中EN Submit a tool

Qwen3 235B A22B

Rank #186 qwen

qwen/qwen3-235b-a22b-04-28

Usage data date 2026-07-26 · updated daily

Leaderboard Back to home

Usage and specs

Daily rank#186
Daily tokens3.3B
Daily requests706.2K
Daily change +103.8%
Context window131.1K
Released

What is 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 code tasks, and a "non-thinking" mode for general conversational efficiency. The model demonstrates strong reasoning ability, multilingual support (100+ languages and dialects), advanced instruction-following, and agent tool-calling capabilities. It natively handles a 32K token context window and extends up to 131K tokens using YaRN-based scaling.

Qwen3 235B A22B capabilities

Input: Text   Output: Text

Reasoning output Reasoning JSON output Tool choice Tool use Knowledge cutoff 2025-03-31

Qwen3 235B A22B API pricing

Input · per 1M tokens$0.46
Output · per 1M tokens$1.82

List prices in USD; see each provider’s site for current terms.

Tools built on this model

通义听悟 Great for meeting-heavy teams, students, journalists, and researchers turning speech into knowledge; not for formal archival use without human proofreading.