R1 0528
deepseek/deepseek-r1-0528
Compare with DeepSeek V3, R1, R1 Distill Llama 70B
CompareR1 0528
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
DeepInfradeepinfra/fp4fp4 | Healthy | 100% | 98.99% | 743ms | 16.0s | 19 tps | 164K | $0.500 / $2.15 |
StreamLakestreamlake | Healthy | 100% | 99.77% | 3.40s | 12.5s | 42 tps | 128K | $0.571 / $2.29 |
SiliconFlowsiliconflow/fp8fp8 | Healthy | 97.67% | 99.54% | 1.63s | 7.49s | 20 tps | 164K | $0.500 / $2.18 |
Novitanovita/fp8fp8 | No data | — | 99.64% | 1.07s | 9.26s | 21 tps | 164K | $0.700 / $2.50 |
- DeepInfra100%Healthy24h 98.99%
- p50
- 743ms
- p99
- 16.0s
- Throughput
- 19 tps
- Context
- 164K
- $/Mtok
- $0.500 / $2.15
deepinfra/fp4fp4 - StreamLake100%Healthy24h 99.77%
- p50
- 3.40s
- p99
- 12.5s
- Throughput
- 42 tps
- Context
- 128K
- $/Mtok
- $0.571 / $2.29
streamlake - SiliconFlow97.67%Healthy24h 99.54%
- p50
- 1.63s
- p99
- 7.49s
- Throughput
- 20 tps
- Context
- 164K
- $/Mtok
- $0.500 / $2.18
siliconflow/fp8fp8 - Novita—No data24h 99.64%
- p50
- 1.07s
- p99
- 9.26s
- Throughput
- 21 tps
- Context
- 164K
- $/Mtok
- $0.700 / $2.50
novita/fp8fp8
Measured 1m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
1 endpoint reporting no data is omitted from the charts.
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 and p99 are OpenRouter's rolling 30-minute windows, averaged over the hour.
Throughput
Median tokens per second.