modelgrep

Fastest Tencent Models

Quick answer · Updated June 2026

The fastest Tencent model is Hy3 preview at 48 output tokens per second. Hunyuan A13B Instruct (7 t/s) is next.

48 t/sSpeed
41.9Intelligence
$0.063Input /M
262KContext

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

  1. 1T
    hy3-preview
    ReasoningTools41.9 intel · $0.063/M · 4.3s ttft
    48 t/s
    Speed
  2. 2T
    hunyuan-a13b-instruct
    ReasoningJSON$0.140/M · 1.1s ttft · 131K ctx
    7 t/s
    Speed

Frequently asked

What is the fastest Tencent model?

The fastest Tencent model is Hy3 preview at 48 output tokens per second. Hunyuan A13B Instruct (7 t/s) is next.

What's a good alternative to Hy3 preview?

Hunyuan A13B Instruct (7 t/s) is the closest alternative on this metric. See the full ranking above for the tradeoffs.

How many Tencent models are there?

modelgrep tracks 2 Tencent models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by Hy3 preview. 2 of them qualify for this ranking.

More Tencent rankings

All rankings