← Back to all models

INTELLECT 3

intellect-3

Introducing INTELLECT-3: Scaling RL to a 100B+ MoE model on our end-to-end stack. Achieving state-of-the-art performance for its size across math, code and reasoning.

Available at 3 Providers

Provider Source Input Price ($/1M) Output Price ($/1M) Description Free
vercel vercel Input: $0.20 Output: $1.10 Introducing INTELLECT-3: Scaling RL to a 100B+ MoE model on our end-to-end stack. Achieving state-of-the-art performance for its size across math, code and reasoning.
cortecs models-dev Input: $0.22 Output: $1.20 Provider: Cortecs, Context: 128000, Output Limit: 128000
openrouter openrouter Input: $0.20 Output: $1.10 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, code, science, and general reasoning, consistently outperforming many larger frontier models. Designed for strong multi-step problem solving, it maintains high accuracy on structured tasks while remaining efficient at inference thanks to its MoE architecture. Context: 131072