Qwen3 235B A22B Instruct 2507

Alibaba

Compared to its predecessor (Qwen3-235B-A22B), the latest open-source Qwen3 model (non-thinking mode) delivers modest improvements in creative performance and model safety.

Try Now

Capabilities

Tool Use

Technical Specifications

Context Window

131,072 tokens

Max Output

32,768 tokens

Pricing

Token Costs (per 1M tokens)

Cache Miss Input

$0.23

Non-Reasoning Output

$0.92

Tool Costs (per 1K calls)

Web Search

$15

Code Execution

$0.19

Retired

Made legacy on

Reason

Merged

Recommended Replacement

Qwen3.6 Plus

Retired on