Docs/Developer/Plans and limits

Plans and limits

What each plan’s tokens may do, and the ceilings a run body is checked against.

Every plan’s tokens can read, validate and estimate. Writing through the API, meaning saving a scenario or launching a run, is what the paid plans include. There is no separate charge for API use: a run launched through the API meters exactly like one launched from the builder, agent turns against the month’s allowance and inference on your own keys.

#Developer access by plan

Free FreeStarter $10/moPro $49/moLab $499/mo
API and MCPRead, validate, estimateFull: author scenarios, launch runsFull: author scenarios, launch runsFull: author scenarios, launch runs
Access tokens131025
Requests per minute, per token60120300600
Saved scenarios52050500
Saved skills52050500

#Run ceilings by plan

These are the limits GET /api/v1/me reports under limits, and the ones an estimate or a launch is checked against.

FreeStarterProLab
Seats per run46816
Ticks per run30060020002000
Trials per series241050
Queued runs12310
Agent turns per month5,00012,00060,000Unlimited

#What a refusal looks like

A write on a read-only plan answers 403 plan_api with a message that names the upgrade. A body over a plan ceiling answers 400 with the ceiling’s code (plan_seats, plan_ticks, plan_series, plan_quota) and a message that says what to change. Validate reports the ticks ceiling as a warning before you ever try to launch.

{
  "error": "plan_api",
  "message": "The Free plan's tokens can read, validate and estimate; saving a scenario through the API needs Starter or above. Upgrade at /pricing, or save it from the Studio's run builder."
}

The full plan table, including spend caps and log retention, is on /pricing.