Tencent: Hy3
tencent/hy3
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:...
Modalities
In / Out Price
$0.0825 / $0.33 per 1M
Context
262K
Released
Jul 6, 2026
Knowledge Cutoff
—
Pricing
What Reroute charges per unit. No markup on inference — you pay the carrier's price, metered from the carrier's own usage numbers.
Input tokens
$0.0825 / M
Output tokens
$0.33 / M
Cache read
$0.0206 / M
Long-context pricing
Prompts over 0 tokens: $0.132 input / $0.528 output per M.
Prompts over 0 tokens: $0.0825 input / $0.33 output per M.
By provider
Each carrier sets its own price. The router weighs these against uptime when it picks one.
| Provider | Input /M | Output /M | Cache read /M | Cache write /M | Discount |
|---|---|---|---|---|---|
| Tencent | $0.0825 | $0.33 | $0.0206 | — | — |
 Novita | $0.14 | $0.58 | $0.035 | — | — |
 GMICloud | $0.14 | $0.58 | $0.035 | — | — |
 Phala | $0.15 | $0.64 | $0.04 | — | — |
 AtlasCloud | $0.20 | $0.80 | $0.05 | — | — |