Hy4 Preview API: Pricing and Specs

Hy4 Preview API

Hy4 Preview is a large language model by Tencent Hunyuan, available on the Venice API as hy4-preview. It runs privately, with zero data retention.Hy4 Preview is a 770B-parameter Mixture-of-Experts flagship model from the Tencent Hy team, with 49B parameters active per token and a 1M-token context window. It is post-trained for software engineering, office and data analysis, game development, and scientific research, with strong long-horizon reasoning, tool use, and agentic performance.

Hy4 Preview API pricing

Model ID	Variant	Privacy	Price
`hy4-preview`	Standard	Private	$1.04 / $3.13 per 1M

Hy4 Preview specifications

Spec	Value
Provider	Tencent Hunyuan
Released	Aug 28, 2026
Privacy	Private
Status	Stable
Open weights	Yes
Context window	1M tokens
Max output	64K tokens
Reasoning effort	none, low, high
Served precision	FP4

How to use the Hy4 Preview API

Send requests to POST https://api.venice.ai/api/v1/chat/completions with "model": "hy4-preview" and your API key.

curl https://api.venice.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "hy4-preview",
    "messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }],
    "reasoning_effort": "high"
  }'

Related models

Abliterated Large Flash API: $1.25 / $2.50 per 1M
Kimi K2.7 Code API: $0.75 / $3.50 per 1M
Gemini 3.8 Flash API: $0.9375 / $4.69 per 1M
Gemini 3.7 Flash API: $0.9375 / $4.69 per 1M

Explore

By modality

Hy4 Preview API