Qwen: Qwen3 235B A22B
Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a "thinking" mode for complex reasoning, math, and... Massive 235B MoE architecture (22B active per token) Seamless thinking/non-thinking mode switching Strong multilingual performance across 100+ languages Open-weight with competitive reasoning benchmarks Chinese-first training may bias some cultural references Less Western community tooling and ecosystem Very large total size limits local deployment Multilingual applications and translation Complex reasoning and chain-of-thought Cost-efficient open-weight deployment Coding and technical tasks
Specifications
| Lab | Qwen |
|---|---|
| Context window | 131,072 |
| Input price | $0.46/1M |
| Output price | $1.82/1M |
| Release | 2025-04-01 00:00:00 |
Strengths
- Massive 235B MoE architecture (22B active per token)
- Seamless thinking/non-thinking mode switching
- Strong multilingual performance across 100+ languages
- Open-weight with competitive reasoning benchmarks
Weaknesses
- Chinese-first training may bias some cultural references
- Less Western community tooling and ecosystem
- Very large total size limits local deployment
Best for
- Multilingual applications and translation
- Complex reasoning and chain-of-thought
- Cost-efficient open-weight deployment
- Coding and technical tasks
In Depth: Qwen3 235B A22B
Summary
Qwen3 235B A22B is an AI model from Qwen.
Released 2025-04-01 00:00:00. It currently appears in the Overall category on LMRank and 1 other category. It supports Text input and produces Text output, with a context window of 131.1K tokens. Input pricing is $0.46 per 1M tokens and output is $1.82 per 1M tokens on OpenRouter.