Pay for what your agent does.
No seats, no minimums. A read costs one credit; a solved flow costs ten. Compile it into a skill and every later run drops back to one — you pay the discovery premium just once.
Free
For trying the engine and small personal agents.
Start free- 1,000 action credits / month
- Indexed DOM state + skill replay
- MCP, LangChain & REST
- Community support
Starter
For production agents with steady volume.
Get Starter- 50,000 action credits / month
- Per-tenant API keys + audit log
- Human-in-the-loop handoff
- Email support
Scale
For high-volume workloads that grow with you.
Start scaling- Pay-as-you-go credits
- Volume discounts
- Priority replay throughput
- Priority support
Enterprise
For teams with compliance and custom rules of engagement.
Contact sales- SSO + SCIM
- Dedicated capacity
- Custom allowlist & RoE
- SLA + solutions engineering
The whole cost model on one line each.
Every action has a flat, predictable credit cost. Compiling a skill is the only premium — and it pays for itself the second time you run it.
| Action | Cost | What it does |
|---|---|---|
| Read a page (indexed state) | 1 credit | Perceive without acting. |
| Solve a semantic flow | 10 credits | Plan + execute a goal with the model in the loop. |
| Compile a reusable skill | 50 credits | Discover & minimize once. |
| Replay a compiled skill | 1 credit | Deterministic, zero LLM cost. |
Example: a goal you run 1,000 times costs 10,000 credits if re-reasoned each time — or 50 credits to compile once, then 1,000 credits to replay. Skill compilation pays for itself on run six.
Start with 1,000 free credits.
No card required. Upgrade when your agent earns its keep.