Model Library/Qwen4 Max
Qwen4 Max

Qwen4 Max

qwen/qwen4-max
by Qwen
Input price
$1.413/ M tokens
Output price
$4.24/ M tokens
Context window
977Ktokens
Max output
128Ktokens

Qwen4‑max is the new‑generation MoE flagship model of the Qwen4 family, with 2.4T total parameters and 71B activated parameters. Boasting million‑token context window and native vision capability, it delivers major improvements in coding and office productivity. It can autonomously drive long‑cycle projects and deliver complete outputs in tens of days, supporting hundreds of professional domains such as law, finance, design and scientific research for end‑to‑end production‑grade results. Native visual understanding runs through planning, execution and verification, enabling deep semantic analysis of ultra‑long documents and long‑form videos. Powered by Live‑Delivery mechanism, it performs self‑planning and closed‑loop iteration for long‑horizon tasks, steadily iterating deliverables for real‑world complex workflows。

Features

Serverless API

Docs

qwen/qwen4-max is available via Novita's serverless API, where you pay per token. There are several ways to call the API, including OpenAI-compatible endpoints with exceptional reasoning performance.

Available Serverless

Run queries immediately, pay only for usage

Input$1.413 / M Tokens
Cache Read$0.071 / M Tokens
Cache Write(5m)$1.767 / M Tokens
Cache Write(1h)$2.827 / M Tokens
Output$4.24 / M Tokens
  1. Get your API key

    Sign up and create a key to run the code below. The API is OpenAI-compatible.

  2. Make your first request

    The API is OpenAI-compatible: point any OpenAI SDK at the base URL and pass this model ID.

    Base URL
    https://api.novita.ai/openaihttps://api.novita.ai/anthropic
    Model ID
    qwen/qwen4-max
    API Endpoint
    chat/completionsresponses
    1from openai import OpenAI
    2
    3client = OpenAI(
    4    api_key="<Your API Key>",
    5    base_url="https://api.novita.ai/openai"
    6)
    7
    8response = client.chat.completions.create(
    9    model="qwen/qwen4-max",
    10    messages=[
    11        {"role": "system", "content": "You are a helpful assistant."},
    12        {"role": "user", "content": "Hello, how are you?"}
    13    ],
    14    max_tokens=131000,
    15    temperature=0.7
    16)
    17
    18print(response.choices[0].message.content)