Qwen3 235B A22B

alibaba

Qwen3 hybrid reasoning model enables seamless switching between thinking and non-thinking modes during conversations. It delivers strong reasoning performance with fewer parameters, comparable to QwQ, and significantly outperforms Qwen2.5-72B-Instruct in general capabilities, achieving state-of-the-art (SOTA) results for its scale.

Try Now

Capabilities

Tool Use

Extended Thinking

Example Use Cases

Strong reasoning with efficient compute

Complex task needing large alibaba model

Moe model for cost-effective reasoning

Technical Specifications

Context Window

131,072 tokens

Max Output

8,192 tokens

Cache Miss Cost

$0.70 per 1M tokens

Non-Reasoning Cost

$2.80 per 1M tokens

Reasoning Cost

$8.40 per 1M tokens

Web Search Cost

$15 per 1K calls

Code Execution Cost

$0.19 per 1K calls

⚠️ Legacy

Made legacy on

Reason

Untested

Recommended Replacement

Qwen3 Max