DeepSeek V4 Flash 0423
deepseek/deepseek-v4-flash
Compare with DeepSeek V4 Flash 0731, DeepSeek V4 Pro 0423, DeepSeek V4 Pro 0813
CompareDeepSeek V4 Flash 0423
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 99.94% | 98.68% | 98.68% | 922ms | 4.23s | 66 tps | 1.0M | $0.140 / $0.280 | |
Cloudflarecloudflare | Healthy | 100% | 100% | 100% | 100% | 758ms | 1.70s | 61 tps | 384K | $0.440 / $1.32 |
DeepSeekdeepseek | Healthy | 100% | 99.00% | 84.07% | 84.07% | 811ms | 3.32s | 87 tps | 1.0M | $0.440 / $1.32 |
Phalaphala | Healthy | 100% | 91.92% | 95.08% | 95.08% | 3.79s | 215s | 6.0 tps | 1.0M | $0.200 / $0.400 |
| Healthy | 99.98% | 99.24% | 98.97% | 98.97% | 1.21s | 9.37s | 67 tps | 1.0M | $0.130 / $0.280 | |
| Healthy | 99.97% | 99.72% | 99.76% | 99.76% | 1.11s | 5.85s | 75 tps | 1.0M | $0.140 / $0.280 | |
| Healthy | 99.95% | 99.79% | 99.70% | 99.70% | 843ms | 5.62s | 78 tps | 1.0M | $0.134 / $0.268 | |
Venicevenice | Healthy | 99.93% | 99.87% | 99.49% | 99.49% | 1.65s | 4.54s | 36 tps | 1.0M | $0.138 / $0.275 |
| Healthy | 99.86% | 99.73% | 99.70% | 99.70% | 773ms | 6.53s | 18 tps | 1.0M | $0.090 / $0.180 | |
| Healthy | 99.86% | 99.50% | 99.30% | 99.30% | 688ms | 5.57s | 67 tps | 1.0M | $0.140 / $0.280 | |
| Healthy | 99.80% | 99.87% | 99.89% | 99.89% | 1.07s | 8.87s | 52 tps | 1.0M | $0.140 / $0.280 | |
| Healthy | 99.74% | 99.48% | 99.56% | 99.56% | 559ms | 14.5s | 32 tps | 1.0M | $0.140 / $0.280 | |
| Healthy | 99.72% | 99.65% | 99.19% | 99.19% | 3.28s | 12.0s | 36 tps | 1.0M | $0.083 / $0.165 | |
| Healthy | 99.60% | 99.66% | 99.28% | 99.28% | 704ms | 9.12s | 37 tps | 1.0M | $0.090 / $0.180 | |
DigitalOceandigitalocean | Healthy | 99.28% | 99.30% | 98.81% | 98.81% | 1.76s | 22.6s | 6.0 tps | 1.0M | $0.068 / $0.168 |
| Healthy | 98.94% | 99.69% | 99.37% | 99.37% | 2.41s | 10.4s | 49 tps | 1.0M | $0.084 / $0.168 | |
| Healthy | 97.57% | 98.69% | 98.71% | 98.71% | 953ms | 12.4s | 37 tps | 1.0M | $0.140 / $0.450 | |
Azureazure/us | Down | — | 87.32% | 85.18% | 85.18% | 2.35s | 45.3s | 25 tps | 1.0M | $0.210 / $0.560 |
- Baidu100%Healthy24h 99.94%
- 7d
- 98.68%
- 30d
- 98.68%
- p50
- 922ms
- p99
- 4.23s
- Throughput
- 66 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
baidu/fp8fp8 - Cloudflare100%Healthy24h 100%
- 7d
- 100%
- 30d
- 100%
- p50
- 758ms
- p99
- 1.70s
- Throughput
- 61 tps
- Context
- 384K
- $/Mtok
- $0.440 / $1.32
cloudflare - DeepSeek100%Healthy24h 99.00%
- 7d
- 84.07%
- 30d
- 84.07%
- p50
- 811ms
- p99
- 3.32s
- Throughput
- 87 tps
- Context
- 1.0M
- $/Mtok
- $0.440 / $1.32
deepseek - Phala100%Healthy24h 91.92%
- 7d
- 95.08%
- 30d
- 95.08%
- p50
- 3.79s
- p99
- 215s
- Throughput
- 6.0 tps
- Context
- 1.0M
- $/Mtok
- $0.200 / $0.400
phala - SiliconFlow99.98%Healthy24h 99.24%
- 7d
- 98.97%
- 30d
- 98.97%
- p50
- 1.21s
- p99
- 9.37s
- Throughput
- 67 tps
- Context
- 1.0M
- $/Mtok
- $0.130 / $0.280
siliconflow/fp8fp8 - Novita99.97%Healthy24h 99.72%
- 7d
- 99.76%
- 30d
- 99.76%
- p50
- 1.11s
- p99
- 5.85s
- Throughput
- 75 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
novita/fp8fp8 - Alibaba99.95%Healthy24h 99.79%
- 7d
- 99.70%
- 30d
- 99.70%
- p50
- 843ms
- p99
- 5.62s
- Throughput
- 78 tps
- Context
- 1.0M
- $/Mtok
- $0.134 / $0.268
alibaba/fp8fp8 - Venice99.93%Healthy24h 99.87%
- 7d
- 99.49%
- 30d
- 99.49%
- p50
- 1.65s
- p99
- 4.54s
- Throughput
- 36 tps
- Context
- 1.0M
- $/Mtok
- $0.138 / $0.275
venice - Sail Research99.86%Healthy24h 99.73%
- 7d
- 99.70%
- 30d
- 99.70%
- p50
- 773ms
- p99
- 6.53s
- Throughput
- 18 tps
- Context
- 1.0M
- $/Mtok
- $0.090 / $0.180
sail-research/fp4fp4 - Parasail99.86%Healthy24h 99.50%
- 7d
- 99.30%
- 30d
- 99.30%
- p50
- 688ms
- p99
- 5.57s
- Throughput
- 67 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
parasail/fp8fp8 - AtlasCloud99.80%Healthy24h 99.87%
- 7d
- 99.89%
- 30d
- 99.89%
- p50
- 1.07s
- p99
- 8.87s
- Throughput
- 52 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
atlas-cloud/fp4fp4 - CoreWeave99.74%Healthy24h 99.48%
- 7d
- 99.56%
- 30d
- 99.56%
- p50
- 559ms
- p99
- 14.5s
- Throughput
- 32 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
coreweave/fp8fp8 - StreamLake99.72%Healthy24h 99.65%
- 7d
- 99.19%
- 30d
- 99.19%
- p50
- 3.28s
- p99
- 12.0s
- Throughput
- 36 tps
- Context
- 1.0M
- $/Mtok
- $0.083 / $0.165
streamlake/fp8fp8 - DeepInfra99.60%Healthy24h 99.66%
- 7d
- 99.28%
- 30d
- 99.28%
- p50
- 704ms
- p99
- 9.12s
- Throughput
- 37 tps
- Context
- 1.0M
- $/Mtok
- $0.090 / $0.180
deepinfra/fp8fp8 - DigitalOcean99.28%Healthy24h 99.30%
- 7d
- 98.81%
- 30d
- 98.81%
- p50
- 1.76s
- p99
- 22.6s
- Throughput
- 6.0 tps
- Context
- 1.0M
- $/Mtok
- $0.068 / $0.168
digitalocean - GMICloud98.94%Healthy24h 99.69%
- 7d
- 99.37%
- 30d
- 99.37%
- p50
- 2.41s
- p99
- 10.4s
- Throughput
- 49 tps
- Context
- 1.0M
- $/Mtok
- $0.084 / $0.168
gmicloud/fp8fp8 - Mancer 297.57%Healthy24h 98.69%
- 7d
- 98.71%
- 30d
- 98.71%
- p50
- 953ms
- p99
- 12.4s
- Throughput
- 37 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.450
mancer/fp8fp8 - Down24h 87.32%
- 7d
- 85.18%
- 30d
- 85.18%
- p50
- 2.35s
- p99
- 45.3s
- Throughput
- 25 tps
- Context
- 1.0M
- $/Mtok
- $0.210 / $0.560
azure/us
Measured 3m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
Price changes
- DeepSeek V4 Flash 0423DeepSeekdeepseek$0.220 / $0.660 → $0.440 / $1.322026-08-21 06:10 UTC
- DeepSeek V4 Flash 0423DeepSeekdeepseek$0.440 / $1.32 → $0.220 / $0.6602026-08-21 04:10 UTC
- DeepSeek V4 Flash 0423DeepSeekdeepseek$0.220 / $0.660 → $0.440 / $1.322026-08-21 01:10 UTC
- DeepSeek V4 Flash 0423StreamLakestreamlake/fp8$0.076 / $0.151 → $0.083 / $0.1652026-08-20 23:45 UTC
- DeepSeek V4 Flash 0423Baidubaidu/fp8$0.077 / $0.154 → $0.140 / $0.2802026-08-20 23:35 UTC
- DeepSeek V4 Flash 0423StreamLakestreamlake/fp8$0.078 / $0.157 → $0.076 / $0.1512026-08-20 22:05 UTC
- DeepSeek V4 Flash 0423Mancer 2mancer/fp8$0.145 / $0.450 → $0.140 / $0.4502026-08-20 22:00 UTC
- DeepSeek V4 Flash 0423Baidubaidu/fp8$0.080 / $0.160 → $0.077 / $0.1542026-08-20 21:45 UTC
- DeepSeek V4 Flash 0423GMICloudgmicloud/fp8$0.112 / $0.224 → $0.084 / $0.1682026-08-20 18:45 UTC
- DeepSeek V4 Flash 0423StreamLakestreamlake/fp8$0.081 / $0.162 → $0.078 / $0.1572026-08-20 17:55 UTC
- DeepSeek V4 Flash 0423Baidubaidu/fp8$0.083 / $0.165 → $0.080 / $0.1602026-08-20 17:45 UTC
- DeepSeek V4 Flash 0423StreamLakestreamlake/fp8$0.084 / $0.168 → $0.081 / $0.1622026-08-20 16:15 UTC
- DeepSeek V4 Flash 0423Baidubaidu/fp8$0.085 / $0.171 → $0.083 / $0.1652026-08-20 15:50 UTC
- DeepSeek V4 Flash 0423StreamLakestreamlake/fp8$0.087 / $0.174 → $0.084 / $0.1682026-08-20 15:01 UTC
- DeepSeek V4 Flash 0423Baidubaidu/fp8$0.088 / $0.176 → $0.085 / $0.1712026-08-20 14:40 UTC
- DeepSeek V4 Flash 0423StreamLakestreamlake/fp8$0.089 / $0.177 → $0.087 / $0.1742026-08-20 13:01 UTC
- DeepSeek V4 Flash 0423Baidubaidu/fp8$0.140 / $0.280 → $0.088 / $0.1762026-08-20 12:45 UTC
- DeepSeek V4 Flash 0423DeepSeekdeepseek$0.440 / $1.32 → $0.220 / $0.6602026-08-20 10:05 UTC
- DeepSeek V4 Flash 0423DeepSeekdeepseek$0.220 / $0.660 → $0.440 / $1.322026-08-20 06:10 UTC
- DeepSeek V4 Flash 0423DeepSeekdeepseek$0.440 / $1.32 → $0.220 / $0.6602026-08-20 04:05 UTC
- DeepSeek V4 Flash 0423StreamLakestreamlake/fp8$0.083 / $0.165 → $0.089 / $0.1772026-08-20 02:35 UTC
- DeepSeek V4 Flash 0423GMICloudgmicloud/fp8$0.084 / $0.168 → $0.112 / $0.2242026-08-20 01:10 UTC
- DeepSeek V4 Flash 0423DeepSeekdeepseek$0.220 / $0.660 → $0.440 / $1.322026-08-20 01:05 UTC
- DeepSeek V4 Flash 0423StreamLakestreamlake/fp8$0.074 / $0.148 → $0.083 / $0.1652026-08-20 00:00 UTC
- DeepSeek V4 Flash 0423Baidubaidu/fp8$0.076 / $0.151 → $0.140 / $0.2802026-08-19 23:45 UTC
- DeepSeek V4 Flash 0423StreamLakestreamlake/fp8$0.077 / $0.154 → $0.074 / $0.1482026-08-19 22:05 UTC
- DeepSeek V4 Flash 0423Baidubaidu/fp8$0.078 / $0.157 → $0.076 / $0.1512026-08-19 21:50 UTC
- DeepSeek V4 Flash 0423StreamLakestreamlake/fp8$0.080 / $0.160 → $0.077 / $0.1542026-08-19 21:10 UTC
- DeepSeek V4 Flash 0423Baidubaidu/fp8$0.081 / $0.162 → $0.078 / $0.1572026-08-19 20:50 UTC
- DeepSeek V4 Flash 0423StreamLakestreamlake/fp8$0.083 / $0.165 → $0.080 / $0.1602026-08-19 19:15 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.