Hy3
Tencent
Built for real-world business scenarios, Hy3 features a 295B/21B active MoE architecture, native 256K context support, and three reasoning modes. It enhances coding, long-form comprehension, multi-turn dialogue, and agentic task execution, balancing reliability, efficiency, and cost across both high-frequency interactions and complex workflows.
- Language
- Implicit caching
- Reasoning
- Tool use
- Structured output
- open weights
- Context
- 262K
- Max output
- 262K
- Input / 1M
- $0.140
- Output / 1M
- $0.580
Quickstart
Point any OpenAI-compatible client at Maxynetic Systems and pass tencent/hy3 as the model.
curl https://api.maxynetic.com/v1/chat/completions \
-H "Authorization: Bearer $MAXYNETIC_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "tencent/hy3",
"messages": [{ "role": "user", "content": "Explain routing in one line." }]
}'Pricing
Billed per token with no markup on the underlying provider rate.
Input
Per 1M prompt tokens
$0.140
Output
Per 1M completion tokens
$0.580
Cache read
Per 1M cached prompt tokens
$0.035
A 1M-token prompt with 250K tokens of output costs about $0.285.
Rates for this model vary by upstream provider; Maxynetic Systems routes to the cheapest healthy one by default.