INTELLECT 3 is a 100B+ Mixture-of-Experts language model from Prime Intellect. Through AI Gateway it runs with a context window of 131.1K tokens at $0.20 input and $1.10 output per million tokens. Model type: chat.
import { streamText } from 'ai'
const result = streamText({ model: 'prime-intellect/intellect-3', prompt: 'Why is the sky blue?'})INTELLECT 3 is a Mixture-of-Experts (MoE) language model built on the GLM-4.5-Air base and released November 26, 2025. It targets math, code, science, and logic workloads.
Prime Intellect published benchmark results for this model class on math, code, science, and reasoning. The model targets research, software engineering, and multi-step reasoning. On AI Gateway, INTELLECT 3 supports a context window of 131.1K tokens and up to 131.1K tokens per request.
Details: https://www.primeintellect.ai/blog/intellect-3.