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) | 99.92% | 99.77% | 99.74% | 2.26s | 9.57s | 84 tps | 262K | $0.200 / $0.800 | |
| Healthy | 100%◆ (best) | 99.80% | 99.83%◆ (best) | 99.57% | 1.31s◆ (best) | 4.70s◆ (best) | 53 tps | 262K | $0.130 / $0.530 | |
Phalaphala | Healthy | 100%◆ (best) | 99.78% | 99.49% | 99.81% | 2.42s | 27.9s | 48 tps | 262K | $0.150 / $0.640 |
| Healthy | 100%◆ (best) | 99.80% | 99.46% | 99.83%◆ (best) | 3.47s | 20.7s | 61 tps | 262K | $0.083 / $0.330◆ (best) | |
| No data | — | — | — | — | — | — | — | 262K | $0.132 / $0.527 | |
| No data | — | — | — | 96.08% | — | — | — | 262K | $0.105 / $0.435 | |
| No data | — | 99.87% | 99.18% | 99.22% | 2.34s | 7.74s | 92 tps◆ (best) | 262K | $0.140 / $0.580 | |
Novitanovita | No data | — | 99.44% | 98.83% | 99.64% | 3.38s | 21.2s | 53 tps | 262K | $0.140 / $0.580 |
- AtlasCloud100%◆ (best)Healthy24h 99.92%
- 7d
- 99.77%
- 30d
- 99.74%
- p50
- 2.26s
- p99
- 9.57s
- Throughput
- 84 tps
- Context
- 262K
- $/Mtok
- $0.200 / $0.800
atlas-cloud/fp8fp8 - DeepInfra100%◆ (best)Healthy24h 99.80%
- 7d
- 99.83%◆ (best)
- 30d
- 99.57%
- p50
- 1.31s◆ (best)
- p99
- 4.70s◆ (best)
- Throughput
- 53 tps
- Context
- 262K
- $/Mtok
- $0.130 / $0.530
deepinfra/fp4fp4 - Phala100%◆ (best)Healthy24h 99.78%
- 7d
- 99.49%
- 30d
- 99.81%
- p50
- 2.42s
- p99
- 27.9s
- Throughput
- 48 tps
- Context
- 262K
- $/Mtok
- $0.150 / $0.640
phala - Tencent100%◆ (best)Healthy24h 99.80%
- 7d
- 99.46%
- 30d
- 99.83%◆ (best)
- p50
- 3.47s
- p99
- 20.7s
- Throughput
- 61 tps
- Context
- 262K
- $/Mtok
- $0.083 / $0.330◆ (best)
tencent/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 99.87%
- 7d
- 99.18%
- 30d
- 99.22%
- p50
- 2.34s
- p99
- 7.74s
- Throughput
- 92 tps◆ (best)
- Context
- 262K
- $/Mtok
- $0.140 / $0.580
gmicloud/bf16bf16 - No data24h 99.44%
- 7d
- 98.83%
- 30d
- 99.64%
- p50
- 3.38s
- p99
- 21.2s
- Throughput
- 53 tps
- Context
- 262K
- $/Mtok
- $0.140 / $0.580
novita
Measured 5m 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.