Command Palette
Search for a command to run

INTELLECT-3

by PrimeIntellect

Specifications

Input
Output
Context window
128K tokens
Released
Nov 2025

Performance

Speed
40 t/s
TTFT
362 ms
Latency
Intelligence

Pricing

Input
€0.25
per 1M tokens
Output
€1.38
per 1M tokens

About this model

INTELLECT-3 is an open-source foundation model released under Apache 2.0 license. Designed for general-purpose tasks including text generation, reasoning, and code understanding. Built through decentralized training approach, representing community-driven AI development. Features strong performance across diverse benchmarks while maintaining accessibility for research and commercial use. Supports function calling and tool integration with focus on practical deployment scenarios.

Technical specifications

Capabilities
Input modalities
Output modalities
Reasoning
No

Knowledge horizon

Released Nov 2025
Today
Since release 6 mo

See also

Add Model to Comparison
Search for a model to add
Command Palette
Search for a command to run