Hy3
tencent/hy3
Compare with Hy3 preview, Hy-MT2-1.8B, Hy-MT2-30B-A3B
CompareHy3
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 99.75% | 99.31% | 99.31% | 1.50s | 3.40s | 120 tps | 262K | $0.200 / $0.800 | |
| Healthy | 100% | 99.48% | 99.15% | 99.15% | 807ms | 5.69s | 63 tps | 262K | $0.132 / $0.528 | |
| Healthy | 100% | 98.04% | 96.94% | 96.94% | 2.20s | 22.1s | 60 tps | 262K | $0.126 / $0.522 | |
| Healthy | 99.90% | 99.85% | 99.66% | 99.66% | 2.57s | 15.9s | 63 tps | 262K | $0.132 / $0.528 | |
Novitanovita | Healthy | 98.94% | 98.84% | 98.92% | 98.92% | 2.24s | 34.7s | 45 tps | 262K | $0.140 / $0.580 |
| Healthy | 98.15% | 95.58% | 97.44% | 97.44% | 374ms | 2.94s | 72 tps | 262K | $0.140 / $0.580 |
- AtlasCloud100%Healthy24h 99.75%
- 7d
- 99.31%
- 30d
- 99.31%
- p50
- 1.50s
- p99
- 3.40s
- Throughput
- 120 tps
- Context
- 262K
- $/Mtok
- $0.200 / $0.800
atlas-cloud/fp8fp8 - Baidu100%Healthy24h 99.48%
- 7d
- 99.15%
- 30d
- 99.15%
- p50
- 807ms
- p99
- 5.69s
- Throughput
- 63 tps
- Context
- 262K
- $/Mtok
- $0.132 / $0.528
baidu/fp8fp8 - GMICloud100%Healthy24h 98.04%
- 7d
- 96.94%
- 30d
- 96.94%
- p50
- 2.20s
- p99
- 22.1s
- Throughput
- 60 tps
- Context
- 262K
- $/Mtok
- $0.126 / $0.522
gmicloud/bf16bf16 - Tencent99.90%Healthy24h 99.85%
- 7d
- 99.66%
- 30d
- 99.66%
- p50
- 2.57s
- p99
- 15.9s
- Throughput
- 63 tps
- Context
- 262K
- $/Mtok
- $0.132 / $0.528
tencent/fp8fp8 - Novita98.94%Healthy24h 98.84%
- 7d
- 98.92%
- 30d
- 98.92%
- p50
- 2.24s
- p99
- 34.7s
- Throughput
- 45 tps
- Context
- 262K
- $/Mtok
- $0.140 / $0.580
novita - DeepInfra98.15%Healthy24h 95.58%
- 7d
- 97.44%
- 30d
- 97.44%
- p50
- 374ms
- p99
- 2.94s
- Throughput
- 72 tps
- Context
- 262K
- $/Mtok
- $0.140 / $0.580
deepinfra/fp8fp8
Measured 1m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
Price changes
- Hy3Baidubaidu/fp8$0.125 / $0.502 → $0.132 / $0.5282026-08-20 23:36 UTC
- Hy3Baidubaidu/fp8$0.131 / $0.523 → $0.125 / $0.5022026-08-20 22:41 UTC
- Hy3Baidubaidu/fp8$0.132 / $0.528 → $0.131 / $0.5232026-08-20 21:41 UTC
- Hy3Baidubaidu/fp8$0.125 / $0.502 → $0.132 / $0.5282026-08-19 23:40 UTC
- Hy3Baidubaidu/fp8$0.131 / $0.523 → $0.125 / $0.5022026-08-19 21:40 UTC
- Hy3Baidubaidu/fp8$0.125 / $0.502 → $0.131 / $0.5232026-08-19 20:45 UTC
- Hy3Baidubaidu/fp8$0.131 / $0.523 → $0.125 / $0.5022026-08-19 19:40 UTC
- Hy3Baidubaidu/fp8$0.132 / $0.528 → $0.131 / $0.5232026-08-19 13:50 UTC
History
Availability
Axis starts at 90% so small differences stay visible; it expands to 0 when an endpoint falls below.
Time to first token
Logarithmic axis — the fleet spans two orders of magnitude. P50 is OpenRouter's rolling 30-minute window.
Throughput
Median tokens per second.