Skip to content
Pricing

Your models. Your workflow. One subscription.

Capuchin for everyday coding. Auto to handle model selection. An included frontier budget for Claude, Gemini, and ChatGPT. Find your paid plan below, or try Capuchin free — no card.

One seat, every surface

From editor to terminal. One seat covers it.

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

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
Auto mode
Background & scheduled agents
Team features
Download
Recommended

Pro

$20/month

Your everyday coding companion, with Capuchin, Auto, and frontier models when you need them.

Everything in Free
IDE, Code Agent and CLI included
Capuchin for everyday coding (fair use)
$20/mo frontier allowance (Claude/Gemini/ChatGPT)
Auto mode (Balanced)
Live consumption dashboard
Prepaid credits available for additional usage
Background & scheduled agents
Priority queue
Team features
Start Pro

Pro+

$60/month

Take on more work in parallel, with priority access and more room for frontier models.

Everything in Pro
IDE, Code Agent and CLI included
$60/mo frontier allowance (Claude/Gemini/ChatGPT)
Auto mode — Balanced + Max quality
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
Capuchin for everyday coding (fair use)
$120/mo frontier allowance included
Auto mode — Balanced + Max quality
Maximum parallel & background agents
Priority inference queue + early access
Priority support
Go Ultra

Keep your usage in view. Paid Capuchin access has no fixed monthly token allocation; short-window fair-use and concurrency limits apply. Frontier budgets are $20/month on Pro, $60 on Pro+, and $120 on Ultra — not fixed task counts. Usage varies by model, tokens, context, and caching, and a task may make multiple requests. Track it in your dashboard; prepaid credits can fund usage beyond your allowance.

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.

Everyday Capuchin

Keep coding with Capuchin on paid plans, with no fixed monthly token allocation. Fair-use and concurrency limits apply.

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

Use compatible local or self-hosted models on your own hardware. Hardware, hosting, and operating costs remain yours.

See where your budget goes

Follow frontier consumption in your dashboard and add prepaid credits for usage beyond your allowance.

Frequently asked questions

Can I try Capuchin for free?

Yes — claim the promo for free Capuchin access, no card required. The promo covers Capuchin, not Auto or frontier usage. Afterward, the Free tier keeps the full IDE working with your own key (BYOK) or local models.

How does the frontier allowance work?

Current monthly frontier dollar budgets are $20 on Pro, $60 on Pro+, and $120 on Ultra, independent of subscription price. Claude, Gemini, and ChatGPT usage consumes this allowance. Consumption varies by model, input and output tokens, context size, and caching; a single task can make multiple requests. Prepaid credits may fund additional usage. You can also use your own provider key (BYOK) and pay that provider directly.

What affects how long my allowance lasts?

Model choice, context size, output length, cache availability, and the number of requests all affect consumption. Agent tasks may make multiple requests, so there is no fixed cost per task or guaranteed number of runs. Indexing happens locally, but prompts and selected code context submitted for managed inference are processed by the service and applicable model providers. Check your usage dashboard to track consumption.

What is Auto mode?

Auto handles model selection for you using the models configured for each mode. Balanced is available on Pro and above; Max quality is available on Pro+ and above. The model used can change, so neither mode guarantees a particular model or a fixed sequence of models for every task. Frontier requests draw from your allowance or prepaid credits, and Max quality may use more. Fair-use, concurrency, and available-balance limits apply.

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.

Does paid Capuchin access have limits?

Current paid Capuchin access has no fixed monthly token allocation. Short-window fair-use and concurrency limits still apply and may temporarily limit requests. This is separate from the monthly dollar allowance for frontier models.

Is the Code Agent included in my plan?

Yes — the Code Agent is included in every plan, including Free with your own keys. So is the CLI, for the terminal and CI.

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.