Skip to content
LLMs
Tencent logo

Tencent: Hy4 preview

by Tencent

Tencent: Hy4 preview is a large language model from Tencent. It costs $0.834 per million input tokens and $2.50 per million output tokens. Its context window is 1.0M tokens.

ReasoningTool callingStructured outputPrompt cachingOpen weights
Input / 1M tokens
$0.834
Output / 1M tokens
$2.50
Cached input / 1M
$0.042

On repeated prefixes

Context window
1.0M

tokens

Who serves it cheapest

1 hosts serve Hy4 preview. Same weights, same API - the price difference is pure margin and routing.

Providers serving Tencent: Hy4 preview, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
TencentCheapestfp8$0.834$2.501.0M-100.0%

About 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...

Specifications

Tencent: Hy4 preview specifications
Model IDtencent/hy4-preview
ProviderTencent
Context window1.0M tokens
Max output64K tokens
Input modalitiestext
Output modalitiestext
Knowledge cutoff-
Open weightsYes - tencent/Hy4-preview
ReleasedAugust 28, 2026

Cheaper alternatives

Models that cost less than Hy4 preview while keeping at least half its context window and every input modality it supports.

Frequently asked

How much does Tencent: Hy4 preview cost?

$0.834 per million input tokens and $2.50 per million output tokens. Cached input reads cost $0.042 per million tokens.

What is the context window of Tencent: Hy4 preview?

1.0M tokens, with up to 64K tokens of output per request.