Simple, usage-based pricing.

Pay only for the workflow steps your agents actually run. Start free.

Developer

For prototyping, side projects, and evaluating LoopLlama.

$0/ month
  • 25 workflow steps / month (hard cap)
  • Unlimited workflows and agents
  • All 13 connectors, schedules, and webhooks
  • Full per-step traces
  • Email support
Start free

Pro

For teams shipping their first agentic features.

$149/ month
  • 250 workflow steps / month
  • $0.20 / step overage, billed monthly
  • Everything in Developer
  • Human-in-the-loop approvals
  • Per-agent model choice
  • Priority email support
Upgrade to Pro
Most popular

Business

For teams running agentic workflows in production.

$1,198/ month
  • 2,000 workflow steps / month
  • $0.15 / step overage, billed monthly
  • Everything in Pro
  • Onboarding call and workflow design help
  • Priority support with a named contact
  • Security questionnaire and DPA on request
Get API access

Enterprise

VPC deploys, compliance, and procurement-friendly terms.

Custom
  • Volume step pricing
  • Single-tenant or VPC deployment
  • Custom connectors and agent templates
  • Invoice billing and custom terms
  • Dedicated implementation support
Contact sales

Frequently asked questions

What counts as a workflow step?
One reasoning turn by one agent — typically one LLM call plus any tool invocations it triggers. A typical workflow runs 5–30 steps depending on complexity. Steps are metered consistently across all tiers.
How do step overages work?
Paid plans include a monthly step allotment, then bill any additional steps automatically at your tier's overage rate ($0.20/step on Pro, $0.15 on Business) — priced just above our underlying Claude model cost and shown live in your dashboard. The free Developer tier is a hard cap instead: runs pause when you hit the limit, so you never get a surprise bill.
Do I need my own model API key?
No. Model access is included in the step price — LoopLlama runs your agents on Claude and the cost is built into each step. You choose which Claude model each agent uses.
How do you handle our data?
Workflow inputs, outputs, and traces are stored encrypted at rest, scoped to your account, and never used to train models. Connector credentials are encrypted with a separate key. You can delete workflows and their run history at any time.
Can I run this on my own infrastructure?
On the Enterprise plan we can run a single-tenant deployment in a dedicated VPC with the same API and SDK. Contact sales to scope it.
Can I switch plans or cancel anytime?
Yes. Upgrade, downgrade, or cancel from the dashboard at any time through the Stripe billing portal. Plans are billed monthly.