Qwen: Qwen 3.7 Flash

qwen/qwen3.7-flash

textVisionReasoningVideo

The fastest and cheapest model in the Qwen 3.7 line: reasoning, image input and a 1M-token context. Built for everyday work where speed and volume matter — long-text analysis, drafts, simple code.

Price in / out

Cache, read / write

Context / Max output

1M / 65.5K

Released

Jul 27, 2026

Additional rates

Above 32K prompt tokens the upstream charges more: 6.8× input, 6.2× output. Per-route rates are in the table below.

Parameters

messagesrequired

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 · 6

temperature0–2

seedoptional

top_p0–1

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/qwen3.7-flash",
    messages=[{"role": "user", "content": "Привет"}],
    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/qwen3.7-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