What is AnLink in the current release?
It is a unified access layer for a small set of Chinese models with one OpenAI-compatible request surface, console-issued API keys, trial credit, and usage visibility.

FAQ
This page focuses on the current MVP. It is written to answer the practical questions that show up during registration, key issuance, model selection, and first request validation.
Answers
It is a unified access layer for a small set of Chinese models with one OpenAI-compatible request surface, console-issued API keys, trial credit, and usage visibility.
Open https://console.anlinkai.com, register, create an API key, then call https://api.anlinkai.com/api/v1/chat/completions with a currently active model code.
No. The current product goal is to abstract that away behind one base URL and one access flow.
New accounts currently start with trial credit for integration validation. Balance and recorded cost are visible in the console.
Not in the current MVP. Self-service payment and recharge are explicitly outside the first release.
Use POST /chat/completions first. That is the primary path the MVP is designed around.
No. Keep the key in server-side environment variables or backend secret storage.
Check three things first: whether the model is active, whether your account still has credit, and whether the key is still active.
Use the Usage Logs page in the console and compare request status, token counts, and any recorded error code.
The recommended validation path is still non-streaming chat completions. Keep the first integration simple.
Yes. During MVP validation, pricing and enabled model exposure may change while routing and support are still being tuned.
Not yet. Org controls, advanced routing, broad catalog expansion, and public SLA are not part of the current release.