Hy3
tencent/hy3InputOutput
Compare its 8 providersIncident RSSCompare with Hy3 preview, Hy-MT2-1.8B, Hy-MT2-30B-A3B
CompareHy3
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 99.82% | 99.83% | 99.55% | 868ms | 27.8s | 69 tps | 262K | $0.130 / $0.530 | |
Novitanovita | Healthy | 100% | 92.66% | 98.95% | 99.67% | 3.02s | 25.8s | 70 tps | 262K | $0.140 / $0.580 |
| Healthy | 100% | 98.30% | 99.51% | 99.85% | 3.40s | 72.9s | 63 tps | 262K | $0.083 / $0.330 | |
| Healthy | 97.06% | 94.94% | 99.17% | 99.17% | 2.19s | 6.60s | 47 tps | 262K | $0.140 / $0.580 | |
| No data | — | 94.54% | 99.76% | 99.74% | 1.98s | 37.1s | 56 tps | 262K | $0.200 / $0.800 | |
| No data | — | — | — | — | — | — | — | 262K | $0.132 / $0.527 | |
| No data | — | — | — | 96.72% | — | — | — | 262K | $0.105 / $0.435 | |
Phalaphala | No data | — | 94.93% | 99.47% | 99.65% | 1.98s | 14.5s | 65 tps | 262K | $0.150 / $0.640 |
- DeepInfra100%Healthy24h 99.82%
- 7d
- 99.83%
- 30d
- 99.55%
- p50
- 868ms
- p99
- 27.8s
- Throughput
- 69 tps
- Context
- 262K
- $/Mtok
- $0.130 / $0.530
deepinfra/fp4fp4 - Novita100%Healthy24h 92.66%
- 7d
- 98.95%
- 30d
- 99.67%
- p50
- 3.02s
- p99
- 25.8s
- Throughput
- 70 tps
- Context
- 262K
- $/Mtok
- $0.140 / $0.580
novita - Tencent100%Healthy24h 98.30%
- 7d
- 99.51%
- 30d
- 99.85%
- p50
- 3.40s
- p99
- 72.9s
- Throughput
- 63 tps
- Context
- 262K
- $/Mtok
- $0.083 / $0.330
tencent/fp8fp8 - GMICloud97.06%Healthy24h 94.94%
- 7d
- 99.17%
- 30d
- 99.17%
- p50
- 2.19s
- p99
- 6.60s
- Throughput
- 47 tps
- Context
- 262K
- $/Mtok
- $0.140 / $0.580
gmicloud/bf16bf16 - No data24h 94.54%
- 7d
- 99.76%
- 30d
- 99.74%
- p50
- 1.98s
- p99
- 37.1s
- Throughput
- 56 tps
- Context
- 262K
- $/Mtok
- $0.200 / $0.800
atlas-cloud/fp8fp8 - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.132 / $0.527
baidu/fp8fp8 - No data24h —
- 7d
- —
- 30d
- 96.72%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.105 / $0.435
deepinfra/fp8fp8 - No data24h 94.93%
- 7d
- 99.47%
- 30d
- 99.65%
- p50
- 1.98s
- p99
- 14.5s
- Throughput
- 65 tps
- Context
- 262K
- $/Mtok
- $0.150 / $0.640
phala
Measured 5m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
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, averaged over the hour.
Throughput
Median tokens per second.
Daily availability
One row per endpoint · one dot per day · last 90 days.
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 8 endpoints · 47 days with data, 38 endpoint-days below 90%.
Price changes
- Hy3Tencenttencent/fp8$0.132 → $0.083 / $0.528 → $0.330cache read $0.033 → $0.0212026-10-04 16:06 UTC
- Hy3Tencenttencent/fp8$0.083 → $0.132 / $0.330 → $0.528cache read $0.021 → $0.0332026-10-04 00:11 UTC
- Hy3Tencenttencent/fp8$0.132 → $0.083 / $0.528 → $0.330cache read $0.033 → $0.0212026-10-03 16:11 UTC
- Hy3Tencenttencent/fp8$0.083 → $0.132 / $0.330 → $0.528cache read $0.021 → $0.0332026-10-03 00:06 UTC
- Hy3Tencenttencent/fp8$0.132 → $0.083 / $0.528 → $0.330cache read $0.033 → $0.0212026-10-02 16:10 UTC
- Hy3Tencenttencent/fp8$0.083 → $0.132 / $0.330 → $0.528cache read $0.021 → $0.0332026-10-02 00:05 UTC
- Hy3Tencenttencent/fp8$0.132 → $0.083 / $0.528 → $0.330cache read $0.033 → $0.0212026-10-01 16:10 UTC
- Hy3Tencenttencent/fp8$0.083 → $0.132 / $0.330 → $0.528cache read $0.021 → $0.0332026-10-01 00:06 UTC
- Hy3Tencenttencent/fp8$0.132 → $0.083 / $0.528 → $0.330cache read $0.033 → $0.0212026-09-30 16:16 UTC
- Hy3Tencenttencent/fp8$0.083 → $0.132 / $0.330 → $0.528cache read $0.021 → $0.0332026-09-30 16:11 UTC
- Hy3Tencenttencent/fp8$0.132 → $0.083 / $0.528 → $0.330cache read $0.033 → $0.0212026-09-30 16:01 UTC
- Hy3Tencenttencent/fp8$0.083 → $0.132 / $0.330 → $0.528cache read $0.021 → $0.0332026-09-30 00:06 UTC
- Hy3Tencenttencent/fp8$0.132 → $0.083 / $0.528 → $0.330cache read $0.033 → $0.0212026-09-29 16:11 UTC
- Hy3Tencenttencent/fp8$0.083 → $0.132 / $0.330 → $0.528cache read $0.021 → $0.0332026-09-29 00:16 UTC
- Hy3Tencenttencent/fp8$0.132 → $0.083 / $0.528 → $0.330cache read $0.033 → $0.0212026-09-29 00:11 UTC
- Hy3Tencenttencent/fp8$0.083 → $0.132 / $0.330 → $0.528cache read $0.021 → $0.0332026-09-29 00:06 UTC
- Hy3Tencenttencent/fp8$0.132 → $0.083 / $0.528 → $0.330cache read $0.033 → $0.0212026-09-28 16:11 UTC
- Hy3Tencenttencent/fp8$0.083 → $0.132 / $0.330 → $0.528cache read $0.021 → $0.0332026-09-28 00:16 UTC
- Hy3Tencenttencent/fp8$0.132 → $0.083 / $0.528 → $0.330cache read $0.033 → $0.0212026-09-28 00:11 UTC
- Hy3Tencenttencent/fp8$0.083 → $0.132 / $0.330 → $0.528cache read $0.021 → $0.0332026-09-28 00:06 UTC
- Hy3Tencenttencent/fp8$0.132 → $0.083 / $0.528 → $0.330cache read $0.033 → $0.0212026-09-27 16:06 UTC
- Hy3Tencenttencent/fp8$0.083 → $0.132 / $0.330 → $0.528cache read $0.021 → $0.0332026-09-27 00:06 UTC
- Hy3Tencenttencent/fp8$0.132 → $0.083 / $0.528 → $0.330cache read $0.033 → $0.0212026-09-26 16:11 UTC
- Hy3Tencenttencent/fp8$0.083 → $0.132 / $0.330 → $0.528cache read $0.021 → $0.0332026-09-26 00:15 UTC
- Hy3Tencenttencent/fp8$0.132 → $0.083 / $0.528 → $0.330cache read $0.033 → $0.0212026-09-26 00:10 UTC
- Hy3Tencenttencent/fp8$0.083 → $0.132 / $0.330 → $0.528cache read $0.021 → $0.0332026-09-26 00:05 UTC
- Hy3Tencenttencent/fp8$0.132 → $0.083 / $0.528 → $0.330cache read $0.033 → $0.0212026-09-25 16:10 UTC
- Hy3Tencenttencent/fp8$0.083 → $0.132 / $0.330 → $0.528cache read $0.021 → $0.0332026-09-25 00:11 UTC
- Hy3Tencenttencent/fp8$0.132 → $0.083 / $0.528 → $0.330cache read $0.033 → $0.0212026-09-24 16:11 UTC
- Hy3Tencenttencent/fp8$0.083 → $0.132 / $0.330 → $0.528cache read $0.021 → $0.0332026-09-24 00:06 UTC