Lowest-Latency Baidu Models

Quick answer · Updated June 2026

ERNIE 4.5 VL 424B A47B has the lowest latency of any Baidu model, responding in about 1.4s to first token.

1.4sLatency

30 t/sSpeed

$0.420Input /M

131KContext

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

1B
ernie-4.5-vl-424b-a47b
ReasoningVision$0.420/M · 30 t/s · 131K ctx
1.4s
Latency

Frequently asked

Which Baidu model has the lowest latency?

ERNIE 4.5 VL 424B A47B has the lowest latency of any Baidu model, responding in about 1.4s to first token.

How many Baidu models are there?

modelgrep tracks 1 Baidu models with live benchmarks, speed, latency and per-provider pricing. 1 of them qualify for this ranking.

More Baidu rankings

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