Hy3: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100%◆ (best) | 99.80% | 99.83%◆ (best) | 99.57% | 1.17s◆ (best) | 4.92s◆ (best) | 58 tps | 262K | $0.130 / $0.530 | |
Phalaphala | Healthy | 100%◆ (best) | 99.79% | 99.49% | 99.81% | 2.45s | 17.7s | 64 tps | 262K | $0.150 / $0.640 |
| Healthy | 100%◆ (best) | 99.81% | 99.46% | 99.83%◆ (best) | 3.44s | 20.8s | 63 tps | 262K | $0.083 / $0.330◆ (best) | |
| No data | — | 99.92% | 99.77% | 99.74% | 2.25s | 34.0s | 83 tps | 262K | $0.200 / $0.800 | |
| No data | — | — | — | — | — | — | — | 262K | $0.132 / $0.527 | |
| No data | — | — | — | 96.08% | — | — | — | 262K | $0.105 / $0.435 | |
| No data | — | 99.86% | 99.18% | 99.22% | 2.27s | 7.64s | 91 tps◆ (best) | 262K | $0.140 / $0.580 | |
Novitanovita | No data | — | 99.44% | 98.83% | 99.64% | 2.86s | 20.8s | 51 tps | 262K | $0.140 / $0.580 |
- DeepInfra100%◆ (best)Healthy24h 99.80%
- 7d
- 99.83%◆ (best)
- 30d
- 99.57%
- p50
- 1.17s◆ (best)
- p99
- 4.92s◆ (best)
- Throughput
- 58 tps
- Context
- 262K
- $/Mtok
- $0.130 / $0.530
deepinfra/fp4fp4 - Phala100%◆ (best)Healthy24h 99.79%
- 7d
- 99.49%
- 30d
- 99.81%
- p50
- 2.45s
- p99
- 17.7s
- Throughput
- 64 tps
- Context
- 262K
- $/Mtok
- $0.150 / $0.640
phala - Tencent100%◆ (best)Healthy24h 99.81%
- 7d
- 99.46%
- 30d
- 99.83%◆ (best)
- p50
- 3.44s
- p99
- 20.8s
- Throughput
- 63 tps
- Context
- 262K
- $/Mtok
- $0.083 / $0.330◆ (best)
tencent/fp8fp8 - No data24h 99.92%
- 7d
- 99.77%
- 30d
- 99.74%
- p50
- 2.25s
- p99
- 34.0s
- Throughput
- 83 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
- 96.08%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.105 / $0.435
deepinfra/fp8fp8 - No data24h 99.86%
- 7d
- 99.18%
- 30d
- 99.22%
- p50
- 2.27s
- p99
- 7.64s
- Throughput
- 91 tps◆ (best)
- Context
- 262K
- $/Mtok
- $0.140 / $0.580
gmicloud/bf16bf16 - No data24h 99.44%
- 7d
- 98.83%
- 30d
- 99.64%
- p50
- 2.86s
- p99
- 20.8s
- Throughput
- 51 tps
- Context
- 262K
- $/Mtok
- $0.140 / $0.580
novita
Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.
Price vs latency
One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag
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.