Hy4 preview

AI model Released Aug 28, 2026

Context window: 1,024,000 tokens
Maximum output: 64,000 tokens
Open weights: Yes

No matched benchmark results are available for this entry yet.

Run it locally

Inference · memory estimate

Hy4 preview

Not enough verified architecture information for a reliable VRAM estimate.

API cost

USD / month

Input tokens / monthOutput tokens / month

Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.

Hy4 preview

Provider offer

Hy4 preview / Pricing tiers 1

Provider / scope	Rate	Currency	Amount / unit
DeepInfratencent/Hy4-previewStandard	Cached input	USD	0.042 / 1M tokens
	Input	USD	0.834 / 1M tokens
	Output	USD	2.501 / 1M tokens

Capabilities

Context window: 1,024,000 tokens
Maximum output: 64,000 tokens
Reasoning: Yes
Tool calling: Yes
Open weights: Yes

Input modalities

text

Output modalities

text