Back to all models
deepseek
deepseekDeepSeek: DeepSeek V3.1
DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...
deepseek/deepseek-chat-v3.1
Context Size
163.84K
Input Price
31,500 pts/M
Output Price
118,500 pts/M
Architecture
Text
Supported Parameters
frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Details
TokenizerDeepSeek
Instruct Typedeepseek-v3.1
Max Completion32,768 tokens
Provider Context163.84K tokens
ModeratedNo
CreatedAug 21, 2025