Skip to main content
Tencent HunyuanAug 28, 2026

Hy4 Preview

hy4-previewPrivateOpen weights

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.

$1.04/$3.13
per 1M in / out
1M
context window
64K
max output
How it comparesamong 143 text models
GPQA Diamondhigher than 61%88.4%
Blended pricecheaper than 54%$1.56
Context windowlarger than 88%1M
Max outputlarger than 35%64K

Further right is better. Hover a dot for its model.

Time to first token— 
Output speed— 
Uptime— 

Last 24 hours of Venice traffic.How it’s measured

Capabilities

What the model takes in, returns and supports through the API.

InText
OutText
Streamingstream: true
Function callingtoolsStructured outputsresponse_formatReasoningreasoning_effort none · low · high
Web searchenable_web_search
Prompt cachingReads at $0.0525
Optimized for codeTuned for software work

Not supportedimage input, video input, audio input, X search and log probabilities

Benchmarks

GPQA Diamond
88.4%51st of 139 · 8 score higher for less, including DeepSeek v4.1 Flash (1017), MiniMax M2.5 and DeepSeek V4.1 Flash 1017 Uncensored

Specs

Model ID
hy4-preview
Endpoint
POST /api/v1/chat/completions
Context window
1,048,576 tokens
Max output
64,000 tokens
Reasoning
none · low · high · default high
Precision
FP4
Privacy
Private
Added
Aug 28, 2026

Compare

ModelInputOutputGPQA DiamondContextMax outputFirst tokenSpeed
Hy4 Preview$1.04$3.1388.4%1M64K——
Abliterated Large Flash$1.25$2.5088.9%1M128K——
Kimi K2.6 E2EE$0.87$4.12—256K8K——
Pareto$1.00$4.0094.8%1M32K——
Kimi K2.7 Code$0.75$3.5084.3%256K64K——

Pricing

Billed per token in USD. Reasoning tokens bill as output.

Input$1.04per 1M tokens
Cached input$0.052595% off input
Output$3.13per 1M tokens

Estimate a workload

$0.0036per request
$36.48for 10,000 requests

Blended price against similar models

Hy4 Preview$1.56
Pareto$1.75

Per 1M tokens at three input tokens for each output token.

Quickstart

OpenAI-compatible: point any OpenAI SDK at the Venice base URL with a Venice 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"
}'
Base URL https://api.venice.ai/api/v1

Parameters

ParameterValuesNotes
modelhy4-previewRequired
messagestextContent parts the model reads
max_completion_tokensUp to 64,000Counts reasoning tokens
reasoning_effortnone | low | highDefault high
toolsFunction definitionsWith tool_choice
response_format{ type: "json_schema" }Output that matches a schema
streamtrue | falseServer-sent events
venice_parameters.enable_web_searchauto | on | offWeb results and citations