Back to all models
qwen
qwenQwen: Qwen3 14B
Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for...
qwen/qwen3-14b
Context Size
131.702K
Input Price
15,000 pts/M
Output Price
36,000 pts/M
Architecture
Text
Supported Parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Details
TokenizerQwen3
Instruct Typeqwen3
Max Completion40,960 tokens
Provider Context40.96K tokens
ModeratedNo
CreatedApr 28, 2025