Every tier includes the full edge proxy, attribution, and budgets. Higher tiers unlock scale, retention, and controls your security team will ask for.
For solo builders and early experiments.
For teams who need full visibility and control.
Volume, security, and control for regulated teams.
All plans include the full edge proxy and sub-millisecond overhead on Cloudflare's global network.
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.
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.
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.
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.
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.