Skip to main content

Hunyuan A13B Instruct

General purpose

Tencent · Released July 2025 · Knowledge cutoff March 2025

Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark...

Facts and pricing

Provider
Tencent
Context window
131K tokens
Input price
1.5 credits / 1M tokens ($0.14 raw)
Output price
6.3 credits / 1M tokens ($0.57 raw)
Vision (image input)
No
Tool calling
No
Extended reasoning
No

Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.10x margin. Raw prices shown per 1M tokens.

What Hunyuan A13B Instruct is best for

Tencent family

ModelContextInput cr/MOutput cr/MReleased
Hy4 preview1.0M9.227.5August 2026
Hy-MT2-1.8B8K0.481.9August 2026
Hy-MT2-30B-A3B8K0.813.2August 2026
Hy-MT2-7B8K0.813.2August 2026
Hy3262K0.913.6July 2026
Hy3 preview262K2.06.6April 2026
Hunyuan A13B Instruct131K1.56.3July 2025

Frequently asked questions

What is Hunyuan A13B Instruct?
Hunyuan A13B Instruct is an AI model by Tencent. Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark...
How much does Hunyuan A13B Instruct cost on Zeplik?
Input tokens cost 1.5 credits per million and output tokens 6.3 credits per million (1 credit = $0.10; the raw provider rates are $0.14 and $0.57 per million). New accounts start with free credits.
How long can a conversation with Hunyuan A13B Instruct be?
Hunyuan A13B Instruct has a 131K-token context window (131,072 tokens), which covers the conversation plus any documents you attach.
Does Hunyuan A13B Instruct support images and tools?
Hunyuan A13B Instruct is text-only and does not support tool calling.

Related models

Hy4 previewGeneral purpose

Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...

1.0M ctx27.5 cr/M outAugust 2026
Hy-MT2-1.8BGeneral purpose

Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided...

8K ctx1.9 cr/M outAugust 2026
Hy-MT2-30B-A3BGeneral purpose

Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and...

8K ctx3.2 cr/M outAugust 2026
Hy-MT2-7BGeneral purpose

Hy-MT2-7B is a 7B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation.

8K ctx3.2 cr/M outAugust 2026
Hy3General purpose

Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...

262K ctx3.6 cr/M outJuly 2026
Hy3 previewGeneral purpose

Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...

262K ctx6.6 cr/M outApril 2026

More you can do with Hunyuan A13B Instruct

Hunyuan A13B Instruct - Tencent AI Model | Zeplik Chat