← All models View on HuggingFace →
Qwen: Qwen3 8B
qwen/qwen3-8b
Tool useJSONReasoningStreaming
Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It supports seamless switching between "thinking" mode for math,...
Pricing
Input
$0.05 / 1M
Output
$0.4 / 1M
Specs
Context
131,072 tokens
Input
text
Output
text
Knowledge cutoff: 2025-03-31
Released: 2025-04
Supported parameters
frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Open weights · HuggingFace
12,876,148 downloads/mo
1,109 likes
apache-2.0 text-generation