hy3-preview

by Hunyuan

Hunyuan Hy3 preview is designed for agent workloads, adopting a MoE architecture with 295B capacity and 21B activated parameters. It provides three modes within the same model—no_think (ultra-fast response), think_low (fast thinking), and think_high (deep reasoning)—to accommodate different latency and depth requirements from high-frequency interactions to complex engineering tasks. On code benchmarks such as SWE-bench Verified it approaches the current state of the art, and its 256K context supports cross-file code refactoring and long-document analysis. It is suitable for developers who require reliable task completion while being sensitive to inference costs.

API Pricing

Input$0.17 / 1M tokens
Output$0.57 / 1M tokens
Cache read$0.05 / 1M tokens

Specifications

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

FAQ

What is hy3-preview?

Hunyuan Hy3 preview is designed for agent workloads, adopting a MoE architecture with 295B capacity and 21B activated parameters. It provides three modes within the same model—no_think (ultra-fast response), think_low (fast thinking), and think_high (deep reasoning)—to accommodate different latency and depth requirements from high-frequency interactions to complex engineering tasks. On code benchmarks such as SWE-bench Verified it approaches the current state of the art, and its 256K context supports cross-file code refactoring and long-document analysis. It is suitable for developers who require reliable task completion while being sensitive to inference costs.

What is the context length of hy3-preview?

hy3-preview has a 256,000 token context window.

How much does hy3-preview cost?

On AIHubMix, hy3-preview costs $0.17 per million input tokens and $0.57 per million output tokens. Cached input reads are billed at $0.05 per million tokens.

What modalities does hy3-preview support?

hy3-preview accepts text input.

What features does hy3-preview support?

hy3-preview 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-preview via API?

hy3-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 hy3-preview — no other code changes needed.

Who develops hy3-preview?

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

More from Hunyuan

hy3

by Hunyuan

The Hy3 official version is honed for real-world business scenarios, using a…

$0.16/1M in · $0.62/1M out
256,000 tokens context

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

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-preview via the AIHubMix unified API — one interface for every major LLM.