灵调AI灵调AI · AI API gateway
Build beyond one model. Keep every request moving.
灵调AI is an OpenAI-compatible AI API gateway for the major providers’ text and code models, billed in US dollars.
From model access to reliable delivery.
52 models. One place to connect.
Compare models, protocols and prices across providers. Choose what fits each part of your product.
A backup route, built into your requests.
When a route has no supply, hits its limit or fails, the request moves to the next route for the same model. Give a regular API key a primary route and ordered backups; you pay once, at the price of the route that answered.
One key. Your routing preference.
Use the same key across models. 灵调AI ranks the route groups your account can use for the requested model, following your chosen strategy.
Quick start
- OpenAI-compatible base URL:
https://api.wyoai.site/v1 - Anthropic-compatible base URL:
https://api.wyoai.site - Gemini-compatible base URL:
https://api.wyoai.site
curl https://api.wyoai.site/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"gpt-6-sol","messages":[{"role":"user","content":"Hello"}]}'Frequently asked questions
What can I do with 灵调AI?
Build with text, code and image models from different providers. One key and one console keep your keys, usage and billing together.
How is 灵调AI different from calling each provider directly?
You use one API key, one base URL and one US-dollar balance for models from many providers. Each model lists its price next to the official rate, and every request records its token usage and cost.
Is it easy to connect my existing app?
Usually you only change the base URL and API key. Use https://api.wyoai.site/v1 with OpenAI SDKs and compatible tools, or https://api.wyoai.site with Anthropic and Gemini SDKs. Claude Code and Codex each set up with one command.
How do I find the right model?
Start with what you want to make. On Models & Pricing, compare supported APIs, route groups and rates, then open a model for the details. To weigh price against stability, pick route groups per key or let a smart key choose.
How are prices calculated?
Each model lists its price for every route group, per 1M tokens or per image, beside the official rate. 1 credit is US$1, and your usage log records the cost of each request.
Do I need a subscription to start?
No. Start with pay-as-you-go credits. If you prefer a plan, compare its monthly allowance and limits in your wallet first. Your console shows usage and charges as you go.
What happens when an upstream provider fails?
A backup takes over. With backup routes or a smart key, the request moves to the next route for the same model, and you are charged once, at the price of the route that answered.
Can I keep each project under control?
Give each project its own API key. Set a quota and expiration date, add model or IP restrictions when needed, and track usage separately.
Can my team share one account?
Yes. Issue a key for each person or project, give each key its own quota, and read cost by key and model in the usage log. Larger teams can ask about volume pricing.
How does 灵调AI handle my request data?
The Trust Center explains which request data is processed, how long records are kept, which service providers may handle it, and how to report a security issue.
Can I try a model without writing code?
Yes. Open the Playground in your console, pick a model and start chatting; it spends the same balance as the API.
What if I top up and change my mind?
Refund terms are in the Top-up and Refund Policy. Read it before you top up, and contact support if something is unclear.