Lowest-Latency Inception Models

Quick answer · Updated June 2026

Mercury 2 has the lowest latency of any Inception model, responding in about 632ms to first token.

632msLatency

32.8Intelligence

539 t/sSpeed

$0.250Input /M

128KContext

AI models ranked by time-to-first-token (p50). The most responsive large language models for real-time and interactive use cases.

1I
mercury-2
ReasoningToolsJSON32.8 intel · $0.250/M · 539 t/s
632ms
Latency

Frequently asked

Which Inception model has the lowest latency?

Mercury 2 has the lowest latency of any Inception model, responding in about 632ms to first token.

How many Inception models are there?

modelgrep tracks 1 Inception models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by Mercury 2. 1 of them qualify for this ranking.

More Inception rankings

Inception: Smartest LLMs Inception: Best LLMs for Coding Inception: Best LLMs for Design & Frontend Inception: Fastest LLMs Inception: Cheapest LLMs Inception: Best Free LLMs Inception: Best Reasoning LLMs Inception: Best Vision LLMs Inception: Best LLMs for Agents Inception: Best Open-Source LLMs Inception: Longest-Context LLMs

All rankings

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