← All models
P
Prime Intellect: INTELLECT-3
prime-intellect/intellect-3
Tool useJSONReasoningStreaming
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,...
Pricing
Input
$0.2 / 1M
Output
$1.10 / 1M
Specs
Context
131,072 tokens
Input
text
Output
text
Released: 2025-11
Supported parameters
frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningrepetition_penaltyresponse_formatstructured_outputstemperaturetool_choicetoolstop_ktop_p