, and local — freely
This isn't all-or-nothing. The same router that reaches Claude Code also handles pay-per-use API keys (Claude, GPT, Gemini, Groq, OpenRouter) and fully local Ollama models. You can lean on your flat-fee subscription for heavy work, drop to a free local model for private tasks, and add a key only if you want a model your subscription doesn't cover.
A nice side effect: routing through a subscription CLI is effectively $0 per request from the assistant's point of view, which makes it a natural default for high-volume, everyday use.
How Jarvis picks
You can name a model per message with a prefix, or set a default and forget it. The subscription CLI is always opt-in — Jarvis won't silently route through it unless you choose it — so there are no surprise interactions with your plan. And if a backend is unavailable, the router falls back along a chain so you still get an answer.
Why it matters
The usual objection to a powerful agent is cost: "if it runs 100 tool-driven requests a session, the API bill will hurt." Running on a flat-fee subscription you already pay for removes that anxiety — heavy usage doesn't translate into a scary invoice, so you can actually let the assistant do a lot of work. What Jarvis itself costs is on the pricing page — it's separate from whatever you pay your model provider.
Bring the plan you already have. Your assistant runs on your Claude subscription through Claude Code — no API key, no meter, no markup.
Stop reading. Start commanding.
Install Jarvis from the Microsoft Store, add a key (or run fully local), and give it a real task.
New to Jarvis? Read the setup guide.