Per-execution pricing: one fee per execution that returns proof, charged only when proof comes back. Failed or cancelled runs cost nothing. Planning and approvals are free.
Entry: $244/month (30% off early access, regular $349/month) for up to 5,000 requests per month. Pro: $559/month (30% off early access, regular $799/month) for up to 16,000 requests per month.
Key features
Boundary approval system for controlled execution
Checkpoint-based resumable execution
Verifiable proof of completion
Composable proof for multi-agent workflows
Per-execution pricing model
Integration with multiple agent frameworks
Build agents without code from the dashboard
Ground agents in your own knowledge bases
Connect twenty built-in integrations
Set request limits per project
Switch between models with one click
Control agent data retention
Set guardrails on agent responses
Use frontier and open-source models
Connect through API or MCP servers
Test agents in playground before production
What makes it different
Pay only for verified results, not for attempts or planning
Human-approved boundaries ensure agent actions stay within limits
Interruptible checkpoints allow pausing and resuming executions
Proof is built into results for auditability and composability
Agents only access what you explicitly allow, not the entire internet or your systems
No message content stored by default, only metadata for usage reports
Predictable monthly pricing with a hard request limit, no surprise bills
EU-hosted with isolated storage and databases
Agents evolve without rebuilding when switching models or tools