← All models View on HuggingFace →
DeepSeek: R1 0528
deepseek/deepseek-r1-0528
Tool useJSONReasoningStreaming
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...
Pricing
Input
$0.5 / 1M
Output
$2.15 / 1M
Specs
Context
163,840 tokens
Input
text
Output
text
Knowledge cutoff: 2025-03-31
Released: 2025-05
Supported parameters
frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Open weights · HuggingFace
5,179,850 downloads/mo
2,449 likes
mit text-generation