INTELLECT-3

Released
2026-04-01
Last refreshed
2026-06-29
Status
Researched 158d ago
Open sourceCommercial use: permittedRAGAgentsLong contextClassificationJSON / Tool use

INTELLECT-3 is a released rag, agents, and long context model with open-source and 128K context; evaluate it while provider pricing coverage matures.

Prime Intellect releases · 1 in the last 12 monthsChangelog →
Specifications
Family
INTELLECT
Released
2026-04-01
Context
128K
Parameters
106B
Architecture
Mixture of Experts
Specialization
general
Openness
Open source
License
Apache 2.0OSI-approvedPermitted
Weights
Available
Code
Unknown
Training
Fine-tuned
Created by

Prime Intellect is an AI research organization focused on decentralized training and open-weights frontier models includ

Website
Pricing

No tracked provider pricing is available yet.

About

INTELLECT-3 is Prime Intellect's 106B-parameter MoE model with 12B active parameters, post-trained from GLM-4.5-Air-Base via SFT and reinforcement learning, matching frontier closed-model performance.

Providers

No active provider routes are tracked for this model yet.

Capabilities

ReasoningJSON / Tool useStructured Outputs

Benchmark peer barsfor RAG

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.