Qwen3 8B

alibaba

Qwen3 hybrid reasoning model enables seamless switching between thinking and non-thinking modes during conversations. It achieves SOTA reasoning performance at its scale and significantly outperforms Qwen2.5-7B in general capabilities.

Try Now

Capabilities

Tool Use

Extended Thinking

Example Use Cases

Local or budget deployment with reasoning

Efficient model for moderate tasks

Small-scale reasoning or coding

Technical Specifications

Context Window

131,072 tokens

Max Output

8,192 tokens

Cache Miss Cost

$0.18 per 1M tokens

Non-Reasoning Cost

$0.70 per 1M tokens

Reasoning Cost

$2.10 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