Fastest Prime Intellect Models

Quick answer · Updated June 2026

The fastest Prime Intellect model is INTELLECT-3 at 49 output tokens per second.

49 t/sSpeed

22.2Intelligence

$0.200Input /M

131KContext

AI models ranked by output speed (tokens per second, p50). The fastest large language models for low-latency and high-throughput applications.

1P
intellect-3
ReasoningToolsJSON22.2 intel · $0.200/M · 195ms ttft
49 t/s
Speed

Frequently asked

What is the fastest Prime Intellect model?

The fastest Prime Intellect model is INTELLECT-3 at 49 output tokens per second.

How many Prime Intellect models are there?

modelgrep tracks 1 Prime Intellect models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by INTELLECT-3. 1 of them qualify for this ranking.

More Prime Intellect rankings

Prime Intellect: Smartest LLMs Prime Intellect: Best LLMs for Coding Prime Intellect: Best LLMs for Design & Frontend Prime Intellect: Lowest-Latency LLMs Prime Intellect: Cheapest LLMs Prime Intellect: Best Free LLMs Prime Intellect: Best Reasoning LLMs Prime Intellect: Best Vision LLMs Prime Intellect: Best LLMs for Agents Prime Intellect: Best Open-Source LLMs Prime Intellect: Longest-Context LLMs

All rankings

Small & Fast LLMs Smartest LLMs Best LLMs for Coding Best LLMs for Design & Frontend Lowest-Latency LLMs Cheapest LLMs Best Free LLMs Best Reasoning LLMs Best Vision LLMs Best LLMs for Agents Best Open-Source LLMs Longest-Context LLMs