Pricing
Simple, transparent pricing. Start free with 1,000 gateway requests per day. Scale to enterprise with unlimited runners and custom SLAs.
Plans
Free
$0/month — No credit card required.
- 1,000 gateway requests / day
- Full 5-step governance chain (rate limiting, cost tracking, PII scanning, model allowlists, HITL)
- Cost tracking dashboard
- 10 requests per minute (RPM)
- 7-day data retention
- Community support
Best for: Evaluating Curate-Me governance with an existing OpenClaw or LLM setup.
Starter
$49/month (or $39/month billed annually)
Everything in Free, plus:
- 100,000 gateway requests / month
- 3 managed runners
- 50 session hours / month
- 60 RPM
- 30-day data retention
- Budget alerts
- HITL approval queues
- Priority email support
Best for: Solo developers shipping AI agents to production with cost control.
Growth
$199/month (or $159/month billed annually)
Everything in Starter, plus:
- 500,000 gateway requests / month
- 5 managed runners
- 200 session hours / month
- 300 RPM
- 90-day data retention
- Desktop streaming (agent observation)
- Skill scanner (unlimited scans)
- Multi-channel monitoring
- Kill switch with auto-triggers
- 99.9% uptime SLA
Best for: Small teams running multiple agents in production who need visibility and governance.
Enterprise
Custom pricing — Contact sales for a quote.
Everything in Growth, plus:
- Unlimited gateway requests
- Unlimited managed runners
- Unlimited session hours
- Custom RPM limits
- 1 year+ data retention
- SSO / SAML
- Audit log exports (JSON + PDF, SOC 2 / GDPR ready)
- Dedicated support engineer
- Connect your own machines (run on your hardware)
- Data residency (EU / US)
- Custom SLAs (99.95%+)
- Dedicated infrastructure
Best for: Organizations with compliance requirements, data residency needs, or large-scale agent deployments.
Plan Comparison
| Feature | Free | Starter | Growth | Enterprise |
|---|---|---|---|---|
| Gateway requests | 1K/day | 100K/mo | 500K/mo | Unlimited |
| Managed runners | 0 | 3 | 5 | Unlimited |
| Session hours | — | 50 hrs/mo | 200 hrs/mo | Unlimited |
| RPM | 10 | 60 | 300 | Custom |
| Data retention | 7 days | 30 days | 90 days | 1 yr+ |
| Governance chain | Full | Full | Full | Full + custom |
| Cost tracking | Dashboard | Dashboard + alerts | Dashboard + alerts + export | Full + export |
| PII scanning | Regex | Regex | Regex + Presidio NER | Regex + Presidio + custom |
| Kill switch | Manual | Manual | Manual + auto + webhook | Manual + auto + webhook |
| HITL approvals | No | Yes | Yes + custom workflows | Yes + custom workflows |
| Desktop streaming | No | No | Yes | Yes |
| Skill scanner | 10 scans/day | 10 scans/day | Unlimited | Unlimited + custom rules |
| Multi-channel | No | No | Yes + custom channels | Yes + custom channels |
| Audit export | No | No | JSON | JSON + PDF + SOC 2 |
| Your machines | No | No | No | Yes |
| SSO / SAML | No | No | No | Yes |
| Support | Community | Priority email | Priority with SLA | Dedicated engineer |
| Uptime SLA | Best effort | Best effort | 99.9% | 99.95%+ custom |
Overage Pricing
When you exceed your plan limits, usage is billed at the following rates:
| Resource | Overage Rate |
|---|---|
| Gateway requests | $0.10 per 1,000 requests |
| Compute (lightweight profile) | $0.10 / hour |
| Compute (standard profile) | $0.25 / hour |
| Compute (heavy profile) | $0.50 / hour |
| Additional managed runner | $25 / month per runner |
Overage charges are billed at the end of each billing cycle. You can set hard caps in the dashboard to prevent unexpected charges.
LLM Provider Costs
Important: Curate-Me never marks up LLM API costs. You pay the provider directly (OpenAI, Anthropic, Google, Groq, Mistral, xAI, and more) at their published rates. Curate-Me only charges for the governance platform — gateway routing, cost tracking, rate limiting, PII scanning, and managed runners.
You bring your own provider API keys. We govern the calls.
See Supported Models for current provider pricing.
FAQ
Can I switch plans at any time? Yes. Upgrade or downgrade from the dashboard. Upgrades take effect immediately. Downgrades are prorated and take effect at the next billing cycle.
What payment methods do you accept? Visa, Mastercard, American Express via Stripe. Annual plans are paid upfront. Enterprise plans support invoicing with NET-30 terms.
Is there a free trial for paid plans? Yes. All paid plans include a 14-day free trial. No credit card required to start.
What happens when I exceed the request limit? On Free, requests are denied with a 429 status code. On paid plans, overage is billed at $0.10 per 1,000 requests. You can configure hard caps or auto-upgrade in the dashboard.
Do annual plans include a discount? Yes. Annual billing saves approximately 20% compared to monthly billing on Starter and Growth plans. Enterprise pricing is tailored to your usage.
Can I add extra runners without upgrading? Yes. Additional managed runners are available at $25/month per runner on any paid plan.
What counts as a gateway request? Each LLM API call that passes through the gateway counts as one request. This includes chat completions, embeddings, and image generation calls. Health checks and metadata queries do not count.
Get Started
- Sign up for free — No credit card required
- Gateway Overview — Understand routing, governance, and headers
- Contact sales for Enterprise