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% | 418ms | 3.06s | 60 tps | 1.0M | $1.74 / $3.48 |
DeepInfradeepinfra/fp8fp8 | Healthy | 100% | 96.53% | 866ms | 28.7s | 29 tps | 1.0M | $1.30 / $2.60 |
DeepSeekdeepseek | Healthy | 99.96% | 74.76% | 1.09s | 2.87s | 27 tps | 1.0M | $0.660 / $1.98 |
Novitanovita/fp8fp8 | Healthy | 99.73% | 99.15% | 1.59s | 93.1s | 57 tps | 1.0M | $1.44 / $2.88 |
Togethertogether | Healthy | 97.71% | 91.50% | 721ms | 14.0s | 51 tps | 512K | $1.74 / $3.48 |
AtlasCloudatlas-cloud/fp4fp4 | Down | 97.14% | 92.08% | 1.38s | 9.72s | 37 tps | 1.0M | $1.68 / $3.38 |
SiliconFlowsiliconflow/fp8fp8 | Healthy | 96.90% | 96.33% | 2.20s | 67.4s | 47 tps | 1.0M | $1.50 / $3.14 |
StreamLakestreamlake/fp8fp8 | Degraded | 94.60% | 96.26% | 2.38s | 15.8s | 36 tps | 1.0M | $0.657 / $1.31 |
Baidubaidu/fp8fp8 | Degraded | 91.14% | 97.00% | 769ms | 7.58s | 60 tps | 1.0M | $0.659 / $1.32 |
Alibabaalibaba/fp8fp8 | Down | 85.52% | 97.35% | 1.32s | 11.3s | 61 tps | 1.0M | $1.42 / $2.83 |
GMICloudgmicloud/fp8fp8 | Down | 84.38% | 95.43% | 2.78s | 15.8s | 32 tps | 1.0M | $0.696 / $1.39 |
Ionstreamionstream/fp4fp4 | Down | 80.67% | 94.95% | 3.43s | 13.5s | 15 tps | 1.0M | $1.13 / $2.26 |
Azureazure/us | Down | 72.25% | 93.17% | 1.83s | 15.4s | 46 tps | 1.0M | $1.91 / $3.83 |
Parasailparasail/fp8fp8 | Down | 72.07% | 89.45% | 866ms | 12.0s | 31 tps | 1.0M | $1.74 / $3.48 |
CoreWeavecoreweave/fp8fp8 | No data | — | 96.80% | 474ms | 3.80s | 63 tps | 1.0M | $1.15 / $2.55 |
DigitalOceandigitalocean | Down | — | 93.69% | — | — | — | 1.0M | $0.870 / $1.74 |
Fireworksfireworks | No data | — | 0.00% | 2.03s | 9.99s | 41 tps | 1.0M | $1.74 / $3.48 |
Venicevenice | Down | — | 75.35% | 2.34s | 65.1s | 31 tps | 1.0M | $1.65 / $3.30 |
- BaseTen100%Healthy24h 99.76%
- p50
- 418ms
- p99
- 3.06s
- Throughput
- 60 tps
- Context
- 1.0M
- $/Mtok
- $1.74 / $3.48
baseten/fp4fp4 - DeepInfra100%Healthy24h 96.53%
- p50
- 866ms
- p99
- 28.7s
- Throughput
- 29 tps
- Context
- 1.0M
- $/Mtok
- $1.30 / $2.60
deepinfra/fp8fp8 - DeepSeek99.96%Healthy24h 74.76%
- p50
- 1.09s
- p99
- 2.87s
- Throughput
- 27 tps
- Context
- 1.0M
- $/Mtok
- $0.660 / $1.98
deepseek - Novita99.73%Healthy24h 99.15%
- p50
- 1.59s
- p99
- 93.1s
- Throughput
- 57 tps
- Context
- 1.0M
- $/Mtok
- $1.44 / $2.88
novita/fp8fp8 - Together97.71%Healthy24h 91.50%
- p50
- 721ms
- p99
- 14.0s
- Throughput
- 51 tps
- Context
- 512K
- $/Mtok
- $1.74 / $3.48
together - AtlasCloud97.14%Down24h 92.08%
- p50
- 1.38s
- p99
- 9.72s
- Throughput
- 37 tps
- Context
- 1.0M
- $/Mtok
- $1.68 / $3.38
atlas-cloud/fp4fp4 - SiliconFlow96.90%Healthy24h 96.33%
- p50
- 2.20s
- p99
- 67.4s
- Throughput
- 47 tps
- Context
- 1.0M
- $/Mtok
- $1.50 / $3.14
siliconflow/fp8fp8 - StreamLake94.60%Degraded24h 96.26%
- p50
- 2.38s
- p99
- 15.8s
- Throughput
- 36 tps
- Context
- 1.0M
- $/Mtok
- $0.657 / $1.31
streamlake/fp8fp8 - Baidu91.14%Degraded24h 97.00%
- p50
- 769ms
- p99
- 7.58s
- Throughput
- 60 tps
- Context
- 1.0M
- $/Mtok
- $0.659 / $1.32
baidu/fp8fp8 - Alibaba85.52%Down24h 97.35%
- p50
- 1.32s
- p99
- 11.3s
- Throughput
- 61 tps
- Context
- 1.0M
- $/Mtok
- $1.42 / $2.83
alibaba/fp8fp8 - GMICloud84.38%Down24h 95.43%
- p50
- 2.78s
- p99
- 15.8s
- Throughput
- 32 tps
- Context
- 1.0M
- $/Mtok
- $0.696 / $1.39
gmicloud/fp8fp8 - Ionstream80.67%Down24h 94.95%
- p50
- 3.43s
- p99
- 13.5s
- Throughput
- 15 tps
- Context
- 1.0M
- $/Mtok
- $1.13 / $2.26
ionstream/fp4fp4 - Azure72.25%Down24h 93.17%
- p50
- 1.83s
- p99
- 15.4s
- Throughput
- 46 tps
- Context
- 1.0M
- $/Mtok
- $1.91 / $3.83
azure/us - Parasail72.07%Down24h 89.45%
- p50
- 866ms
- p99
- 12.0s
- Throughput
- 31 tps
- Context
- 1.0M
- $/Mtok
- $1.74 / $3.48
parasail/fp8fp8 - CoreWeave—No data24h 96.80%
- p50
- 474ms
- p99
- 3.80s
- Throughput
- 63 tps
- Context
- 1.0M
- $/Mtok
- $1.15 / $2.55
coreweave/fp8fp8 - DigitalOcean—Down24h 93.69%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.870 / $1.74
digitalocean - Fireworks—No data24h 0.00%
- p50
- 2.03s
- p99
- 9.99s
- Throughput
- 41 tps
- Context
- 1.0M
- $/Mtok
- $1.74 / $3.48
fireworks - Venice—Down24h 75.35%
- p50
- 2.34s
- p99
- 65.1s
- Throughput
- 31 tps
- Context
- 1.0M
- $/Mtok
- $1.65 / $3.30
venice
Measured 32s 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.
Throughput
Median tokens per second.