XPNCORE
HomeAPI MarketplacePricingDocumentationBlogFAQ
LoginRegister
XPNCORE

High-quality API marketplace for developers.

Product

  • API Marketplace
  • Pricing
  • AI Models
  • Documentation
  • Blog
  • FAQ
  • System Status

Company

  • About
  • Contact

Legal

  • Terms of Service
  • Privacy Policy
  • Refund Policy

© 2026 XPNCORE. All rights reserved.

OpenAI-compatible · One API key for every model

FAQ

Frequently asked questions

Short answers to help you integrate and operate the gateway safely.

Integration

Is the gateway OpenAI-compatible?

Yes. The public contract prioritizes GET /v1/models and POST /v1/chat/completions, including bounded JSON and SSE streaming. Use only capabilities published for the selected model.

Do I need a separate API key for every provider?

No. The client uses a platform-issued API key and a public model ID. Upstream credentials are managed server-side and are never exposed to users.

Models

How do I know which models my account can use?

Call GET /v1/models with the current API key. The result is filtered by subscription, plan, permissions, model status, and currently usable routes.

How do aliases such as auto, fast, or coding work?

Aliases resolve server-side to configured routes. The router still checks entitlement, capability, health, quota, and policy before selecting an actual candidate.

Usage and billing

Does an internal retry or failover charge usage more than once?

The gateway reserves quota before dispatch and settles one durable outcome for the public request. Internal attempts remain observable but do not become multiple user usage charges by default.

Is quota only shown in the dashboard, or actually enforced?

The backend checks and reserves quota before calling an upstream. Dashboard values, realtime counters, and notifications are supporting views; they do not replace gateway enforcement.

Reliability

What happens if a stream is interrupted?

After output is committed, the gateway does not replay the request because that could duplicate content. The outcome is classified conservatively and the client receives a sanitized error.

Support

What should I do when many requests fail at once?

Check the status page, retain the request ID and timestamp, then open a dashboard ticket or use the published contact channel. Never send full API keys, access tokens, or sensitive prompts.

Could not find an answer? Open a dashboard ticket or contact support.