Pricing.
You are in full control. Handler never limits what you can do, and every way of running it is set up for you. Pick any of these, and switch whenever you like.
- Built in. Handler installs a speech model and runs it on your computer. Free forever.
- Your own local setup. LM Studio, Ollama or another model you run on your computer; Handler finds it for you. Free.
- What you already pay for. Claude Code, Codex with your ChatGPT plan, Gemini CLI, GitHub Copilot or OpenCode, or an API key from OpenAI, DeepSeek, OpenRouter, Groq, Mistral or any other provider.
- JUC, in one click. Sign in with your email and we run it for you. Free through 2026*; see pricing for 2027 on.
JUC hosted plans
Every plan is free through the end of 2026*. After that, pay monthly, or yearly and get two months free.
Free
$0
- JUC hosted speech and language models, free through 2026*
- Built-in local speech, your own setup and your own providers, always free
Budget
$2/mo
or $20 a year
- One $2 a month hosted pool, no daily cap
- Everyday models picked for value
- Runs low? Pause, or add one more block. Never a surprise bill.
Standard
$5/mo
or $50 a year
- One $5 a month hosted pool
- Named, reliable models
- Web research with live sources
Pro
$10/mo
or $100 a year
- One $10 a month hosted pool
- Premium frontier models, and your pick
- Priority at peak times
Max
$20/mo
or $200 a year
- Our most generous allowances, for heavy use across all our services
- Premium frontier models, and your pick
- Priority at peak times
Enterprise
Talk to us
Volume inference, custom limits and routing, invoiced. Contact for availability: support@julianutility.com.
When a plan runs low
Your plan's price is your runway. When it runs low you choose, per account:
- Pause: usage stops at your runway until next month. A hard stop, never a surprise bill.
- Bump: continue into one more block of your plan's size; we bill that block the moment it starts, and you're never floating more than one payment.
- Pay-as-you-go: meter past your pool at the posted rates, for as long as you enable it.
Free alpha access through 2026; no paid subscription starts automatically. * Free hosted inference is offered through December 31, 2026, as long as we are able to serve it. Beta pricing is planned and is not active.
Source is not available during the alpha. We plan to make it available after.