INTELLECT-3

prime-intellect

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.

Try Now

Capabilities

Tool Use

Extended Thinking

Example Use Cases

Efficient math or science reasoning

Multi-step coding with thinking

High-accuracy moe reasoning

Technical Specifications

Context Window

131,072 tokens

Max Output

131,072 tokens

Cache Miss Cost

$0.20 per 1M tokens

Non-Reasoning Cost

$1.10 per 1M tokens

Web Search Cost

$15 per 1K calls

Code Execution Cost

$0.19 per 1K calls

⚠️ Legacy

Made legacy on

Reason

Untested

Recommended Replacement

Qwen3.5 Plus