Model Comparison
Hy3-preview
vs
gemma-4-26B-A4B-it
May 11, 2026
Pricing
Input
$
0.066
/ M Tokens
$
0.12
/ M Tokens
Output
$
0.26
/ M Tokens
$
0.4
/ M Tokens
Metadata
Create on
Apr 13, 2026
Mar 11, 2026
License
TENCENT HY COMMUNITY LICENSE AGREEMENT
APACHE 2.0
Provider
Tencent
Specification
State
Available
Available
Architecture
Mixture-of-Experts
Mixture of Experts
Calibrated
No
Yes
Mixture of Experts
Yes
Yes
Total Parameters
80B
31B
Activated Parameters
21B
3.8B
Reasoning
No
No
Precision
FP8
FP8
Context length
262K
262K
Max Tokens
262K
262K
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
Not 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
