Tencent Hunyuan Hy4 Preview Tops OpenRouter Weekly Usage Chart

Tencent Hunyuan Hy4 Preview claimed the top spot on OpenRouter's weekly usage leaderboard, consuming 187M tokens ($16.2) over the week and surpassing GLM 5.3's 34M (data truncated in the post). Developers say the ranking matches their hands-on experience — fewer output tokens, higher cache hit rates, and lower real costs — yet the model is barely discussed amid the hype around GLM, Qwen, DeepSeek, and Kimi.

Confirmed

@mariofilhoml shared OpenRouter weekly data: Hy4 consumed 187M tokens ($16.2) versus 34M for GLM 5.3 (as shown in the truncated post).
@mariofilhoml and @brunovolpato both said the No.1 ranking matches their trial experience and was unsurprising.
@mariofilhoml found Hy4 used fewer output tokens even at high output settings, with higher OpenRouter cache hit rates and notably cheaper actual costs compared with GLM 5.3.
@cantor8 observed Hy4 is the most-used model on OpenRouter yet almost nobody discusses it.

Unconfirmed

@mariofilhoml admitted his judgment that Hy4 is roughly on par with GLM 5.3 is only a gut feeling without systematic evaluation.
No public benchmark scores or context-length results for Hy4 are available yet.

Why it matters

Topping real-world usage signals meaningful developer adoption, with low cost and token efficiency likely driving it — useful reference for cost-sensitive API users.
The gap between usage and discussion volume suggests actual usage data can reveal overlooked models that community hype misses.

2026-09-05 ~ 2026-09-07 · 5 related posts

Primary sources

Tencent Hy4 burns 187M weekly tokens on OpenRouter, topping GLM 5.3 at 34M — mariofilhoml · 2026-09-06 03:50 (UTC+08:00)
User finds Tencent Hunyuan Hy4 cheaper than GLM 5.3 via fewer output tokens, high cache hit rate — mariofilhoml · 2026-09-06 03:43 (UTC+08:00)
Why is nobody talking about Tencent Hy4, the most-used model on OpenRouter? — cantor8 · 2026-09-07 19:13 (UTC+08:00)

Tencent's Hunyuan Hy4 Preview tops OpenRouter weekly rankings — mariofilhoml · 2026-09-05
Tencent's Hy4 Preview tops OpenRouter weekly ranking, and devs are weighing it vs GLM — brunovolpato · 2026-09-06
[source] User finds Tencent Hunyuan Hy4 cheaper than GLM 5.3 via fewer output tokens, high cache hit rate — mariofilhoml · 2026-09-06
[source] Tencent Hy4 burns 187M weekly tokens on OpenRouter, topping GLM 5.3 at 34M — mariofilhoml · 2026-09-06
[source] Why is nobody talking about Tencent Hy4, the most-used model on OpenRouter? — cantor8 · 2026-09-07