Qwen: Qwen3 8B reasoning
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,...
Capabilities
Context Window 40k tokens
Max Output 8k tokens
Inputs
Outputs
Pricing (per 1M tokens)
Input $0.05
Output $0.40
Cache Read $0.05
Cache Write -
Supported Parameters
frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p