Hy4 Preview

LLM
Tencent

Hy4 Preview is built for real-world productivity tasks including coding, office work, and scientific research. This 770B-parameter MoE model activates 49B parameters per token and supports a 1,000,000 token context window.

Context tokens

1,000,000

Output tokens

8,192

Released

Sep 17, 2026

Capabilities

Tool use
Structured output

Supported tools

  • Seclai Content Tools

    Inspect source documents connected to your account. Includes tools for loading full content, reading character ranges, searching within documents, viewing stats, and listing available content sources. When a source_connection_content_version_id is provided in agent run metadata it is used as the default. Otherwise the model can discover content via list_content_sources.

  • Seclai Knowledge Base

    Search your knowledge bases using semantic similarity. Includes search_knowledge_base and list_knowledge_bases. When a knowledge_base_id is provided in the prompt or agent run metadata it is used as the default. Otherwise the model can discover available knowledge bases at runtime.

  • Seclai Memory Banks

    Manage persistent memory across agent runs. Includes tools for listing memory banks, writing entries, searching memory via semantic similarity, and loading entries in chronological order. Supports two memory types: 'conversation' (speaker-attributed turns) and 'general' (freeform text). Use key to organize entries by topic, session, or user.

Pricing

TypeCreditsUnits
Input11.0922Credits per 1k tokens
Output33.2633Credits per 1k tokens
Cache hit0.5586Credits per 1k tokens

Variants

No variants available for this model.

Try This Model

Write a prompt and experiment with Hy4 Preview in the model experiments page. You can compare it with other models side by side.