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
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Degraded | 100% | 92.28% | 96.48% | 96.48% | 1.39s | 6.72s | 43 tps | 1.0M | $1.68 / $3.38 | |
| Degraded | 100% | 98.55% | 97.92% | 97.92% | 1.05s | 3.09s | 47 tps | 1.0M | $1.69 / $3.38 | |
| Healthy | 100% | 99.88% | 99.88% | 99.88% | 431ms | 3.11s | 51 tps | 1.0M | $1.74 / $3.48 | |
| Degraded | 100% | 95.83% | 99.50% | 99.50% | 571ms | 3.77s | 57 tps | 1.0M | $1.15 / $2.55 | |
| Healthy | 100% | 99.45% | 98.58% | 98.58% | 1.08s | 22.4s | 30 tps | 1.0M | $1.30 / $2.60 | |
DeepSeekdeepseek | Healthy | 100% | 99.47% | 84.27% | 84.27% | 1.03s | 3.09s | 33 tps | 1.0M | $1.32 / $3.96 |
| Degraded | 99.86% | 95.95% | 98.22% | 98.22% | 1.50s | 5.29s | 52 tps | 1.0M | $1.42 / $2.83 | |
| Healthy | 99.64% | 98.57% | 98.21% | 98.21% | 2.21s | 14.5s | 38 tps | 1.0M | $0.790 / $1.58 | |
| Degraded | 99.63% | 94.14% | 96.85% | 96.85% | 3.27s | 12.2s | 29 tps | 1.0M | $0.792 / $2.38 | |
| Healthy | 99.41% | 98.57% | 99.05% | 99.05% | 1.48s | 82.0s | 54 tps | 1.0M | $1.60 / $3.20 | |
| Degraded | 98.76% | 96.41% | 97.17% | 97.17% | 2.11s | 107s | 42 tps | 1.0M | $1.50 / $3.14 | |
| Degraded | 98.15% | 91.24% | 91.97% | 91.97% | 783ms | 8.16s | 48 tps | 1.0M | $1.74 / $3.48 | |
Togethertogether | Healthy | 97.03% | 96.11% | 97.54% | 97.54% | 951ms | 13.8s | 45 tps | 512K | $1.74 / $3.48 |
| Degraded | 96.93% | 94.35% | 95.81% | 95.81% | 2.71s | 15.6s | 20 tps | 1.0M | $1.13 / $2.26 | |
Venicevenice | Healthy | 96.19% | 79.36% | 84.46% | 84.46% | 2.08s | 30.3s | 42 tps | 1.0M | $1.65 / $3.30 |
Azureazure/us | Degraded | 96.03% | 93.19% | 94.63% | 94.63% | 2.54s | 18.3s | 45 tps | 1.0M | $1.91 / $3.83 |
Fireworksfireworks | Degraded | 95.21% | 93.97% | 95.75% | 95.75% | 1.43s | 9.65s | 56 tps | 1.0M | $1.74 / $3.48 |
DigitalOceandigitalocean | Degraded | 93.03% | 91.62% | 55.59% | 55.59% | 2.69s | 17.4s | 5.0 tps | 1.0M | $0.870 / $1.74 |
- AtlasCloud100%Degraded24h 92.28%
- 7d
- 96.48%
- 30d
- 96.48%
- p50
- 1.39s
- p99
- 6.72s
- Throughput
- 43 tps
- Context
- 1.0M
- $/Mtok
- $1.68 / $3.38
atlas-cloud/fp4fp4 - Baidu100%Degraded24h 98.55%
- 7d
- 97.92%
- 30d
- 97.92%
- p50
- 1.05s
- p99
- 3.09s
- Throughput
- 47 tps
- Context
- 1.0M
- $/Mtok
- $1.69 / $3.38
baidu/fp8fp8 - BaseTen100%Healthy24h 99.88%
- 7d
- 99.88%
- 30d
- 99.88%
- p50
- 431ms
- p99
- 3.11s
- Throughput
- 51 tps
- Context
- 1.0M
- $/Mtok
- $1.74 / $3.48
baseten/fp4fp4 - CoreWeave100%Degraded24h 95.83%
- 7d
- 99.50%
- 30d
- 99.50%
- p50
- 571ms
- p99
- 3.77s
- Throughput
- 57 tps
- Context
- 1.0M
- $/Mtok
- $1.15 / $2.55
coreweave/fp8fp8 - DeepInfra100%Healthy24h 99.45%
- 7d
- 98.58%
- 30d
- 98.58%
- p50
- 1.08s
- p99
- 22.4s
- Throughput
- 30 tps
- Context
- 1.0M
- $/Mtok
- $1.30 / $2.60
deepinfra/fp8fp8 - DeepSeek100%Healthy24h 99.47%
- 7d
- 84.27%
- 30d
- 84.27%
- p50
- 1.03s
- p99
- 3.09s
- Throughput
- 33 tps
- Context
- 1.0M
- $/Mtok
- $1.32 / $3.96
deepseek - Alibaba99.86%Degraded24h 95.95%
- 7d
- 98.22%
- 30d
- 98.22%
- p50
- 1.50s
- p99
- 5.29s
- Throughput
- 52 tps
- Context
- 1.0M
- $/Mtok
- $1.42 / $2.83
alibaba/fp8fp8 - StreamLake99.64%Healthy24h 98.57%
- 7d
- 98.21%
- 30d
- 98.21%
- p50
- 2.21s
- p99
- 14.5s
- Throughput
- 38 tps
- Context
- 1.0M
- $/Mtok
- $0.790 / $1.58
streamlake/fp8fp8 - GMICloud99.63%Degraded24h 94.14%
- 7d
- 96.85%
- 30d
- 96.85%
- p50
- 3.27s
- p99
- 12.2s
- Throughput
- 29 tps
- Context
- 1.0M
- $/Mtok
- $0.792 / $2.38
gmicloud/fp8fp8 - Novita99.41%Healthy24h 98.57%
- 7d
- 99.05%
- 30d
- 99.05%
- p50
- 1.48s
- p99
- 82.0s
- Throughput
- 54 tps
- Context
- 1.0M
- $/Mtok
- $1.60 / $3.20
novita/fp8fp8 - SiliconFlow98.76%Degraded24h 96.41%
- 7d
- 97.17%
- 30d
- 97.17%
- p50
- 2.11s
- p99
- 107s
- Throughput
- 42 tps
- Context
- 1.0M
- $/Mtok
- $1.50 / $3.14
siliconflow/fp8fp8 - Parasail98.15%Degraded24h 91.24%
- 7d
- 91.97%
- 30d
- 91.97%
- p50
- 783ms
- p99
- 8.16s
- Throughput
- 48 tps
- Context
- 1.0M
- $/Mtok
- $1.74 / $3.48
parasail/fp8fp8 - Together97.03%Healthy24h 96.11%
- 7d
- 97.54%
- 30d
- 97.54%
- p50
- 951ms
- p99
- 13.8s
- Throughput
- 45 tps
- Context
- 512K
- $/Mtok
- $1.74 / $3.48
together - Ionstream96.93%Degraded24h 94.35%
- 7d
- 95.81%
- 30d
- 95.81%
- p50
- 2.71s
- p99
- 15.6s
- Throughput
- 20 tps
- Context
- 1.0M
- $/Mtok
- $1.13 / $2.26
ionstream/fp4fp4 - Venice96.19%Healthy24h 79.36%
- 7d
- 84.46%
- 30d
- 84.46%
- p50
- 2.08s
- p99
- 30.3s
- Throughput
- 42 tps
- Context
- 1.0M
- $/Mtok
- $1.65 / $3.30
venice - Azure96.03%Degraded24h 93.19%
- 7d
- 94.63%
- 30d
- 94.63%
- p50
- 2.54s
- p99
- 18.3s
- Throughput
- 45 tps
- Context
- 1.0M
- $/Mtok
- $1.91 / $3.83
azure/us - Fireworks95.21%Degraded24h 93.97%
- 7d
- 95.75%
- 30d
- 95.75%
- p50
- 1.43s
- p99
- 9.65s
- Throughput
- 56 tps
- Context
- 1.0M
- $/Mtok
- $1.74 / $3.48
fireworks - DigitalOcean93.03%Degraded24h 91.62%
- 7d
- 55.59%
- 30d
- 55.59%
- p50
- 2.69s
- p99
- 17.4s
- Throughput
- 5.0 tps
- Context
- 1.0M
- $/Mtok
- $0.870 / $1.74
digitalocean
Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
Price changes
- DeepSeek V4 Pro 0423DeepSeekdeepseek$0.660 / $1.98 → $1.32 / $3.962026-08-21 06:06 UTC
- DeepSeek V4 Pro 0423DeepSeekdeepseek$1.32 / $3.96 → $0.660 / $1.982026-08-21 04:10 UTC
- DeepSeek V4 Pro 0423DeepSeekdeepseek$0.660 / $1.98 → $1.32 / $3.962026-08-21 01:05 UTC
- DeepSeek V4 Pro 0423StreamLakestreamlake/fp8$0.607 / $1.21 → $0.790 / $1.582026-08-20 23:50 UTC
- DeepSeek V4 Pro 0423Baidubaidu/fp8$0.608 / $1.22 → $1.69 / $3.382026-08-20 23:35 UTC
- DeepSeek V4 Pro 0423StreamLakestreamlake/fp8$0.624 / $1.25 → $0.607 / $1.212026-08-20 22:55 UTC
- DeepSeek V4 Pro 0423Baidubaidu/fp8$0.625 / $1.25 → $0.608 / $1.222026-08-20 22:45 UTC
- DeepSeek V4 Pro 0423StreamLakestreamlake/fp8$0.640 / $1.28 → $0.624 / $1.252026-08-20 22:00 UTC
- DeepSeek V4 Pro 0423Baidubaidu/fp8$0.642 / $1.28 → $0.625 / $1.252026-08-20 21:40 UTC
- DeepSeek V4 Pro 0423StreamLakestreamlake/fp8$0.657 / $1.31 → $0.640 / $1.282026-08-20 20:50 UTC
- DeepSeek V4 Pro 0423Baidubaidu/fp8$0.659 / $1.32 → $0.642 / $1.282026-08-20 20:35 UTC
- DeepSeek V4 Pro 0423StreamLakestreamlake/fp8$0.790 / $1.58 → $0.657 / $1.312026-08-20 19:55 UTC
- DeepSeek V4 Pro 0423Baidubaidu/fp8$0.997 / $1.99 → $0.659 / $1.322026-08-20 19:40 UTC
- DeepSeek V4 Pro 0423StreamLakestreamlake/fp8$1.01 / $2.02 → $0.790 / $1.582026-08-20 19:00 UTC
- DeepSeek V4 Pro 0423GMICloudgmicloud/fp8$1.06 / $3.17 → $0.792 / $2.382026-08-20 18:45 UTC
- DeepSeek V4 Pro 0423StreamLakestreamlake/fp8$0.995 / $1.99 → $1.01 / $2.022026-08-20 16:20 UTC
- DeepSeek V4 Pro 0423StreamLakestreamlake/fp8$1.01 / $2.02 → $0.995 / $1.992026-08-20 16:05 UTC
- DeepSeek V4 Pro 0423Baidubaidu/fp8$1.01 / $2.03 → $0.997 / $1.992026-08-20 15:45 UTC
- DeepSeek V4 Pro 0423StreamLakestreamlake/fp8$1.03 / $2.06 → $1.01 / $2.022026-08-20 15:05 UTC
- DeepSeek V4 Pro 0423Baidubaidu/fp8$1.03 / $2.06 → $1.01 / $2.032026-08-20 14:45 UTC
- DeepSeek V4 Pro 0423StreamLakestreamlake/fp8$1.04 / $2.09 → $1.03 / $2.062026-08-20 14:01 UTC
- DeepSeek V4 Pro 0423Baidubaidu/fp8$1.69 / $3.38 → $1.03 / $2.062026-08-20 13:45 UTC
- DeepSeek V4 Pro 0423DeepSeekdeepseek$1.32 / $3.96 → $0.660 / $1.982026-08-20 10:10 UTC
- DeepSeek V4 Pro 0423Novitanovita/fp8$1.44 / $2.88 → $1.60 / $3.202026-08-20 06:40 UTC
- DeepSeek V4 Pro 0423DeepSeekdeepseek$0.660 / $1.98 → $1.32 / $3.962026-08-20 06:10 UTC
- DeepSeek V4 Pro 0423GMICloudgmicloud/fp8$1.32 / $3.96 → $1.06 / $3.172026-08-20 04:05 UTC
- DeepSeek V4 Pro 0423DeepSeekdeepseek$1.32 / $3.96 → $0.660 / $1.982026-08-20 04:05 UTC
- DeepSeek V4 Pro 0423StreamLakestreamlake/fp8$0.522 / $1.04 → $1.04 / $2.092026-08-20 03:05 UTC
- DeepSeek V4 Pro 0423GMICloudgmicloud/fp8$0.522 / $1.04 → $1.32 / $3.962026-08-20 01:30 UTC
- DeepSeek V4 Pro 0423DeepSeekdeepseek$0.660 / $1.98 → $1.32 / $3.962026-08-20 01:05 UTC
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.