Tencent

Hunyuan A13B Instruct

tencent/hunyuan-a13b-instruct

JSON

Specification

Published by the vendor; the platform bills at the target's declared price.

Hunyuan A13B Instruct

reasoning open weights

Tencent tencent/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...

Input $/1M: $0.14
Output $/1M: $0.57
Context: 131K
Max output: 118K
Released: Jul 8, 2025
Modalities: text

On this deployment

No routing target resolves to this model yet. Declare one and the router picks it up without retraining.

Not routable here yet

Add a target with metadata.model set to this id.

targets.yamlyaml

# targets.yaml - declare a target that runs Hunyuan A13B Instruct
targets:
  - id: hunyuan-a13b-instruct
    kind: llm
    name: Hunyuan A13B Instruct
    metadata:
      model: tencent/hunyuan-a13b-instruct          # links the target to this catalogue entry
    capabilities:
      domains: [general]
      supports_tools: false
      context_window: 131072
    cost:
      usd_per_1k_tokens: 0.000355

Price among Tencent models

Input list price per million tokens; Hunyuan A13B Instruct is the 5th cheapest of 7 listed.

1
Hy-MT2-1.8B
$0.04
2
Hy-MT2-30B-A3B
$0.07
3
Hy-MT2-7B
$0.07
4
Hy3
$0.13
5
Hunyuan A13B Instruct
$0.14
6
Hy3 preview
$0.18
7
Hy4 preview
$0.83

More from Tencent

Other models by the same vendor in the catalogue.