XinoAPI exposes Qwen models with explicit model IDs such as qwen-turbo, qwen-plus, and qwen-max for global developers building apps and agent workflows.
Use qwen-turbo for high-volume, cost-sensitive workloads. It has a 1M context window and is the lowest-cost Qwen route in the current catalog.
Use qwen-plus as the balanced default for product features, structured outputs, and agent workflows. It supports 1M context.
Use qwen-max for the most demanding Qwen tasks when flagship quality is the priority. It supports 256K context.
Keep the OpenAI SDK, change the base URL to https://api.xinoapi.com/v1, and select the Qwen model by its explicit ID. Review the current Qwen API prices before scaling traffic.
from openai import OpenAI
client = OpenAI(
api_key="xino-your-key-here",
base_url="https://api.xinoapi.com/v1",
)
response = client.chat.completions.create(
model="qwen-plus",
messages=[{"role": "user", "content": "Hello from XinoAPI"}],
)
print(response.choices[0].message.content)Use explicit model IDs. Avoid legacy aliases in new integrations.
Use qwen-turbo for high-volume tasks, qwen-plus for balanced quality, and qwen-max for flagship use cases.
Use the explicit backend model IDs published by XinoAPI, such as qwen-plus and qwen-max.
Yes. Use the standard chat completions endpoint at https://api.xinoapi.com/v1.
Review pricing, choose a model, and test with a small request before moving production traffic.