Qwen: Qwen3.8 27B

qwen/qwen3.8-27b

textVisionReasoningVideo

An open-weight dense vision-language model from Qwen: coding, professional workflows, research, multimodal interaction, and long-running agent tasks. Thinking can be enabled or disabled. Understands images and video, 256K context.

Pricing

Request / 1M

Response / 1M

Parameters

messagesrequired

reasoning_effortoff · low · medium · xhigh

temperature0–2

max_tokensoptional

streamtrue · false

image_urlimage (data: URL)

How to use via API

from openai import OpenAI

client = OpenAI(base_url="https://api.mixen.ai/v1", api_key="mxn-...")
resp = client.chat.completions.create(
    model="qwen/qwen3.8-27b",
    messages=[{"role": "user", "content": "Привет"}],
    reasoning_effort="low",  # off · low · medium · xhigh
    temperature=0.7,
    max_tokens=1024,
    stream=False,
)
print(resp.choices[0].message.content)

# Стриминг: stream=True — ответ приходит чанками
for chunk in client.chat.completions.create(
    model="qwen/qwen3.8-27b",
    messages=[{"role": "user", "content": "Привет"}],
    stream=True,
):
    print(chunk.choices[0].delta.content or "", end="", flush=True)

Try in the botAPI docs

Related models