Qwen3-235B-A22B — reviews, specs & pricing

Alibaba's flagship MoE model with hybrid reasoning.

Summary

Qwen3-235B-A22B is a mixture-of-experts model with 235B total/22B active parameters, supporting seamless switching between thinking and non-thinking modes. It supports 100+ languages and a 128k context window. It's released under Apache 2.0.

Sample use case

Used for multilingual chat, agentic tool use, and coding tasks. Popular for self-hosted deployments requiring open licensing.

Specifications

  • Provider: alibaba
  • License: open
  • Parameters: 235B
  • Context: 128k tokens
  • Released: 2025-04-29

Pros

  • Apache 2.0 license
  • Hybrid reasoning modes
  • Strong multilingual coverage

Cons

  • Large compute footprint
  • Less mature Western ecosystem support
  • Documentation partly in Chinese

Average rating 0.0 from 0 community reviews on Reviuws.

Frequently asked questions

What is Qwen3-235B-A22B?

Qwen3-235B-A22B is a mixture-of-experts model with 235B total/22B active parameters, supporting seamless switching between thinking and non-thinking modes. It supports 100+ languages and a 128k context window. It's released under Apache 2.0.

How much does Qwen3-235B-A22B cost?

Pricing for Qwen3-235B-A22B is not publicly listed.

Is Qwen3-235B-A22B open source?

Qwen3-235B-A22B is released under the open license.