DeepSeek V4 Pro 0423
deepseek/deepseek-v4-pro
Compare with DeepSeek V4 Pro 0813, DeepSeek V4 Flash 0731, DeepSeek V4 Flash 0423
CompareDeepSeek V4 Pro 0423
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
BaseTenbaseten/fp4fp4 | Healthy | 100% | 99.76% | 419ms | 3.17s | 59 tps | 1.0M | $1.74 / $3.48 |
DeepInfradeepinfra/fp8fp8 | Healthy | 100% | 96.50% | 865ms | 29.9s | 29 tps | 1.0M | $1.30 / $2.60 |
DeepSeekdeepseek | Healthy | 100% | 74.80% | 1.10s | 2.84s | 27 tps | 1.0M | $0.660 / $1.98 |
Novitanovita/fp8fp8 | Healthy | 99.58% | 99.15% | 1.59s | 78.5s | 58 tps | 1.0M | $1.44 / $2.88 |
Togethertogether | Healthy | 98.62% | 91.49% | 646ms | 13.8s | 51 tps | 512K | $1.74 / $3.48 |
SiliconFlowsiliconflow/fp8fp8 | Healthy | 96.48% | 96.39% | 2.19s | 47.9s | 47 tps | 1.0M | $1.50 / $3.14 |
StreamLakestreamlake/fp8fp8 | Degraded | 94.93% | 96.29% | 2.38s | 16.3s | 36 tps | 1.0M | $0.657 / $1.31 |
Baidubaidu/fp8fp8 | Degraded | 90.88% | 97.12% | 774ms | 7.27s | 62 tps | 1.0M | $0.659 / $1.32 |
Alibabaalibaba/fp8fp8 | Down | 85.86% | 97.40% | 1.32s | 10.6s | 62 tps | 1.0M | $1.42 / $2.83 |
Ionstreamionstream/fp4fp4 | Down | 85.48% | 95.06% | 3.44s | 13.4s | 15 tps | 1.0M | $1.13 / $2.26 |
Azureazure/us | Down | 85.37% | 93.30% | 1.75s | 16.8s | 48 tps | 1.0M | $1.91 / $3.83 |
GMICloudgmicloud/fp8fp8 | Down | 83.50% | 95.49% | 2.81s | 10.8s | 34 tps | 1.0M | $0.696 / $1.39 |
Parasailparasail/fp8fp8 | Down | 81.22% | 89.59% | 866ms | 12.1s | 32 tps | 1.0M | $1.74 / $3.48 |
AtlasCloudatlas-cloud/fp4fp4 | Down | 75.76% | 92.11% | 1.37s | 8.53s | 38 tps | 1.0M | $1.68 / $3.38 |
CoreWeavecoreweave/fp8fp8 | No data | — | 96.82% | 474ms | 3.80s | 63 tps | 1.0M | $1.15 / $2.55 |
DigitalOceandigitalocean | Down | — | 93.72% | — | — | — | 1.0M | $0.870 / $1.74 |
Fireworksfireworks | No data | — | 0.00% | 2.02s | 12.0s | 41 tps | 1.0M | $1.74 / $3.48 |
Venicevenice | Down | — | 75.38% | 2.43s | 55.8s | 29 tps | 1.0M | $1.65 / $3.30 |
- BaseTen100%Healthy24h 99.76%
- p50
- 419ms
- p99
- 3.17s
- Throughput
- 59 tps
- Context
- 1.0M
- $/Mtok
- $1.74 / $3.48
baseten/fp4fp4 - DeepInfra100%Healthy24h 96.50%
- p50
- 865ms
- p99
- 29.9s
- Throughput
- 29 tps
- Context
- 1.0M
- $/Mtok
- $1.30 / $2.60
deepinfra/fp8fp8 - DeepSeek100%Healthy24h 74.80%
- p50
- 1.10s
- p99
- 2.84s
- Throughput
- 27 tps
- Context
- 1.0M
- $/Mtok
- $0.660 / $1.98
deepseek - Novita99.58%Healthy24h 99.15%
- p50
- 1.59s
- p99
- 78.5s
- Throughput
- 58 tps
- Context
- 1.0M
- $/Mtok
- $1.44 / $2.88
novita/fp8fp8 - Together98.62%Healthy24h 91.49%
- p50
- 646ms
- p99
- 13.8s
- Throughput
- 51 tps
- Context
- 512K
- $/Mtok
- $1.74 / $3.48
together - SiliconFlow96.48%Healthy24h 96.39%
- p50
- 2.19s
- p99
- 47.9s
- Throughput
- 47 tps
- Context
- 1.0M
- $/Mtok
- $1.50 / $3.14
siliconflow/fp8fp8 - StreamLake94.93%Degraded24h 96.29%
- p50
- 2.38s
- p99
- 16.3s
- Throughput
- 36 tps
- Context
- 1.0M
- $/Mtok
- $0.657 / $1.31
streamlake/fp8fp8 - Baidu90.88%Degraded24h 97.12%
- p50
- 774ms
- p99
- 7.27s
- Throughput
- 62 tps
- Context
- 1.0M
- $/Mtok
- $0.659 / $1.32
baidu/fp8fp8 - Alibaba85.86%Down24h 97.40%
- p50
- 1.32s
- p99
- 10.6s
- Throughput
- 62 tps
- Context
- 1.0M
- $/Mtok
- $1.42 / $2.83
alibaba/fp8fp8 - Ionstream85.48%Down24h 95.06%
- p50
- 3.44s
- p99
- 13.4s
- Throughput
- 15 tps
- Context
- 1.0M
- $/Mtok
- $1.13 / $2.26
ionstream/fp4fp4 - Azure85.37%Down24h 93.30%
- p50
- 1.75s
- p99
- 16.8s
- Throughput
- 48 tps
- Context
- 1.0M
- $/Mtok
- $1.91 / $3.83
azure/us - GMICloud83.50%Down24h 95.49%
- p50
- 2.81s
- p99
- 10.8s
- Throughput
- 34 tps
- Context
- 1.0M
- $/Mtok
- $0.696 / $1.39
gmicloud/fp8fp8 - Parasail81.22%Down24h 89.59%
- p50
- 866ms
- p99
- 12.1s
- Throughput
- 32 tps
- Context
- 1.0M
- $/Mtok
- $1.74 / $3.48
parasail/fp8fp8 - AtlasCloud75.76%Down24h 92.11%
- p50
- 1.37s
- p99
- 8.53s
- Throughput
- 38 tps
- Context
- 1.0M
- $/Mtok
- $1.68 / $3.38
atlas-cloud/fp4fp4 - CoreWeave—No data24h 96.82%
- p50
- 474ms
- p99
- 3.80s
- Throughput
- 63 tps
- Context
- 1.0M
- $/Mtok
- $1.15 / $2.55
coreweave/fp8fp8 - DigitalOcean—Down24h 93.72%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.870 / $1.74
digitalocean - Fireworks—No data24h 0.00%
- p50
- 2.02s
- p99
- 12.0s
- Throughput
- 41 tps
- Context
- 1.0M
- $/Mtok
- $1.74 / $3.48
fireworks - Venice—Down24h 75.38%
- p50
- 2.43s
- p99
- 55.8s
- Throughput
- 29 tps
- Context
- 1.0M
- $/Mtok
- $1.65 / $3.30
venice
Measured 50s ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
2 endpoints reporting no data are 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.