HomeModels › Qwen3-Max
Alibaba Cloud · 2026 Flagship · 397B MoE

Qwen3-Max API

Alibaba Cloud's 2026 flagship. 397B-parameter MoE with 22B active. Top-tier agentic reasoning, multilingual, and long-context performance.

$0.80
Input / 1M tokens
$3.20
Output / 1M tokens
256K
Context window
0%
Platform fee
Sign Up — Get $0.50 Free Credit See All Pricing

Why use Qwen3-Max on NovAI?

  • 397B total / 22B active MoE architecture
  • ArenaHard 95.6, AIME'24 85.7 — competitive with GPT-4 and Claude 3.5
  • Native function-calling and tool-use designed for agent workflows
  • 256K context window for long-document tasks
  • Best-in-class Chinese + English bilingual performance

Best use cases

  • Multilingual agent workflows
  • Enterprise RAG with long documents
  • Structured data extraction
  • Research-grade reasoning

Quick start

cURL

curl https://aiapi-pro.com/v1/chat/completions \
  -H "Authorization: Bearer $NOVAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3-max",
    "messages": [{"role":"user","content":"Hello"}]
  }'

Python (OpenAI SDK)

from openai import OpenAI
client = OpenAI(
    base_url="https://aiapi-pro.com/v1",
    api_key="YOUR_NOVAI_API_KEY",
)
resp = client.chat.completions.create(
    model="qwen3-max",
    messages=[{"role":"user","content":"Hello"}],
)
print(resp.choices[0].message.content)

Full documentation: aiapi-pro.com/#docs

Ready to try Qwen3-Max?

Zero platform fee. Credits never expire. OpenAI-compatible API.

Sign Up Free