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.

Context
131K
Max output
118K
Input price
$0.14/1M tokens
Output price
$0.57/1M tokens

Capabilities

Reasoning & Interaction
Reasoning
Output Control
Structured Output
JSON Mode

Details

Model IDtencent/hunyuan-a13b-instruct
Provider OpenRouter
Creator tencent
Family—
License—
Status—
Type—
Input modalitiestext
Output modalitiestext
Open weight—
Parameters—
Architecture—
Context window131K tokens
Max input—
Max output118K tokens
Reasoning tokens—
Knowledge cutoff—
Release date
Sourceofficial

Pricing

Input
$0.14
Output
$0.57
Cache write
—
Cache read
—
Batch in
—
Batch out
—

API

GET/v1/models/openrouter/tencent/hunyuan-a13b-instruct

Tencent: Hunyuan A13B Instruct

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.

Changes · 5 entries
tencent/hunyuan-a13b-instructupdateca7a400Nov 2, 2026, 03:02 AM
max_output_tokens131072→117964
tencent/hunyuan-a13b-instructupdatee3d7dedAug 31, 2026, 04:13 AM
max_output_tokens131072→117964
tencent/hunyuan-a13b-instructupdate1cd659eMar 24, 2026, 04:19 AM
capabilitiesjson modeyes
tencent/hunyuan-a13b-instructupdate2b100acMar 23, 2026, 05:30 AM
release_date2025-07-08
taglineHunyuan-A13B is a 13B active parameter Mixture-of-Experts...
tencent/hunyuan-a13b-instructcreate7f5c66fMar 21, 2026, 05:16 AM