Frequently asked questions

Yes. XPNCORE accepts requests in the OpenAI (Chat Completions, Responses), Anthropic Messages (Claude Code, Anthropic SDKs), Google Gemini and Ollama formats. Change the base URL and API key; everything else stays the same.

No. One XPNCORE API key works for every model you can access, from OpenAI, Anthropic, Google and the other models in the catalog.

Call GET /v1/models with your API key, or open the Models & Pricing page. Use the exact model ID from the list when you send a request.

A combo is one model ID that covers several models. Each request is served by one of them and billed at that model's price, within the range shown on the pricing page.

Top up your wallet by bank transfer. Each request is charged to your wallet at the price of the model used; you pay only for what you use, with no monthly fee.

No. However many times we retry internally or switch sources, you pay once for the final result. Failed requests are not charged.

New requests are rejected at once and not charged. Top up or renew your plan to continue; the dashboard figures are for tracking only.

We never resend the request automatically, because that could duplicate content. Keep the part of the answer you received and decide whether to send it again.

Every request has a request ID, in the x-routing-request-id response header and under Usage › Request log in the dashboard. When a request fails, open a support request with its request ID and the time, so an admin can look up exactly that request. When many fail at once, check the Status page first, then send a few of their request IDs. Never send your API key or sensitive content.