LLM·Dex
Open weightsAlibabaopentext

Qwen3-72B

Alibaba's flagship open-weight Qwen3, strong on multilingual, code, and math, Apache-2.0 licensed.

Updated


Quick facts

Released
Apr 2025
Context
128K tokens
Output / 1M
Pricing not published
License
Apache-2.0

About Qwen3-72B

Qwen3-72B is Alibaba's spring 2025 flagship and the strongest open-weight model on Chinese benchmarks at the time of release. The model also leads the open-weight pack on math reasoning and is competitive on code.

The Apache-2.0 license makes it the preferred choice for teams that need clean commercial deployment terms, particularly in jurisdictions where Llama's community license is awkward.

Benchmarks

Published scores from Alibaba's model card or independent leaderboards. We do not publish numbers we cannot source, see methodology.

HumanEval
,
Python coding pass@1
MMLU
84.0
Broad academic knowledge
GPQA
,
Graduate-level reasoning
SWE-bench
,
Real software-engineering tasks
  • MMLU84.0

Capabilities

Strengths

  • Apache-2.0 license
  • Strongest open-weight on Chinese
  • Strong multilingual coverage

Tracked weaknesses

  • No native vision in this variant

Pricing

Per-million-token rates as published by Alibaba.

Per-token pricing not yet published for Qwen3-72B. Check the official provider site for current tiers.

Call Qwen3-72B from your code

Drop-in snippet for the Alibaba SDK. Set your API key in the environment and run.

typescript
import OpenAI from "openai";

const client = new OpenAI({
  // Use OPENAI_API_KEY for OpenAI, or your provider's key + baseURL.
  apiKey: process.env.OPENAI_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "qwen-3-72b",
  messages: [
    { role: "user", content: "What's the time complexity of quicksort?" },
  ],
});

console.log(completion.choices[0].message.content);

Best for

Tasks where Qwen3-72B ranks among LLMDex's top picks.

Compare Qwen3-72B with…

Frequently asked

  • How much does Qwen3-72B cost?
    Alibaba has not published per-token API pricing for Qwen3-72B at the time of writing. Check the official site for current pricing tiers, or compare against alternative models on LLMDex.
  • What is Qwen3-72B's context window?
    Qwen3-72B supports a context window of 128K tokens.
  • Is Qwen3-72B open source?
    Qwen3-72B ships with open weights under the Apache-2.0 license. You can self-host it, fine-tune it, and (subject to the license terms) deploy it commercially.
  • When was Qwen3-72B released?
    Qwen3-72B was released on Apr 29, 2025 by Alibaba.
Friday digest

Intelligence, distilled weekly.

One short email every Friday, new model launches, leaderboard moves, and pricing drops. Curated by hand. Free, no spam.