hy4-preview · Hunyuan
Hy4 Preview is Tencent Hunyuan’s large language model for agents, coding, office automation, and complex tool use.Hy4 preview has a total of 770B parameters and 49B active parameters, and is primarily optimized for agent, coding, and productivity scenarios. It strengthens understanding, planning, tool invocation, and sustained execution capabilities for complex tasks. Compared with the previous generation, Hy4 preview further improves multi-step agents, code development, and productivity tasks, offering better task decomposition, context continuity, instruction following, and long-horizon execution. In coding scenarios, it further enhances code understanding, generation, modification, and the handling of complex engineering tasks; in productivity scenarios, it focuses on improving document processing, information analysis, office automation, game development, webpage generation, and cross-tool collaboration. Hy4 preview is suitable for coding agents, complex tool invocation, and various agent workflows that require multi-step planning and sustained execution, providing more reliable task completion for complex real-world business scenarios.
Hy4 Preview is Tencent Hunyuan’s large language model for agents, coding, office automation, and complex tool use.Hy4 preview has a total of 770B parameters and 49B active parameters, and is primarily optimized for agent, coding, and productivity scenarios. It strengthens understanding, planning, tool invocation, and sustained execution capabilities for complex tasks. Compared with the previous generation, Hy4 preview further improves multi-step agents, code development, and productivity tasks, offering better task decomposition, context continuity, instruction following, and long-horizon execution. In coding scenarios, it further enhances code understanding, generation, modification, and the handling of complex engineering tasks; in productivity scenarios, it focuses on improving document processing, information analysis, office automation, game development, webpage generation, and cross-tool collaboration. Hy4 preview is suitable for coding agents, complex tool invocation, and various agent workflows that require multi-step planning and sustained execution, providing more reliable task completion for complex real-world business scenarios.
Hy4 Preview has a 1,048,576 token context window. It supports up to 64,000 output tokens.
On AIHubMix, Hy4 Preview costs $0.845 per million input tokens and $2.535 per million output tokens. Cached input reads are billed at $0.042 per million tokens.
Hy4 Preview accepts text input.
Hy4 Preview supports tool calling, function calling, structured outputs, web search, long context and thinking. Per-protocol parameter support is listed in the capability table on this page.
Hy4 Preview is available through the AIHubMix unified API. The API is OpenAI-compatible: point your OpenAI SDK at https://aihubmix.com/v1, use your AIHubMix API key, and set the model name to hy4-preview — no other code changes needed.
Hy4 Preview is developed by Hunyuan. AIHubMix aggregates it alongside models from other providers behind one API and one bill.
Hy4 Preview was released on August 28, 2026 by Hunyuan.
The Hy3 official version is honed for real-world business scenarios, using a…
The Hy3 official version is honed for real-world business scenarios, using a…
Using the Hunyuan Sheng 3D 3.1 model, it can generate higher-precision and higher-quality…
Hunyuan Hy3 preview is designed for agent workloads, adopting a MoE architecture with…
Hunyuan-A13B-Instruct has 8 billion parameters and can match larger models by activating…
Hunyuan-MT-7B is a lightweight translation model with 7 billion parameters, designed to…
Use Hy4 Preview via the AIHubMix unified API — one interface for every major LLM.