ModelWatch
← Catalog

Qwen3 235B A22B Thinking 2507

Alibaba (Qwen)qwenlm.github.io

Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...

open-weights
Input price
$0.45 / 1M tokens
Output price
$3.50 / 1M tokens
Context window
128K tokens
Max output
16K tokens
Output speed
n/a
Time to first token
n/a
Inputs
text
Open weights
Yes
OpenRouter id
qwen/qwen3-235b-a22b-thinking-2507
Listed
Jul 25, 2025

Benchmarks

Intelligence Index
n/a
Engineering Index
n/a

No independent speed or benchmark data for this model yet. Prices, context window and listing date are live from OpenRouter.

Compare with others