SargalaySargalay

Command Palette

Search for a command to run...

Back to all models
prime-intellect

Prime Intellect: INTELLECT-3

INTELLECT-3 is a 106B-parameter Mixture-of-Experts model (12B active) post-trained from GLM-4.5-Air-Base using supervised fine-tuning (SFT) followed by large-scale reinforcement learning (RL). It offers state-of-the-art performance for its size across math,...

prime-intellect/intellect-3

Context Size

131.072K

Input Price

1,230 Ks/M

Output Price

6,765 Ks/M


Architecture

Text

Supported Parameters

frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningrepetition_penaltyresponse_formatstructured_outputstemperaturetool_choicetoolstop_ktop_p

Details

TokenizerOther
Max Completion131,072 tokens
Provider Context131.072K tokens
ModeratedNo