EN Submit a tool

Hunyuan A13B Instruct

Rank #324 tencent

tencent/hunyuan-a13b-instruct

Usage data date 2026-07-26 · updated daily

Usage and specs

Daily rank#324
Daily tokens55.1M
Daily requests51.1K
Daily change −45.3%
Context window32.8K
Released

What is Hunyuan A13B Instruct

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.).

Hunyuan A13B Instruct capabilities

Input: Text   Output: Text

Reasoning output Reasoning JSON output Structured outputs Knowledge cutoff 2025-03-31

Hunyuan A13B Instruct API pricing

Input · per 1M tokens$0.14
Output · per 1M tokens$0.57

List prices in USD; see each provider’s site for current terms.

Tools built on this model