Hy4 preview

Tencenttext → textHugging Face OpenRouter

The cheapest provider for Hy4 preview is DeepInfra at $1.25 per 1M tokens (blended), charging $0.834 per 1M input and $2.501 per 1M output tokens. 4 providers serve it at the same price. Context window: 1M tokens. Prices tracked since Oct 3, 2026.

Best price

$1.25

at DeepInfra

Input / output

$0.834 / $2.501

per 1M tokens

Providers

1.00× spread

7 days

—

best price

30 days

—

best price

Context

tokens

Providers

Active offers ranked by blended price. Bars are relative to the most expensive.

Provider prices for Tencent: Hy4 preview, USD per 1M tokens
Provider	Input	Output	Blended	vs cheapest	Context	Uptime 1d	Price since
DeepInfraCheapest fp8	$0.834	$2.501	$1.25	best	1M	97.6%	Oct 3
Novita fp8	$0.834	$2.501	$1.25	best	1M	83.9%	Oct 3
SiliconFlow fp8	$0.834	$2.501	$1.25	best	1M	95.8%	Oct 3
Tencent fp8	$0.834	$2.501	$1.25	best	1M	99.5%	Oct 3

DeepInfraCheapest
$1.25
$0.834 in · $2.501 out
best
1M ctx97.6% uptimefp8
Novita
$1.25
$0.834 in · $2.501 out
best
1M ctx83.9% uptimefp8
SiliconFlow
$1.25
$0.834 in · $2.501 out
best
1M ctx95.8% uptimefp8
Tencent
$1.25
$0.834 in · $2.501 out
best
1M ctx99.5% uptimefp8

Blended = (3 × input + output) / 4.

Price history

Hover to compare providers at any point in time. Click a legend item to hide it.

USD per 1M tokens · each step is a price change

Not enough history yet

Tracking since Oct 3, 2026. The chart fills in as new crawls arrive every 6 hours.

Long-context pricing

Higher rates once the prompt passes a size threshold.

Offered by	Prompt size	Input	Output
Tencent	base	$0.834	$2.501
	> 0	$0.834	$2.501
	> 0	$0.751	$2.25

Other pricing

Cache, reasoning and per-call fees. Token rates per 1M; others per unit.

Offered by	Cache read
DeepInfra, Novita +2	$0.042

Change log

Every recorded change for this model since Oct 3, 2026.

No changes yet

Tracking since Oct 3, 2026. Price changes, new providers and delistings will show up here.

About this model

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...

Released: Aug 28, 2026
First tracked: Oct 3, 2026
Canonical slug: tencent/hy4-preview-20260827
Weights: tencent/Hy4-preview