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