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).
Specifications
| Lab | Prime Intellect |
|---|---|
| Context window | 131.1K tokens |
| Input price | $0.20/1M |
| Output price | $1.10/1M |
| Release | Nov 2025 |
Strengths
- 106B total parameters with 12B active (MoE architecture)
- Post-trained from GLM-4.5-Air-Base with SFT + large-scale RL
- State-of-the-art performance for its size class
- Budget pricing at $0.20/$1.10 per 1M tokens
- Strong across reasoning, coding, and general intelligence benchmarks
Weaknesses
- Derived from GLM-4.5 base model, not trained from scratch
- Smaller community and ecosystem vs Qwen/DeepSeek alternatives
- Limited deployment options outside of Prime Intellect/OR
Best for
- Cost-effective high-quality inference
- Open-weight fine-tuning and customization
- General reasoning and coding tasks
- Research and experimentation with MoE architectures
In Depth: INTELLECT-3
Summary
INTELLECT-3 is an AI model from Prime Intellect.
Released in Nov 2025. It currently appears in the Overall category on LMRank. It takes text input and produces text output, with a context window of 131.1K tokens. Input pricing is $0.20 per 1M tokens and output is $1.10 per 1M tokens on OpenRouter.