qwen
Qwen: Qwen3 235B A22B Thinking 2507
qwen/qwen3-235b-a22b-thinking-2507
For $1, you can send approximately:
~36.2messages
How do we get this number?
One message = ~7,000 input tokens + ~7,000 output tokens
Input cost per message7,000 x $0.45/M = $0.003150
Output cost per message7,000 x $3.50/M = $0.024500
Total cost per message$0.027650
Messages for $136.17
Context window
128k
tokens
Max response
16k
tokens
Input price
$0.45
per million tokens
Output price
$3.50
per million tokens
Modalities
Input:textOutput:text
Description
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...