← LLM Models

Qwen3 235B A22B Thinking 2507

Alibaba/Qwen

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...

Official page →
📖Context262K tokens
🚀Speed-
💵Input price$0.230/1M
💸Output price$2.30/1M

More from Alibaba/Qwen

Qwen 2.5 72BOSS
Score 60→
Qwen 2.5 Coder 32BOSS
Score 59→
Qwen3 Coder Plus
$0.650/1M→
Qwen3 235B A22B Instruct 2507
$0.090/1M→
Qwen3 30B A3B Thinking 2507
$0.200/1M→
Qwen2.5 7B InstructOSS
$0.100/1M→

API Providers

OpenRouter
Input
$0.230/1M
Output
$2.30/1M
→

Details

Provider
Alibaba/Qwen
Parameters
-
Context
262K tokens
Speed
-
Open Source
No
License
Proprietary
Released
Jul 2025

Reviews

No reviews yet

Log in to rate

← View all 409 models