Recharge balance for API calls across routed providers. Small top-ups stay simple; production spend can move into invoices, commitments, and volume terms.
Custom recharge rules: 10+ self-serve minimum, up to 5000 before enterprise review.
API testing and small experiments.
Individual development and early prototypes.
Early production traffic with predictable balance.
Team production workloads and finance review.
Invoice, discount, and customer-success path.
Annual commitment, SLA, and dedicated capacity.
All platform features come standard — no subscription fees. Just add credits and go.
One OpenAI-compatible endpoint for every model and provider.
Multi-provider routing with health-aware automatic fallback.
Token-accurate metering with clean cost attribution.
Hard caps and soft alerts by key, member, and project.
Shared balance pools, member roles, and org policies.
Order, subscription, and payout events with HMAC signing.
Per-request logs with append-only audit trail.
Email support included. Priority and SLA for committed spend.
The final catalog should be server-owned and show the current platform price per model, provider, and metering unit. These rows show the intended structure.
Answers about balance, model usage, auto recharge, budgets, and enterprise commitments.