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

Thinking

Tool Use

Technical Specifications

Context Window

131,072 tokens

Max Output

8,192 tokens

Pricing

Token Costs (per 1M tokens)

Cache Miss Input

$0.18

Non-Reasoning Output

$0.70

Reasoning Output

$2.10

Tool Costs (per 1K calls)

Web Search

$15

Code Execution

$0.19

Legacy

Made legacy on

Reason

8B model; superseded by Qwen3 32B

Recommended Replacement

Qwen3.6 Plus