Hy4 Preview
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.
Last 24 hours of Venice traffic.How it’s measured
Capabilities
What the model takes in, returns and supports through the API.
stream: truetoolsStructured outputsresponse_formatReasoningreasoning_effort none · low · highenable_web_searchNot supportedimage input, video input, audio input, X search and log probabilities
Benchmarks
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
- Weights
- tencent/Hy4-preview
- Added
- Aug 28, 2026
Compare
| Model | Input | Output |
|---|---|---|
| Hy4 Preview | $1.04 | $3.13 |
| Abliterated Large Flash | $1.25 | $2.50 |
| Kimi K2.6 E2EE | $0.87 | $4.12 |
| Pareto | $1.00 | $4.00 |
| Kimi K2.7 Code | $0.75 | $3.50 |
Pricing
Billed per token in USD. Reasoning tokens bill as output.
Estimate a workload
Blended price against similar models
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"
}'https://api.venice.ai/api/v1Parameters
| Parameter | Values |
|---|---|
model | hy4-preview |
messages | text |
max_completion_tokens | Up to 64,000 |
reasoning_effort | none | low | high |
tools | Function definitions |
response_format | { type: |
stream | true | false |
venice_parameters.enable_web_search | auto | on | off |