Back to all models
deepseek

DeepSeek: R1 0528

May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...

deepseek/deepseek-r1-0528

Context Size

163.84K

Input Price

85,650 pts/M5,267 Ks/M

Output Price

342,900 pts/M21,088 Ks/M


Architecture

Text

Supported Parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Details

TokenizerDeepSeek
Instruct Typedeepseek-r1
Max Completion32,000 tokens
Provider Context128K tokens
ModeratedNo
CreatedMay 28, 2025