Qwen: Qwen 3.8 Flash

qwen/qwen3.8-flash

textVisionReasoningVideo

Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.

Price in / out

Cache, read / write

Context / Max output

1M / 131K

Released

Aug 26, 2026

Parameters

messagesrequired

reasoning_effortoff · low · medium · high

max_tokensoptional · alias max_completion_tokens

streamtrue · false

toolsfunction calling (OpenAI format)

tool_choiceauto · none · required

response_formatjson_object · json_schema

web_search · · ·

providerrouting: order · only · ignore · sort

stream_options{"include_usage": true}

image_urlimage (data: URL)

Fine-tuning · 9

temperature0–2

stopoptional

seedoptional

top_p0–1

top_koptional

frequency_penalty−2…2

presence_penalty−2…2

logprobstrue · false

top_logprobs0–20

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-flash",
    messages=[{"role": "user", "content": "Привет"}],
    reasoning_effort="low",  # off · low · medium · high
    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-flash",
    messages=[{"role": "user", "content": "Привет"}],
    stream=True,
):
    print(chunk.choices[0].delta.content or "", end="", flush=True)

API docsTry in the bot

Related models