Tencent: Hunyuan A13B Instruct

tencent/hunyuan-a13b-instruct

Created Jul 8, 2025131,072 context

$0.14/M input tokens$0.57/M output tokens

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 performance across mathematics, science, coding, and multi-turn reasoning tasks, while maintaining high inference efficiency via Grouped Query Attention (GQA) and quantization support (FP8, GPTQ, etc.).

Tencent: Hunyuan A13B Instruct

tencent/hunyuan-a13b-instruct

Created Jul 8, 2025131,072 context

$0.14/M input tokens$0.57/M output tokens

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 performance across mathematics, science, coding, and multi-turn reasoning tasks, while maintaining high inference efficiency via Grouped Query Attention (GQA) and quantization support (FP8, GPTQ, etc.).

Recent activity on Hunyuan A13B Instruct

Total usage per day on OpenRouter

Prompt

1.21M

Completion

142K

Reasoning

600

Prompt tokens measure input size. Reasoning tokens show internal thinking before a response. Completion tokens reflect total output length.