Skip to content
LLMs
Tencent logo

Tencent: Hy3 preview

by Tencent

Tencent: Hy3 preview is a large language model from Tencent. It costs $0.180 per million input tokens and $0.600 per million output tokens. Its context window is 262K tokens.

ReasoningTool callingPrompt cachingOpen weights
Input / 1M tokens
$0.180
Output / 1M tokens
$0.600
Cached input / 1M
$0.060

On repeated prefixes

Context window
262K

tokens

Who serves it cheapest

1 hosts serve Hy3 preview. Same weights, same API - the price difference is pure margin and routing.

Providers serving Tencent: Hy3 preview, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
GMICloudCheapestbf16$0.180$0.600262K-100.0%

Benchmarks

Independent scores published alongside the catalogue.

Intelligence index
25.8
Coding index
58.8
Agentic index
25.6

About Hy3 preview

Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...

Specifications

Tencent: Hy3 preview specifications
Model IDtencent/hy3-preview
ProviderTencent
Context window262K tokens
Max output236K tokens
Input modalitiestext
Output modalitiestext
Knowledge cutoff-
Open weightsYes - tencent/Hy3-preview
ReleasedApril 22, 2026

Cheaper alternatives

Models that cost less than Hy3 preview while keeping at least half its context window and every input modality it supports.

Frequently asked

How much does Tencent: Hy3 preview cost?

$0.180 per million input tokens and $0.600 per million output tokens. Cached input reads cost $0.060 per million tokens.

What is the context window of Tencent: Hy3 preview?

262K tokens, with up to 236K tokens of output per request.