Hy3 – Benchmarks, Pricing & Intelligence Analysis
Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...
Not available on LLMBase
Hy3 is not currently available in LLMBase Chat or the LLMBase Inference API. Benchmarks, pricing, and model details remain available for research and comparison.
Specifications
Technical details and pricing.
Benchmarks
4 benchmark scores from Artificial Analysis.
Composite Indices
Higher is better; speed and price are normalized
Standard Benchmarks
Only benchmarks with data are shown
EU-Hosted Inference API
Power your AI projects with the best open-source models.
Drop-in OpenAI-compatible API. No data leaves Europe.
Explore Inference APIMiniMax
MiniMax M3
$0.40 / $1.40
per M tokens
Z.ai
GLM 5.2
$1.40 / $4.40
per M tokens
MoonshotAI
Kimi K3
$4.00 / $18.00
per M tokens
DeepSeek
DeepSeek V4 Pro
$1.80 / $3.60
per M tokens
Frequently Asked Questions
What is Hy3 good for?
Use Hy3 for everyday tasks like writing, summarizing, brainstorming, and getting clear explanations.
How much does Hy3 cost?
Pricing is based on usage. Current rates are $0.14/1M tokens for input and $0.56/1M tokens for output.
Is Hy3 available in LLMBase Chat yet?
Not yet on this page. We will add chat and inference actions automatically once an exact catalog entry exists for Hy3.
Does Hy3 support images or audio?
Hy3 focuses on text-based tasks.
Similar Models
Other models you might want to explore.
Benchmarks and pricing use Artificial Analysis where available. Catalog specs are used as a fallback.