Pay for visibility, not for the proxy.

Every tier includes the full edge proxy, attribution, and budgets. Higher tiers unlock scale, retention, and controls your security team will ask for.

Free

$0 forever

For solo builders and early experiments.

Start free
  • Up to 1M tokens/month
  • 1 project, 2 team keys
  • 7-day log retention
  • Per-feature attribution
  • Basic budgets (soft alerts)
  • Community Slack support
  • OpenAI + Anthropic providers
Most popular

Pro

$49 / month

For teams who need full visibility and control.

Start 14-day trial
  • Up to 50M tokens/month ($0.50 per additional 1M)
  • Unlimited projects and team keys
  • 90-day log retention
  • Hard budget stops + Slack/email alerts
  • Optimization reports (model downgrade, caching, prompt bloat)
  • All supported providers
  • CSV + API export
  • Email support, 1 business day

Enterprise

Custom

Volume, security, and control for regulated teams.

Contact sales
  • Unlimited tokens, volume pricing
  • SSO (SAML, Okta, Google Workspace)
  • Audit logs, role-based access, SOC 2 Type II report
  • Dedicated region (US, EU) and 99.95% SLA
  • Self-hosted proxy option
  • Custom data retention and DPA
  • Priority support + named solutions engineer

All plans include the full edge proxy and sub-millisecond overhead on Cloudflare's global network.

Frequently asked questions

Do I need an SDK?

No. HubComb is a drop-in proxy — change your base URL from api.openai.com to proxy.hubcomb.com and pass your team key. Your existing SDKs keep working.

What about data privacy?

Request and response bodies are never persisted by default — we store metadata (tokens, latency, cost, model, tags). Full-body logging is opt-in per project. Enterprise tier supports EU-only routing and self-hosted deployment.

Can I switch providers?

Yes. HubComb routes OpenAI, Anthropic, and other major providers through one endpoint. You can also A/B route the same prompt across providers to compare cost and quality.

What happens if I exceed my tier?

Free tier requests are rate-limited, not blocked — you keep running while we prompt you to upgrade. Pro tier bills overage at $0.50 per additional 1M tokens. Enterprise is flat-rate.

How does attribution actually work?

Each request carries an X-Team-Key header (or a tag). We attribute cost at the edge based on that key, so a single OpenAI account can cleanly bill back to a specific feature, customer, or internal team.

Know what every LLM call costs — before your next invoice.