hy3

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.

API Pricing

Input$0.16 / 1M tokens
Output$0.62 / 1M tokens
Cache read$0.04 / 1M tokens

Specifications

Context window256,000 tokens
Modalitiestext
Featurestool calling, function calling, structured outputs, web, long context, thinking

FAQ

What is hy3?

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.

What is the context length of hy3?

hy3 has a 256,000 token context window.

How much does hy3 cost?

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.

What modalities does hy3 support?

hy3 accepts text input.

What features does hy3 support?

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.

How do I call hy3 via API?

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.

Who develops hy3?

hy3 is developed by Hunyuan. AIHubMix aggregates it alongside models from other providers behind one API and one bill.

More from Hunyuan

hy-3d-3.1

by Hunyuan

Using the Hunyuan Sheng 3D 3.1 model, it can generate higher-precision and higher-quality…

$2/1M in · $2/1M out

hy3-preview

by Hunyuan

Hunyuan Hy3 preview is designed for agent workloads, adopting a MoE architecture with…

$0.17/1M in · $0.57/1M out
256,000 tokens context

tencent/Hunyuan-A13B-Instruct

by Hunyuan

Hunyuan-A13B-Instruct has 8 billion parameters and can match larger models by activating…

$0.14/1M in · $0.56/1M out

tencent/Hunyuan-MT-7B

by Hunyuan

Hunyuan-MT-7B is a lightweight translation model with 7 billion parameters, designed to…

$0.2/1M in · $0.2/1M out

Use hy3 via the AIHubMix unified API — one interface for every major LLM.