Qwen: Qwen3 235B A22B Thinking 2507
qwen/qwen3-235b-a22b-thinking-2507
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...
Modalities
In / Out Price
$0.23 / $2.30 per 1M
Context
131K
Released
Jul 25, 2025
Knowledge Cutoff
Jun 2025
Apps using this model
Top apps by tokens routed through Reroute in the last 30 days. Apps appear here when they send an X-Title header.
No usage through Reroute yet
Once apps call this model with an X-Title header, they're ranked here by tokens.