Inference provider
Tencent
5 models served. Speed, latency and price below are medians across this provider's catalogue, not per-endpoint measurements.
Models served
5
Median output speed
72 t/s
Median latency
866ms
Median price / 1M
$0.129
Catalogue
Strongest and fastest on this provider
What the catalogue looks like at the top end, on the two axes that usually decide the choice.
Highest Intelligence Index
Among models this provider serves
- Hy3Tencent25.3
View as table
| Model | Intelligence |
|---|---|
| Hy3 (Tencent) | 25.3 |
Fastest output
Median tokens per second
- Hy-MT2-1.8BTencent116 t/s
- Hy-MT2-7BTencent95 t/s
- Hy4 previewTencent72 t/s
- Hy3Tencent66 t/s
- Hy-MT2-30B-A3BTencent54 t/s
View as table
| Model | Tokens/s |
|---|---|
| Hy-MT2-1.8B (Tencent) | 116 |
| Hy-MT2-7B (Tencent) | 95 |
| Hy4 preview (Tencent) | 72 |
| Hy3 (Tencent) | 66 |
| Hy-MT2-30B-A3B (Tencent) | 54 |
Full catalogue
All 5 models on Tencent
Filter by creator
5 of 5 models| Hy3 Tencentopen | 25.3 | $0.05 |
| Hy4 preview Tencentopen | — | $0.24 |
| Hy-MT2-1.8B Tencentopen | — | $0.007 |
| Hy-MT2-30B-A3B Tencentopen | — | $0.01 |
| Hy-MT2-7B Tencentopen | — | $0.01 |