R1 0528: 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) | 99.93% | 99.65% | 99.65% | 616ms◆ (best) | 3.22s | 23 tps | 164K | $0.500 / $2.15◆ (best) | |
StreamLakestreamlake | Healthy | 100%◆ (best) | 99.85% | 99.82% | 99.82% | 3.37s | 15.3s | 39 tps◆ (best) | 128K | $0.571 / $2.29 |
| Healthy | 99.60% | 99.31% | 99.47% | 99.47% | 1.38s | 10.1s | 17 tps | 164K | $0.500 / $2.18◆ (best) | |
| No data | — | 100% | 99.91%◆ (best) | 99.91%◆ (best) | 742ms | 965ms◆ (best) | 22 tps | 164K | $0.700 / $2.50 |
- DeepInfra100%◆ (best)Healthy24h 99.93%
- 7d
- 99.65%
- 30d
- 99.65%
- p50
- 616ms◆ (best)
- p99
- 3.22s
- Throughput
- 23 tps
- Context
- 164K
- $/Mtok
- $0.500 / $2.15◆ (best)
deepinfra/fp4fp4 - StreamLake100%◆ (best)Healthy24h 99.85%
- 7d
- 99.82%
- 30d
- 99.82%
- p50
- 3.37s
- p99
- 15.3s
- Throughput
- 39 tps◆ (best)
- Context
- 128K
- $/Mtok
- $0.571 / $2.29
streamlake - SiliconFlow99.60%Healthy24h 99.31%
- 7d
- 99.47%
- 30d
- 99.47%
- p50
- 1.38s
- p99
- 10.1s
- Throughput
- 17 tps
- Context
- 164K
- $/Mtok
- $0.500 / $2.18◆ (best)
siliconflow/fp8fp8 - No data24h 100%
- 7d
- 99.91%◆ (best)
- 30d
- 99.91%◆ (best)
- p50
- 742ms
- p99
- 965ms◆ (best)
- Throughput
- 22 tps
- Context
- 164K
- $/Mtok
- $0.700 / $2.50
novita/fp8fp8
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.
Throughput
Median tokens per second.