Hunyuan-A13B-Instruct

Open weights Active Text LLM MoE hunyuan-a13b

Open-weight 80B MoE (13B active) with fast and slow thinking modes and a 256K context window.

Released
Jun 27, 2025
Context window
262K tokens
Max output
Not disclosed
Parameters
80B 13B active
Input price
Not disclosed
Output price
Not disclosed

Prices are first-party list prices in USD at the standard tier. Last verified Oct 30, 2026.

Pricing

No list price recorded for this model yet.

Specifications

Developer
Tencent
Model type
Text LLM
Architecture
MoE
Parameters
80B (13B active)
Input
Text
Output
Text
Knowledge cutoff
Not disclosed
License
Custom open license
API access
First-party API
Capabilities
Agentic Long context Reasoning