阿里云百炼（Bailian / DashScope）配置

# max_tokens=4096 会被自动作为 max_completion_tokens=4096 发送
curl http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3-max",
    "messages": [{"role": "user", "content": "Hello"}],
    "max_tokens": 4096
  }'

from openai import OpenAI

client = OpenAI(base_url="http://localhost:8080/v1", api_key="unused")

# max_tokens=4096 会被自动作为 max_completion_tokens=4096 发送
completion = client.chat.completions.create(
    model="qwen3-max",
    messages=[{"role": "user", "content": "Hello"}],
    max_tokens=4096,
)

print(completion.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "http://localhost:8080/v1",
  apiKey: "unused",
});

// max_tokens=4096 会被自动作为 max_completion_tokens=4096 发送
const completion = await client.chat.completions.create({
  model: "qwen3-max",
  messages: [{ role: "user", content: "Hello" }],
  max_tokens: 4096,
});

console.log(completion.choices[0].message.content);