Noob
Kick the tires, ship small fixes, and feel the dragon without feeding it your whole budget.
MWS IDE
Blazing Fast AI Coding You Can Afford
Welcome to Mithrandir: zero code retention, more tokens, and the Dragon model family. Dragon Flash, Dragon Pro, and Dragon Thinkmaxing keep your coding fast, private, and affordable.
Pricing
Monthly Dragon token plans for MWS IDE
Stop getting f***** by surprise AI Coding bills, tiny token pools, confusing pricing, and rolling-window lockouts that make you wait. Mithrandir IDE gives you transparent monthly Dragon token plans, more room to run, and maximum performance so you can keep building, powered by our proprietary system for using hardware more efficiently.
Popular
Starter
For solo devs who live in the IDE and want serious daily firepower at a sane price.
Builder
Built for makers in motion: big refactors, agent runs, and fewer pauses when momentum hits.
Pro
For power users running deep sessions, large codebases, and high-stakes builds all week.
Supermax
For the maniacs pushing Dragon Thinkmaxing hardest: maximum runway, maximum speed, no tiny-box energy.
Founder note
We built Mithrandir because we had to.
The compute crunch made building with the best AI models astronomically expensive. We were addicted to building, but priced out of every AI coding system that could actually keep up. At the same time, we lived with the fear that the big model companies would turn our private code into training data. So we invented a more efficient way to code with frontier AI, built it for ourselves, and now we are sharing it with every builder who refuses to slow down.