Pricing

Per person, per month. Usage on top, at a rate you can check.

Sold by Paddle as Merchant of Record. Nothing is bundled and nothing is estimated: the subscription is the subscription, and usage is metered at the two rates below.

Annual is twelve months for the price of 8

Model tokens
× 1.25provider list price

A stated 25% margin over the provider's published list price, priced per model call. Only runs we execute for you meter at all.

Hosted compute
$0.15/hourstandard 2 vCPU / 4 GB runner

Metered per second of task lifetime, drawn from your prepaid balance. Your own machines are never metered.

The basis is the provider's list price, not our cost: batch, prompt-caching and negotiated volume discounts are not passed through. That is what makes the multiplier checkable against a number the provider publishes.

Local runs and self-hosted runners are unlimited on every plan, including Free. They are never metered and never draw the balance.

Free

Early access
$0/mo
No card, on either billing period

The live dashboard plus local-first orchestration. Sign in and try it on your own repos.

  • Live run view + 7 days of history
  • Unlimited local runs and self-hosted runners
  • Answer needs-input from the web
  • Metadata-only privacy, enforced agent-side
  • BYOK: your keys, your subscription
Recommended

Pro

Live
$10/seat/mobilled annually
$120 per person, charged once a year

For the power user who stops operating agents and starts feeding the queue.

  • 90 days of history
  • Personal analytics: success, cost, duration
  • Scheduling + GitHub triggers
  • The self-draining task queue + digest
  • Web push: answer needs-input from your phone

Business

Live
$20/seat/mobilled annually
$240 per person, charged once a year

For teams that run pipelines like shared production infrastructure.

  • 365 days of history
  • RBAC, org secrets, and an audit log
  • Shared pipeline library, reviewed in PRs
  • Cost attribution per developer
  • Matrix runs, regression alerts + budgets, approval gates
Teams

The eleventh person is cheaper. The bill still goes up.

Seats 11 and beyond bill at the volume rate. It is applied marginally, not retroactively — the seats you already had keep their price, so adding a person can never make the invoice smaller.

Business, 12 people, billed per year
SeatsEachSubtotal
Seats 1–10$240 per year$2,400
Seats 11–12$192 per year$384
Total12 people$2,784 per year

We itemise the split here rather than at checkout: our payment provider shows a two-item subscription as a single line, and a total that does not show its own composition invites the question it should have answered.

Support

What we promise to answer

Two tiers, not three. Pro and Business are separated on history and features, never on how fast someone replies.

Free
Best effort

Community and email, answered when we can. No response time is promised.

Pro
We aim to reply within one business day

Email support with a response time we aim for and publish — the same on both paid plans. It is a target we hold ourselves to, not a contractual guarantee.

Business
We aim to reply within one business day

Email support with a response time we aim for and publish — the same on both paid plans. It is a target we hold ourselves to, not a contractual guarantee.

Hosted runners

Usage-basedRoadmap

Managed, ephemeral runners at $0.15/hour for when you would rather not run the metal yourself.

Available on every plan, including Free. Hosted compute always draws your prepaid balance — no subscription includes it, no plan gates it, and there is no starting free credit.

  • Managed, ephemeral runners with per-job isolation
  • BYOK injected at boot, wiped with the task, never logged
  • No cross-job persistence
  • BYOK runs meter compute only, never tokens

Subscriptions are sold by Paddle as Merchant of Record — Paddle is the seller on your receipt and handles sales tax and VAT wherever you are. Both billing periods are offered: an annual plan is one payment covering twelve months at the price of 8. Hosted runners meter per second of active runtime against your balance when they ship.

Good to know

Pricing questions

Do you see my code or my API keys?

No. Pipelines live in your own git repo and your keys stay on your machines. By default the cloud stores only metadata: statuses, timings, token counts; never transcripts or code, unless you explicitly opt up per project.

Is this a gateway or proxy for AI APIs?

No. Model traffic never touches us. Pipeline is an orchestration layer above your agent harness; you bring your own keys and your own subscription. We don't resell, discount, or route tokens.

What are privacy tiers?

Metadata is the default and it is enforced agent-side before anything is sent. You decide, per project, whether to send more than metadata. Nothing leaves your machine unless you opt in.

Can I self-host the agent?

Yes. The execution engine (the pipeline plugin and the pipeline-runner daemon) is open source. Run it on your own machines; the cloud is the optional control plane on top.