Qwen3.5-397B-A17B

Qwen3.5-397B-A17B is a sparse mixture-of-experts model in Alibaba's Qwen line, with roughly 397B total parameters and ~17B activated per token. The Qwen3 family is known for strong multilingual coverage (including Arabic and Chinese), competitive coding and math performance, and reliable instruction following. Suited for high-throughput general-purpose workloads where open-weight flexibility and broad language support matter.

Quick start

Use any OpenAI-compatible client. Just change base_url and your key.

from openai import OpenAI

client = OpenAI(
    api_key="tl-xxxxxxxxxxxxxxxxxxxxxxxx",
    base_url="https://api.thalam.ai/v1",
)

response = client.chat.completions.create(
    model="qwen/qwen3.5-397b-a17b",
    messages=[
        {"role": "user", "content": "Hello from Thalam!"}
    ],
)

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