AI Hub
All models
LLMOpen weights

Hunyuan-A13B

Tencent

Updated May 21, 2026 · Benchmarks via Artificial Analysis, specs & pricing via OpenRouter · Methodology · Report an error

Specifications

Type
LLM
Access
Open weights
Released
June 27, 2025
License
Apache 2.0
Parameters
80B (13B active)
Context window
256,000 tokens
Input
Text
Output
Text

Our take

Efficient fine-grained MoE (80B total, 13B active) with dual fast/slow reasoning modes and a 256K context, under Apache 2.0.

Links

Compare Hunyuan-A13B with

See all Hunyuan-A13B alternatives →