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 | ||||||||
|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 97.19% | 999ms | 22.4s | 106 tps | 1.0M | $1.32 / $3.96 | |
Cloudflarecloudflare | Healthy | 100% | 98.17% | 2.88s | 48.3s | 35 tps | 1.0M | $1.32 / $3.96 |
DeepSeekdeepseek | Healthy | 100% | 99.97% | 1.42s | 8.15s | 36 tps | 1.0M | $0.660 / $1.98 |
DigitalOceandigitalocean | Healthy | 100% | 97.22% | 979ms | 8.18s | 38 tps | 1.0M | $1.32 / $3.96 |
Fireworksfireworks | Healthy | 100% | 98.44% | 3.13s | 17.7s | 34 tps | 1.0M | $1.32 / $3.96 |
| Healthy | 100% | 99.83% | 1.62s | 16.9s | 40 tps | 1.0M | $1.32 / $3.96 | |
StreamLakestreamlake | Healthy | 100% | 99.19% | 1.80s | 14.6s | 31 tps | 1.0M | $1.32 / $3.96 |
Alibabaalibaba | Healthy | 99.93% | 99.85% | 1.24s | 11.5s | 59 tps | 1.0M | $0.603 / $1.81 |
| Healthy | 99.72% | 99.74% | 4.56s | 46.4s | 35 tps | 1.0M | $1.19 / $3.56 | |
Togethertogether | Healthy | 98.42% | 97.60% | 1.51s | 43.2s | 45 tps | 1.0M | $1.32 / $3.96 |
| Healthy | 97.87% | 99.59% | 1.77s | 7.50s | 33 tps | 1.0M | $1.32 / $3.96 | |
| Healthy | 97.20% | 95.73% | 918ms | 22.3s | 54 tps | 1.0M | $1.32 / $3.96 |
- BaseTen100%Healthy24h 97.19%
- p50
- 999ms
- p99
- 22.4s
- Throughput
- 106 tps
- Context
- 1.0M
- $/Mtok
- $1.32 / $3.96
baseten/fp4fp4 - Cloudflare100%Healthy24h 98.17%
- p50
- 2.88s
- p99
- 48.3s
- Throughput
- 35 tps
- Context
- 1.0M
- $/Mtok
- $1.32 / $3.96
cloudflare - DeepSeek100%Healthy24h 99.97%
- p50
- 1.42s
- p99
- 8.15s
- Throughput
- 36 tps
- Context
- 1.0M
- $/Mtok
- $0.660 / $1.98
deepseek - DigitalOcean100%Healthy24h 97.22%
- p50
- 979ms
- p99
- 8.18s
- Throughput
- 38 tps
- Context
- 1.0M
- $/Mtok
- $1.32 / $3.96
digitalocean - Fireworks100%Healthy24h 98.44%
- p50
- 3.13s
- p99
- 17.7s
- Throughput
- 34 tps
- Context
- 1.0M
- $/Mtok
- $1.32 / $3.96
fireworks - Novita100%Healthy24h 99.83%
- p50
- 1.62s
- p99
- 16.9s
- Throughput
- 40 tps
- Context
- 1.0M
- $/Mtok
- $1.32 / $3.96
novita/fp8fp8 - StreamLake100%Healthy24h 99.19%
- p50
- 1.80s
- p99
- 14.6s
- Throughput
- 31 tps
- Context
- 1.0M
- $/Mtok
- $1.32 / $3.96
streamlake - Alibaba99.93%Healthy24h 99.85%
- p50
- 1.24s
- p99
- 11.5s
- Throughput
- 59 tps
- Context
- 1.0M
- $/Mtok
- $0.603 / $1.81
alibaba - GMICloud99.72%Healthy24h 99.74%
- p50
- 4.56s
- p99
- 46.4s
- Throughput
- 35 tps
- Context
- 1.0M
- $/Mtok
- $1.19 / $3.56
gmicloud/fp8fp8 - Together98.42%Healthy24h 97.60%
- p50
- 1.51s
- p99
- 43.2s
- Throughput
- 45 tps
- Context
- 1.0M
- $/Mtok
- $1.32 / $3.96
together - SiliconFlow97.87%Healthy24h 99.59%
- p50
- 1.77s
- p99
- 7.50s
- Throughput
- 33 tps
- Context
- 1.0M
- $/Mtok
- $1.32 / $3.96
siliconflow/fp8fp8 - Parasail97.20%Healthy24h 95.73%
- p50
- 918ms
- p99
- 22.3s
- Throughput
- 54 tps
- Context
- 1.0M
- $/Mtok
- $1.32 / $3.96
parasail/fp8fp8
Measured 1m 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.
Throughput
Median tokens per second.