Qwen3 235B A22B Thinking (2507, FP8)

Qwen/Qwen3-235B-A22B-Thinking-2507-FP8

curl https://api.gmi-serving.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $GMI_API_KEY" \
  -d '{
    "model": "Qwen/Qwen3-235B-A22B-Thinking-2507-FP8",
    "messages": [
      { "role": "system", "content": "You are a helpful assistant." },
      { "role": "user",   "content": "Hello!" }
    ]
  }'

from openai import OpenAI

client = OpenAI(
    base_url="https://api.gmi-serving.com/v1",
    api_key="<gmi-api-key>",
)

resp = client.chat.completions.create(
    model="Qwen/Qwen3-235B-A22B-Thinking-2507-FP8",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user",   "content": "Hello!"},
    ],
)
print(resp.choices[0].message.content)