---
title: "Hunyuan-A13B — LLM-TEST.com"
url: /models/hunyuan-a13b/
canonical_url: https://llm-test.com/models/hunyuan-a13b/
language: en
type: model
summary: "An open-weight mixture-of-experts model with roughly 13B active parameters, giving self-hosters strong quality at modest inference cost."
last_updated: "2026-11-05"
---

# Hunyuan-A13B

_Tencent · Balanced · open weights_

An open-weight mixture-of-experts model with roughly 13B active parameters, giving self-hosters strong quality at modest inference cost.

## At a glance

- Released: Apr 2, 2026
- Provider: Tencent
- Context window: 256,000 tokens
- Max output: 16,000 tokens
- Modalities: Text → text
- Knowledge cutoff: December 2025
- API model ID: `hunyuan-a13b`
- License: Open weights (Tencent Hunyuan Community License)

## Pricing

- Standard: $0.07 input / $0.28 output per 1M tokens (aggregator estimate)
- Example: a 1,500-token prompt + 650-token answer ≈ $0.0003 (standard)

## Best use cases

- **Self-hosted deployment** — Runs on-prem for teams that want Hunyuan quality without the API.
- **Efficient serving** — Activates only a fraction of parameters per token to cut costs.
- **Fine-tuning** — Provides an open base for domain adaptation and research.

## Strengths

- Open weights
- Efficient MoE serving
- Good general quality

## Limitations

- License has usage restrictions
- Text only

## Where to get access

- Consumer app: Tencent Yuanbao / Hunyuan web — https://hunyuan.tencent.com
- API: Tencent Cloud (the Hunyuan API) — https://cloud.tencent.com/product/hunyuan
- Also available: open weights for several Hunyuan models
- Docs: https://cloud.tencent.com/document/product/1729

Full comparison and live pricing: https://llm-test.com/ · directory: https://llm-test.com/models/