Chinese AI APIs, without rewriting your client.

Keep the OpenAI request shape, choose an explicit model ID, and inspect the request record after the call. AIWave gives developers one route for Chinese provider families and one billing surface.

Start with the request your team needs.

A small smoke test proves the route works. The next request should resemble the workload you actually plan to run.

One representative payload, one saved result
01

Keep the client

Set the AIWave base URL and keep the OpenAI Python or Node client you already use.

Keep the client
02

Choose by workload

Use a current model ID for coding, long context, vision, or a small smoke test. Check the dated rate before a larger run.

Choose by workload
03

Keep an audit trail

Inspect usage, status, model ID, effective group, and charge in the request record.

Keep an audit trail

Check the details that decide a successful call.

The client shape is only the beginning. These checks keep a working request understandable after it leaves your terminal.

Route, account, response, record
01

Base URL

The endpoint is OpenAI-compatible, but the model field still needs an exact current ID.

02

Account state

Balance and effective group affect whether a request can run and how it is charged.

03

Response shape

Keep the request ID and usage fields when you move from a smoke test to a real workload.

Run one small request before you scale it.

Keep the key server side. Copy the request, replace the model only with an ID from the current directory, and inspect the response.

OpenAI-compatible chat completions

Copy-ready request

curl https://aiwave.live/v1/chat/completions \
  -H "Authorization: Bearer $AIWAVE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek-v4-pro","messages":[{"role":"user","content":"Say hello in one sentence."}],"max_tokens":32}'

Before production

Keep the first result explainable.

Save the request ID, model ID, usage fields, status, and charge with the application record.

  1. Check the key without printing its value.
  2. Use a current model ID from the directory.
  3. Set a client timeout and bound retries.
  4. Compare the response record with the dated rate.

Questions developers ask before integration.

What is a Chinese AI API?

It is an API route that exposes models from Chinese provider families through a developer-facing interface.

Can I use the OpenAI SDK?

Yes. Set the base URL to https://aiwave.live/v1 and pass an AIWave key on the server side.

How do I choose a model?

Start with the current model directory, then compare the dated rate and context details for the workload.

Run a request you can inspect afterward.

Keep the request small, confirm the route, then move to the workload that matters.