by Hunyuan
The Hy3 official version is honed for real-world business scenarios, using a Mixture-of-Experts (MoE) architecture with 295B total parameters and 21B activated parameters. It natively supports a 256K context window and offers multiple thinking modes: no_think (ultra-fast response), think_low (quick thinking), and think_high (deep reasoning), balancing ultra-fast responses, complex reasoning, and invocation cost. Compared with the Preview version, Hy3—based on real business feedback from Tencent Yuanbao, WorkBuddy, ima, Marvis, and others—focuses on improving the Coding Agent, long-form understanding, multi-turn context continuity, search QA, and complex task execution, performing more stably in reducing hallucinations, improving task completion, and engineering usability. It is better suited to practical scenarios such as frontend tasks, cross-file code development, long-document analysis, office automation, and multi-step Agent workflows.
The Hy3 official version is honed for real-world business scenarios, using a Mixture-of-Experts (MoE) architecture with 295B total parameters and 21B activated parameters. It natively supports a 256K context window and offers multiple thinking modes: no_think (ultra-fast response), think_low (quick thinking), and think_high (deep reasoning), balancing ultra-fast responses, complex reasoning, and invocation cost. Compared with the Preview version, Hy3—based on real business feedback from Tencent Yuanbao, WorkBuddy, ima, Marvis, and others—focuses on improving the Coding Agent, long-form understanding, multi-turn context continuity, search QA, and complex task execution, performing more stably in reducing hallucinations, improving task completion, and engineering usability. It is better suited to practical scenarios such as frontend tasks, cross-file code development, long-document analysis, office automation, and multi-step Agent workflows.
hy3 has a 256,000 token context window.
On AIHubMix, hy3 costs $0.16 per million input tokens and $0.62 per million output tokens. Cached input reads are billed at $0.04 per million tokens.
hy3 accepts text input.
hy3 supports tool calling, function calling, structured outputs, web, long context and thinking. Per-protocol parameter support is listed in the capability table on this page.
hy3 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 hy3 — no other code changes needed.
hy3 is developed by Hunyuan. AIHubMix aggregates it alongside models from other providers behind one API and one bill.
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 hy3 via the AIHubMix unified API — one interface for every major LLM.