FAQ
Common questions about endpoint formats, model access, billing, and support.
What is this service?
It is a unified LLM API gateway for buying API keys, topping up quota, checking usage, and integrating through common API-compatible formats.
Which endpoint formats do you support?
You can use Chat Completions-compatible, Responses-compatible, and Messages-compatible endpoints. Pick the format your client or SDK expects.
What Base URL should I use?
Start with https://api.weeanno.example/v1 for most clients. If your client asks for a full endpoint instead of a Base URL, use the matching chat/completions, responses, or messages path.
Which developer tools and agent workflows are compatible?
Common compatible tools include Codex CLI, Claude Code, OpenCode, OpenClaw, Cursor, Cline, Roo Code, Kilo Code, Windsurf, Dify, n8n, LangChain, OpenWebUI, Cherry Studio, and LM Studio. Configure the Base URL or full endpoint required by each tool.
How is quota billed?
Most models are billed by actual token usage. Purchased quota does not expire and can continue to be used until it is spent.
Can high-volume teams request a custom plan?
Yes. Teams with higher volume, procurement, invoicing, or support requirements can contact support for a custom arrangement.