DeepSeek V4 Pro 0813
deepseek/deepseek-v4-pro-0813
Compare with DeepSeek V4 Pro 0423, DeepSeek V4 Flash 0731, DeepSeek V4 Flash 0423
CompareDeepSeek V4 Pro 0813
| State | ||||||||
|---|---|---|---|---|---|---|---|---|
Alibabaalibaba | Healthy | 100% | 99.85% | 1.24s | 10.0s | 59 tps | 1.0M | $0.603 / $1.81 |
Cloudflarecloudflare | Healthy | 100% | 98.17% | 2.91s | 47.7s | 35 tps | 1.0M | $1.32 / $3.96 |
DeepSeekdeepseek | Healthy | 100% | 99.97% | 1.42s | 8.10s | 36 tps | 1.0M | $0.660 / $1.98 |
DigitalOceandigitalocean | Healthy | 100% | 97.22% | 985ms | 8.12s | 37 tps | 1.0M | $1.32 / $3.96 |
Fireworksfireworks | Healthy | 100% | 98.44% | 3.12s | 17.7s | 35 tps | 1.0M | $1.32 / $3.96 |
| Healthy | 100% | 99.83% | 1.62s | 16.3s | 40 tps | 1.0M | $1.32 / $3.96 | |
| Healthy | 100% | 99.60% | 1.78s | 7.46s | 33 tps | 1.0M | $1.32 / $3.96 | |
StreamLakestreamlake | Healthy | 100% | 99.19% | 1.80s | 15.3s | 31 tps | 1.0M | $1.32 / $3.96 |
| Healthy | 99.49% | 99.74% | 4.53s | 47.0s | 35 tps | 1.0M | $1.19 / $3.56 | |
| Healthy | 98.25% | 97.19% | 999ms | 16.6s | 106 tps | 1.0M | $1.32 / $3.96 | |
Togethertogether | Healthy | 97.71% | 97.60% | 1.35s | 46.0s | 49 tps | 1.0M | $1.32 / $3.96 |
| Healthy | 95.89% | 95.74% | 927ms | 18.3s | 53 tps | 1.0M | $1.32 / $3.96 |
- Alibaba100%Healthy24h 99.85%
- p50
- 1.24s
- p99
- 10.0s
- Throughput
- 59 tps
- Context
- 1.0M
- $/Mtok
- $0.603 / $1.81
alibaba - Cloudflare100%Healthy24h 98.17%
- p50
- 2.91s
- p99
- 47.7s
- Throughput
- 35 tps
- Context
- 1.0M
- $/Mtok
- $1.32 / $3.96
cloudflare - DeepSeek100%Healthy24h 99.97%
- p50
- 1.42s
- p99
- 8.10s
- Throughput
- 36 tps
- Context
- 1.0M
- $/Mtok
- $0.660 / $1.98
deepseek - DigitalOcean100%Healthy24h 97.22%
- p50
- 985ms
- p99
- 8.12s
- Throughput
- 37 tps
- Context
- 1.0M
- $/Mtok
- $1.32 / $3.96
digitalocean - Fireworks100%Healthy24h 98.44%
- p50
- 3.12s
- p99
- 17.7s
- Throughput
- 35 tps
- Context
- 1.0M
- $/Mtok
- $1.32 / $3.96
fireworks - Novita100%Healthy24h 99.83%
- p50
- 1.62s
- p99
- 16.3s
- Throughput
- 40 tps
- Context
- 1.0M
- $/Mtok
- $1.32 / $3.96
novita/fp8fp8 - SiliconFlow100%Healthy24h 99.60%
- p50
- 1.78s
- p99
- 7.46s
- Throughput
- 33 tps
- Context
- 1.0M
- $/Mtok
- $1.32 / $3.96
siliconflow/fp8fp8 - StreamLake100%Healthy24h 99.19%
- p50
- 1.80s
- p99
- 15.3s
- Throughput
- 31 tps
- Context
- 1.0M
- $/Mtok
- $1.32 / $3.96
streamlake - GMICloud99.49%Healthy24h 99.74%
- p50
- 4.53s
- p99
- 47.0s
- Throughput
- 35 tps
- Context
- 1.0M
- $/Mtok
- $1.19 / $3.56
gmicloud/fp8fp8 - BaseTen98.25%Healthy24h 97.19%
- p50
- 999ms
- p99
- 16.6s
- Throughput
- 106 tps
- Context
- 1.0M
- $/Mtok
- $1.32 / $3.96
baseten/fp4fp4 - Together97.71%Healthy24h 97.60%
- p50
- 1.35s
- p99
- 46.0s
- Throughput
- 49 tps
- Context
- 1.0M
- $/Mtok
- $1.32 / $3.96
together - Parasail95.89%Healthy24h 95.74%
- p50
- 927ms
- p99
- 18.3s
- Throughput
- 53 tps
- Context
- 1.0M
- $/Mtok
- $1.32 / $3.96
parasail/fp8fp8
Measured 5m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
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, averaged over the hour.
Throughput
Median tokens per second.