Model Comparison
Hy3-preview
vs
Qwen2.5-72B-Instruct
May 11, 2026
Pricing
Input
$
0.066
/ M Tokens
$
0.59
/ M Tokens
Output
$
0.26
/ M Tokens
$
0.59
/ M Tokens
Metadata
Create on
Apr 13, 2026
Sep 16, 2024
License
TENCENT HY COMMUNITY LICENSE AGREEMENT
-
Provider
Tencent
Qwen
Specification
State
Available
Available
Architecture
Mixture-of-Experts
Causal Transformer
Calibrated
No
No
Mixture of Experts
Yes
Yes
Total Parameters
80B
72B
Activated Parameters
21B
72.7B
Reasoning
No
No
Precision
FP8
FP8
Context length
262K
33K
Max Tokens
262K
4K
Supported Functionality
Serverless
Supported
Supported
Serverless LoRA
Not supported
Not supported
Fine-tuning
Not supported
Not supported
Embeddings
Not supported
Not supported
Rerankers
Not supported
Not supported
Support image input
Not supported
Not supported
JSON Mode
Not supported
Supported
Structured Outputs
Not supported
Not supported
Tools
Supported
Supported
Fim Completion
Not supported
Not supported
Chat Prefix Completion
Supported
Supported
Hy3-preview in Comparison
See how Hy3-preview compares with other popular models across key dimensions.
VS
Qwen3.6-27B
VS
Qwen3.6-35B-A3B
VS
gemma-4-26B-A4B-it
VS
gemma-4-31B-it
VS
Qwen3.5-27B
VS
Qwen3.5-35B-A3B
VS
Qwen3-VL-32B-Instruct
VS
Qwen3-VL-32B-Thinking
VS
Qwen3-VL-30B-A3B-Instruct
VS
Qwen3-VL-30B-A3B-Thinking
VS
gpt-oss-20b
VS
Qwen3-Coder-30B-A3B-Instruct
VS
Qwen3-30B-A3B-Thinking-2507
VS
Qwen3-30B-A3B-Instruct-2507
VS
Qwen3-14B
VS
Qwen3-32B
VS
Qwen2.5-72B-Instruct
VS
Seed-OSS-36B-Instruct
