Prime Intellect: INTELLECT-3
PRIME-INTELLECT Developer Architecture Profile
Intelligence (ELO)1429Chatbot Arena Verified
Max Context131,072Tokens
API Cost / 1M$1.30Blended Prompt + Completion
Model Capabilities
- Coding & Logic
- Fictional
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,...
Granular Pricing Matrix
Input Tokens (Prompt)$0.20 / 1M
Output Tokens (Completion)$1.10 / 1M
Pricing data via OpenRouter. Sync: 4/30/2026
Evaluate Competitors
VS Engine MatchupPrime Intellect: INTELLECT-3 vs Qwen: Qwen3.5-FlashVS Engine MatchupPrime Intellect: INTELLECT-3 vs Z.ai: GLM 4.6VVS Engine MatchupPrime Intellect: INTELLECT-3 vs Mistral: Ministral 3 8B 2512VS Engine MatchupPrime Intellect: INTELLECT-3 vs Qwen: Qwen Plus 0728 (thinking)VS Engine MatchupPrime Intellect: INTELLECT-3 vs xAI: Grok Code Fast 1VS Engine MatchupPrime Intellect: INTELLECT-3 vs Z.ai: GLM 4.5V