Wednesday, October 28, 2026 🏢 AI Companies Hub RSS About Contact Admin
POPULAR BEATS: Generative AI LLMs & NLP Autonomous Agents Robotics & Hardware Enterprise AI AI Ethics & Policy 🏢 All AI Companies

Hunyuan-Large

Large-Scale MoE Transformer
Official Source & Paper
Tencent AI logo Tencent 📄 Open Weights (Tencent Hunyuan License) 🌍 China (China) 🗓️ Effective Date: 05.11.2024

Tencent's open-weights flagship MoE architecture delivering enterprise-grade bilingual performance on 256k token documents.

Model Size / Parameters 389B (52B active) Architecture: Large-Scale MoE Transformer
Context Window (Input) 256k tokens Token Capacity
Max Output Tokens 16k tokens Single Generation Limit
Supported Modalities Text, Code Native Multimodal Ingestion
License & Access Open Weights (Tencent Hunyuan License) Open Weights vs. API
Release Date November 2024 Effective Date: 05.11.2024

Verified Benchmark Results

Standardized academic and industry evaluation benchmarks (Effective Date: 05.11.2024).

MMLU-Pro / 5-Shot General Intellect
85.2%
SWE-bench Verified Software Engineering
38.5%
MATH 500 / AIME Mathematical Reasoning
82.4%
GPQA Diamond Doctoral Science
47.1%
HumanEval / Python Algorithm Synthesis
83.0%

Pricing & Cost Efficiency

Official API token pricing and self-hosted licensing terms.

Input Pricing (Prompt)
Free / Self-Hosted
Per 1 million processed tokens
Output Pricing (Generation)
Free / Self-Hosted
Per 1 million generated tokens
Verified Datasheet: Source: Tencent Research Documentation • Effective Date: 05.11.2024
← Back to All AI Model Datasheets