Production notes
- Use a server runtime.
- Set a request timeout.
- Handle rate-limit and upstream errors explicitly.
- Log the request ID without logging the API key.
quickstart.tstypescript
import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.QINGHENG_API_KEY,
baseURL: process.env.QINGHENG_BASE_URL,
});
const response = await client.chat.completions.create({
model: "qwen3.7-plus",
messages: [{ role: "user", content: "Summarize this incident." }],
});
console.log(response.choices[0]?.message.content);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.