Getting started
- Choose a model from the live catalog.
- Create a server-side API key with narrow permissions.
- Run one basic request.
- Confirm usage and cost.
- Set budgets before production traffic.
Common questions
Is the API compatible with the OpenAI SDK?
The public gateway follows the OpenAI-compatible chat completions pattern. Confirm model-specific features in the live catalog and documentation before production rollout.
Where do model availability and prices come from?
Public model pages read the active catalog exposed by the service. A model is not presented as available merely because its name appears in an article.
Are Alipay and USDT recharge active?
They are planned for the international version, but the collection module is not enabled in this phase. The site must not ask users to transfer funds until a real order and crediting workflow is available.
Can I limit spending by project or API key?
The existing product supports project and key controls, including budget and rate constraints. Exact fields and enforcement behavior are documented in the console and API documentation.
Does the platform expose upstream provider keys?
No public client should receive an upstream provider credential. Applications use a Qingheng key and the gateway handles configured upstream access.
Are failed requests always free?
Billing depends on whether upstream usage was produced and how the request was settled. Review the active billing documentation and the request record rather than assuming every HTTP error has zero cost.
Can I put an API key in a mobile or browser app?
Do not embed a long-lived server key in distributable client code. Use your own backend to authenticate users and make model requests.
What happens when a model is unavailable?
The application should surface a clear failure or use a previously tested fallback. Do not silently move to a different model with unknown behavior.