Hy4 Preview - MixRoute API

Hy4 Preview is Tencent Hy’s next-generation flagship productivity model for complex agents, long-horizon software engineering, office work, and analytical tasks. Call hy4-preview through MixRoute using the OpenAI-compatible Chat Completions endpoint.

Key capabilities

1M context window - Supports up to 960K input tokens and 64K output tokens
Agentic productivity - Designed for complex task execution, coding, documents, spreadsheets, and analysis
Reasoning and tools - Supports preserved thinking, structured output, function calling, and caching
Large MoE architecture - 770B total parameters with 49B activated per token

Quick example

cURL
Python

curl "https://api.mixroute.ai/v1/chat/completions" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "hy4-preview",
    "messages": [
      {
        "role": "user",
        "content": "Review this deployment plan and identify the highest-risk assumption."
      }
    ],
    "max_tokens": 256
  }'

from openai import OpenAI

client = OpenAI(api_key="YOUR_API_KEY", base_url="https://api.mixroute.ai/v1")

response = client.chat.completions.create(
    model="hy4-preview",
    messages=[{"role": "user", "content": "Review this deployment plan and identify the highest-risk assumption."}],
    max_tokens=256,
)

print(response.choices[0].message.content)

Parameters

Parameter	Type	Required	Description
`model`	string	Yes	Model ID. Must be `hy4-preview`.
`messages`	array	Yes	Conversation messages with role and content.
`max_tokens`	integer	No	Maximum generated tokens.
`stream`	boolean	No	Enable SSE streaming.
`reasoning_effort`	string	No	Reasoning effort when supported by the model.
`tools`	array	No	OpenAI-compatible tool definitions.

Vendor reference