This model is 13 months old. The same company has since released something newer: Hy-MT2-30B-A3B (2026-08-20). The details below are still accurate for this model — it just is not what we would recommend today.
Hunyuan A13B Instruct
Tencent🇨🇳 China
Tencent's 13B active parameter Mixture-of-Experts (MoE) language model with 80B total parameters. Supports reasoning via Chain-of-Thought with competitive benchmark performance across mathematics and coding.
Context window131K tokens
Input / 1M tokens$0.14
Output / 1M tokens$0.57
Version History
hunyuan-a13b-instruct-2025-07-08major
Tencent launches Hunyuan A13B Instruct, a 13B-active MoE model (80B total params) with Chain-of-Thought reasoning. 131K context at $0.14/$0.57 per 1M tokens.