Skip to content
Pricing

Every model. One subscription. Every token counted.

Try Capuchin free with the promo — no card. Pro includes unlimited Capuchin plus a Claude · Gemini · ChatGPT allowance that goes further here: lean local context and smart routing average ~$0.06 per frontier request. A hard spend cap means your invoice never surprises you.

One seat, every surface

You are not buying tools. You are buying a seat.

SurfaceIncluded in
MonkeysCode IDEEvery plan, including Free with your own keys
Code AgentEvery plan
CLIEvery plan, shipping shortly

Competitors in this category increasingly charge per product. We charge per person.

Free

$0/month forever

Full agentic IDE on all platforms — BYOK or local models. Try Capuchin free with the promo.

IDE, Code Agent and CLI included
Full agentic IDE (Win/macOS/Linux)
Local-first indexing — fully on your machine
Bring any model — BYOK or local/remote
Open VSX extensions + sideloading
Signed, replayable runs
Capuchin + frontier allowance
Background & scheduled agents
Team features
Download
Recommended

Pro

$20/month

Unlimited Capuchin + $20/mo of Claude · Gemini · ChatGPT included — one subscription replaces three.

Everything in Free
IDE, Code Agent and CLI included
Unlimited agentic usage on Capuchin*
$20/mo frontier allowance (Claude/Gemini/ChatGPT)
Live consumption dashboard
Per-task budgets + hard $0 spend cap
Background & scheduled agents
Priority queue
Team features
Start Pro

Pro+

$60/month

$60/mo frontier allowance, priority queue, more parallel agents.

Everything in Pro
IDE, Code Agent and CLI included
$60/mo frontier allowance (Claude/Gemini/ChatGPT)
Priority inference queue
More parallel agents
Maximum parallel & background agents
Early access to new models
Priority support
Go Pro+

Ultra

$200/month

For power users and frontier-heavy workflows.

Everything in Pro+
IDE, Code Agent and CLI included
Unlimited Capuchin — highest fair-use ceiling
$120/mo frontier allowance included
Maximum parallel & background agents
Priority inference queue + early access
Priority support
Go Ultra

Your allowance goes further here. Indexing and context-building happen on your machine, so frontier prompts carry only the relevant code — averaging ~$0.06 per request on the priciest model, with ~90% of context served from cache. Easy tasks route to Capuchin automatically. Budgets, a hard cap, and a live dashboard mean there are never surprises.

Recommended for teams

Team — $30/seat/mo

Everything in Pro, plus shared encrypted team index, roles, allowlists, version pinning, and centralized billing with usage by member, project, and model.

Start a team
Everything in Pro
Shared encrypted team index
Roles, allowlists & version pinning
Centralized billing + usage by member/project/model

The cheapest token is the one you don't pay us for.

Unlimited on Capuchin

We run our own model on our own infrastructure — generous usage is cheap for us, free at the margin for you.

BYOK frontier

Use Claude, Gemini, or ChatGPT on your own key and pay your provider directly. We don't mark up your tokens.

Local & self-host

Run Capuchin or any model on your own hardware and pay near nothing per token.

Hard cap

Set a ceiling; agents stop instead of billing you — the opposite of usage-based tools whose bills jumped 10–50× for power users.

Frequently asked questions

Can I try Capuchin for free?

Yes — claim the promo for free Capuchin access, no card required. On paid plans Capuchin is unlimited. The Free tier keeps the full IDE working forever with your own key (BYOK) or local models.

How does the frontier allowance work?

Claude, Gemini, and ChatGPT are included as a dollar allowance matching your plan price — $20/mo on Pro, $60/mo on Pro+, $120/mo on Ultra. A live dashboard shows consumption in real time, and a hard cap means you can never overspend. You can also BYOK for zero markup.

How do you make my allowance last?

Three ways. The on-device context engine sends only the relevant slices of your codebase — not whole files — so frontier requests average ~$0.06 even on the priciest model, with ~90% of context served from cache. Smart routing sends everyday work to Capuchin so frontier tokens are reserved for hard problems. And per-task budgets stop runaway agents before they burn your allowance.

Is Free time-limited?

No — the Free tier is built to actually be used, not as a time-gated trial. The full IDE, local models, and BYOK all keep working, forever.

Which models can I use?

Capuchin (ours), Claude, Gemini, ChatGPT, or your own — local or on your own server. BYOK on every tier.

What does 'unlimited' mean?

Unlimited Capuchin usage under a generous fair-use ceiling that only affects extreme automated volume. Ultra gets the highest ceiling.

Is the Code Agent included in my plan?

Yes — the Code Agent is included in every plan, including Free with your own keys. The CLI is coming soon and will also be included at no extra cost.

Can I run with no internet?

Yes — fully air-gapped on Enterprise / Self-Host.

Is it open source?

Open core, Open VSX, MIT framework underneath. Your code is yours.

Start free with Capuchin. Upgrade when it earns it.