Back to all models
qwen

Qwen: Qwen3.8 27B (batch)

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:batch

Context Size

262.144K

Input Price

24,000 pts/M1,476 Ks/M

Output Price

300,000 pts/M18,450 Ks/M


Architecture

Text
Image
Video

Supported Parameters

frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p

Details

TokenizerQwen
Max Completion235,929 tokens
Provider Context262.144K tokens
ModeratedNo
CreatedAug 14, 2026