Back to all models
qwen
qwenQwen: Qwen3.8 27B
Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...
qwen/qwen3.8-27b
Context Size
1,000K
Input Price
63,000 pts/M
Output Price
450,000 pts/M
Architecture
Text
Image
Video
Supported Parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Details
TokenizerQwen
Max Completion131,072 tokens
Provider Context1,000K tokens
ModeratedNo
CreatedAug 14, 2026