R1 0528

R1 0528

by DeepSeek

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 in an inference pass. Fully open-source model.

Capabilities

Text Generation 163K Context
0/500

AI can make mistakes. Handle with care.

Daily Limit Reached

You've used all 10 free messages for today. Join our waitlist to get unlimited access when we launch!