Hy4 preview

by Tencent · tencent/hy4-preview

Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...

Input / 1M tokens
$0.751
Output / 1M tokens
$2.25
Context
1.05M

Specs

Input price$0.751 / 1M tokens
Output price$2.25 / 1M tokens
Cached input$0.0378 / 1M tokens
Context window1.05M tokens
Max output64K tokens
Readstext
Writestext
Tool callingYes
ReasoningYes
ListedAug 28, 2026

List prices in USD, updated Oct 30, 2026. Providers may charge differently.

Providers

7 providers serve this model, as of Oct 30, 2026, 18:12 UTC.

Providers serving this model, sorted by price
ProviderQuantizationContextMax outputInput / 1MOutput / 1MCache read / 1MUptime (30 min)Latency (median)Throughput (median)SupportsStatus
TencentCheapestfp81.05M64K$0.751$2.25$0.0378100%2.97 s47 tok/sNormal
DeepInfrafp41.05M131K$0.792$2.38$0.0399100%1.09 s83 tok/sNormal
AtlasCloudfp81.05M64K$0.834$2.50$0.042100%2.70 s40 tok/sNormal
CohereFastest—262K131K$0.834$2.50$0.042—347 ms119 tok/sNormal
GMICloudbf16262K236K$0.834$2.50$0.042—5.68 s27 tok/sNormal
Novitafp81M64K$0.834$2.50$0.042100%4.40 s44 tok/sNormal
SiliconFlowfp81.05M262K$0.834$2.50$0.042100%1.79 s50 tok/sNormal

"Cheapest" is the lowest input plus output price; "Fastest" the highest median throughput. Columns empty for every provider are not shown.

Usage

#5
by tokens, Oct 29, 2026
1.68T
tokens that day · 7 days +6%

Data as of 2026-10-30T18:12:03.879Z.All rankings