Qwen 3 72B — Alibaba | Modeldex

Qwen 3 72B

Active

72B dense open-weight model with hybrid thinking from Alibaba.

Updated 3 days agoStructured data from Modeldex catalog

AgenticOpen source

Not enough benchmark coverage yet for an Intelligence Index — needs at least 3 results across 2 categories.

Overview

Qwen 3 72B is Alibaba's largest dense open-weight model, featuring hybrid thinking (chain-of-thought toggle), strong multilingual capabilities across 100+ languages, and competitive benchmark results vs GPT-4.1 at open-weight pricing.

History

Qwen 3 72B was released on 2025-04-29.

Training & availability

Weights are publicly available under the Apache-2.0 license, making this an open-weight model suitable for on-prem deployment and fine-tuning.

Capabilities

Context window: 128K tokens.
Max output: 32K tokens.
Input modalities: text.

Recommended for: agentic, open-source.

Limitations

Text-only — cannot process images, audio, or video inputs.

Quick start

Minimal example using the OpenRouter API. Copy, paste, replace the key.

from openai import OpenAI

client = OpenAI(
    base_url="https://openrouter.ai/api/v1",
    api_key="sk-or-...",
)
resp = client.chat.completions.create(
    model="alibaba/qwen-3-72b",
    messages=[{"role": "user", "content": "Explain quantum computing in one sentence."}],
)
print(resp.choices[0].message.content)

Cost calculator

Estimate your monthly bill. Presets are typical workload sizes.

Input tokens / month5.0M

@ $0.2/1M

Output tokens / month2.0M

@ $0.6/1M

Input cost

5.0M × $0.2/1M

Output cost

$1.2

2.0M × $0.6/1M

Total / month

$2.2

$26.4 / year

Integrations & tooling support

Tool calling: Supported
Structured outputs: Supported

Price vs quality

Budget pricing

Priced low — good for high-volume tasks. Quality tier pending more benchmark coverage.