DeepSeek V4 Flash 0731
deepseek/deepseek-v4-flash-0731
Compare with DeepSeek V4 Flash 0423, DeepSeek V4 Pro 0423, DeepSeek V4 Pro 0813
CompareDeepSeek V4 Flash 0731
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Alibabaalibaba | Healthy | 100% | 99.17% | 98.75% | 98.75% | 1.87s | 14.0s | 58 tps | 1.0M | $0.402 / $1.21 |
| Healthy | 100% | 96.13% | 97.82% | 97.82% | 484ms | 4.30s | 65 tps | 1.0M | $0.130 / $0.260 | |
Cloudflarecloudflare | Healthy | 100% | 96.75% | 98.07% | 98.07% | 944ms | 16.3s | 67 tps | 1.3M | $0.440 / $1.32 |
DeepSeekdeepseek | Healthy | 100% | 98.79% | 83.98% | 83.98% | 673ms | 2.94s | 84 tps | 1.0M | $0.220 / $0.660 |
| Healthy | 100% | 97.03% | 97.76% | 97.76% | 973ms | 10.0s | 55 tps | 262K | $0.189 / $0.420 | |
| Healthy | 100% | 99.56% | 99.02% | 99.02% | 2.18s | 7.96s | 68 tps | 262K | $0.220 / $0.660 | |
| Healthy | 99.99% | 99.42% | 99.37% | 99.37% | 1.14s | 6.57s | 94 tps | 1.0M | $0.140 / $0.280 | |
| Healthy | 99.99% | 99.63% | 99.81% | 99.81% | 947ms | 11.5s | 85 tps | 262K | $0.130 / $0.280 | |
| Healthy | 99.96% | 99.52% | 99.53% | 99.53% | 1.34s | 10.3s | 107 tps | 1.0M | $0.440 / $1.32 | |
| Degraded | 99.96% | 88.37% | 79.48% | 79.48% | 3.05s | 27.4s | 34 tps | 262K | $0.077 / $0.155 | |
| Healthy | 99.95% | 99.33% | 97.41% | 97.41% | 983ms | 9.27s | 8.0 tps | 1.0M | $0.080 / $0.180 | |
| Healthy | 99.91% | 99.64% | 99.65% | 99.65% | 851ms | 5.79s | 66 tps | 1.0M | $0.070 / $0.140 | |
| Healthy | 99.80% | 98.84% | 99.20% | 99.20% | 2.40s | 13.7s | 65 tps | 1.0M | $0.084 / $0.168 | |
Waferwafer/fast | Healthy | 99.79% | 98.38% | 98.62% | 98.62% | 3.72s | 15.3s | 53 tps | 1.0M | $0.280 / $0.560 |
| Healthy | 99.79% | 99.24% | 99.46% | 99.46% | 924ms | 9.20s | 95 tps | 1.0M | $0.140 / $0.280 | |
| Healthy | 99.68% | 99.52% | 98.63% | 98.63% | 1.68s | 35.2s | 16 tps | 1.0M | $0.120 / $0.278 | |
| Healthy | 99.67% | 99.75% | 99.18% | 99.18% | 690ms | 6.02s | 43 tps | 1.0M | $0.130 / $0.280 | |
Fireworksfireworks | Healthy | 99.53% | 98.80% | 97.43% | 97.43% | 828ms | 13.9s | 68 tps | 1.0M | $0.140 / $0.280 |
| Healthy | 99.30% | 98.97% | 98.57% | 98.57% | 687ms | 11.9s | 50 tps | 1.0M | $0.080 / $0.180 | |
Phalaphala | Healthy | 99.29% | 98.49% | 97.85% | 97.85% | 794ms | 8.82s | 45 tps | 1.0M | $0.200 / $0.400 |
Togethertogether | Healthy | 99.15% | 97.35% | 97.24% | 97.24% | 1.02s | 12.0s | 41 tps | 1.0M | $0.140 / $0.280 |
| Healthy | 98.88% | 97.80% | 98.58% | 98.58% | 4.51s | 55.1s | 15 tps | 1.0M | $0.065 / $0.180 | |
| Healthy | 98.71% | 98.59% | 98.76% | 98.76% | 1.76s | 12.0s | 50 tps | 1.0M | $0.140 / $0.280 | |
Venicevenice | Healthy | 98.66% | 97.45% | 97.48% | 97.48% | 910ms | 12.4s | 62 tps | 1.0M | $0.175 / $0.350 |
| Healthy | 98.33% | 95.63% | 95.50% | 95.50% | 911ms | 12.3s | 50 tps | 1.0M | $0.145 / $0.450 | |
| Healthy | 98.20% | 98.89% | 97.34% | 97.34% | 1.99s | 72.3s | 33 tps | 1.0M | $0.079 / $0.157 | |
| Healthy | 98.12% | 98.26% | 98.21% | 98.21% | 1.01s | 27.8s | 47 tps | 1.0M | $0.140 / $0.280 | |
DigitalOceandigitalocean | Healthy | 96.04% | 97.32% | 95.90% | 95.90% | 804ms | 6.77s | 11 tps | 1.0M | $0.080 / $0.252 |
| Healthy | 95.73% | 98.27% | 97.88% | 97.88% | 1.26s | 15.4s | 28 tps | 131K | $0.140 / $0.280 | |
| Degraded | 90.85% | 93.85% | 94.77% | 94.77% | 3.78s | 30.9s | 10 tps | 262K | $0.065 / $0.180 |
- Alibaba100%Healthy24h 99.17%
- 7d
- 98.75%
- 30d
- 98.75%
- p50
- 1.87s
- p99
- 14.0s
- Throughput
- 58 tps
- Context
- 1.0M
- $/Mtok
- $0.402 / $1.21
alibaba - BaseTen100%Healthy24h 96.13%
- 7d
- 97.82%
- 30d
- 97.82%
- p50
- 484ms
- p99
- 4.30s
- Throughput
- 65 tps
- Context
- 1.0M
- $/Mtok
- $0.130 / $0.260
baseten/fp8fp8 - Cloudflare100%Healthy24h 96.75%
- 7d
- 98.07%
- 30d
- 98.07%
- p50
- 944ms
- p99
- 16.3s
- Throughput
- 67 tps
- Context
- 1.3M
- $/Mtok
- $0.440 / $1.32
cloudflare - DeepSeek100%Healthy24h 98.79%
- 7d
- 83.98%
- 30d
- 83.98%
- p50
- 673ms
- p99
- 2.94s
- Throughput
- 84 tps
- Context
- 1.0M
- $/Mtok
- $0.220 / $0.660
deepseek - Io Net100%Healthy24h 97.03%
- 7d
- 97.76%
- 30d
- 97.76%
- p50
- 973ms
- p99
- 10.0s
- Throughput
- 55 tps
- Context
- 262K
- $/Mtok
- $0.189 / $0.420
io-net/fp8fp8 - Reka100%Healthy24h 99.56%
- 7d
- 99.02%
- 30d
- 99.02%
- p50
- 2.18s
- p99
- 7.96s
- Throughput
- 68 tps
- Context
- 262K
- $/Mtok
- $0.220 / $0.660
reka/fp4fp4 - Novita99.99%Healthy24h 99.42%
- 7d
- 99.37%
- 30d
- 99.37%
- p50
- 1.14s
- p99
- 6.57s
- Throughput
- 94 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
novita/fp8fp8 - CoreWeave99.99%Healthy24h 99.63%
- 7d
- 99.81%
- 30d
- 99.81%
- p50
- 947ms
- p99
- 11.5s
- Throughput
- 85 tps
- Context
- 262K
- $/Mtok
- $0.130 / $0.280
coreweave/fp8fp8 - AtlasCloud99.96%Healthy24h 99.52%
- 7d
- 99.53%
- 30d
- 99.53%
- p50
- 1.34s
- p99
- 10.3s
- Throughput
- 107 tps
- Context
- 1.0M
- $/Mtok
- $0.440 / $1.32
atlas-cloud/fp4fp4 - Decart99.96%Degraded24h 88.37%
- 7d
- 79.48%
- 30d
- 79.48%
- p50
- 3.05s
- p99
- 27.4s
- Throughput
- 34 tps
- Context
- 262K
- $/Mtok
- $0.077 / $0.155
decart/fp4fp4 - Ambient99.95%Healthy24h 99.33%
- 7d
- 97.41%
- 30d
- 97.41%
- p50
- 983ms
- p99
- 9.27s
- Throughput
- 8.0 tps
- Context
- 1.0M
- $/Mtok
- $0.080 / $0.180
ambient/fp4fp4 - Relace99.91%Healthy24h 99.64%
- 7d
- 99.65%
- 30d
- 99.65%
- p50
- 851ms
- p99
- 5.79s
- Throughput
- 66 tps
- Context
- 1.0M
- $/Mtok
- $0.070 / $0.140
relace/fp4fp4 - GMICloud99.80%Healthy24h 98.84%
- 7d
- 99.20%
- 30d
- 99.20%
- p50
- 2.40s
- p99
- 13.7s
- Throughput
- 65 tps
- Context
- 1.0M
- $/Mtok
- $0.084 / $0.168
gmicloud/fp8fp8 - Wafer99.79%Healthy24h 98.38%
- 7d
- 98.62%
- 30d
- 98.62%
- p50
- 3.72s
- p99
- 15.3s
- Throughput
- 53 tps
- Context
- 1.0M
- $/Mtok
- $0.280 / $0.560
wafer/fast - Baidu99.79%Healthy24h 99.24%
- 7d
- 99.46%
- 30d
- 99.46%
- p50
- 924ms
- p99
- 9.20s
- Throughput
- 95 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
baidu/fp8fp8 - Morph99.68%Healthy24h 99.52%
- 7d
- 98.63%
- 30d
- 98.63%
- p50
- 1.68s
- p99
- 35.2s
- Throughput
- 16 tps
- Context
- 1.0M
- $/Mtok
- $0.120 / $0.278
morph/bf16bf16 - Inceptron99.67%Healthy24h 99.75%
- 7d
- 99.18%
- 30d
- 99.18%
- p50
- 690ms
- p99
- 6.02s
- Throughput
- 43 tps
- Context
- 1.0M
- $/Mtok
- $0.130 / $0.280
inceptron/fp4fp4 - Fireworks99.53%Healthy24h 98.80%
- 7d
- 97.43%
- 30d
- 97.43%
- p50
- 828ms
- p99
- 13.9s
- Throughput
- 68 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
fireworks - DeepInfra99.30%Healthy24h 98.97%
- 7d
- 98.57%
- 30d
- 98.57%
- p50
- 687ms
- p99
- 11.9s
- Throughput
- 50 tps
- Context
- 1.0M
- $/Mtok
- $0.080 / $0.180
deepinfra/fp8fp8 - Phala99.29%Healthy24h 98.49%
- 7d
- 97.85%
- 30d
- 97.85%
- p50
- 794ms
- p99
- 8.82s
- Throughput
- 45 tps
- Context
- 1.0M
- $/Mtok
- $0.200 / $0.400
phala - Together99.15%Healthy24h 97.35%
- 7d
- 97.24%
- 30d
- 97.24%
- p50
- 1.02s
- p99
- 12.0s
- Throughput
- 41 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
together - Sail Research98.88%Healthy24h 97.80%
- 7d
- 98.58%
- 30d
- 98.58%
- p50
- 4.51s
- p99
- 55.1s
- Throughput
- 15 tps
- Context
- 1.0M
- $/Mtok
- $0.065 / $0.180
sail-research/fp4fp4 - SiliconFlow98.71%Healthy24h 98.59%
- 7d
- 98.76%
- 30d
- 98.76%
- p50
- 1.76s
- p99
- 12.0s
- Throughput
- 50 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
siliconflow/fp8fp8 - Venice98.66%Healthy24h 97.45%
- 7d
- 97.48%
- 30d
- 97.48%
- p50
- 910ms
- p99
- 12.4s
- Throughput
- 62 tps
- Context
- 1.0M
- $/Mtok
- $0.175 / $0.350
venice - Mancer 298.33%Healthy24h 95.63%
- 7d
- 95.50%
- 30d
- 95.50%
- p50
- 911ms
- p99
- 12.3s
- Throughput
- 50 tps
- Context
- 1.0M
- $/Mtok
- $0.145 / $0.450
mancer/fp8fp8 - StreamLake98.20%Healthy24h 98.89%
- 7d
- 97.34%
- 30d
- 97.34%
- p50
- 1.99s
- p99
- 72.3s
- Throughput
- 33 tps
- Context
- 1.0M
- $/Mtok
- $0.079 / $0.157
streamlake/fp8fp8 - Parasail98.12%Healthy24h 98.26%
- 7d
- 98.21%
- 30d
- 98.21%
- p50
- 1.01s
- p99
- 27.8s
- Throughput
- 47 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
parasail/fp8fp8 - DigitalOcean96.04%Healthy24h 97.32%
- 7d
- 95.90%
- 30d
- 95.90%
- p50
- 804ms
- p99
- 6.77s
- Throughput
- 11 tps
- Context
- 1.0M
- $/Mtok
- $0.080 / $0.252
digitalocean - AkashML95.73%Healthy24h 98.27%
- 7d
- 97.88%
- 30d
- 97.88%
- p50
- 1.26s
- p99
- 15.4s
- Throughput
- 28 tps
- Context
- 131K
- $/Mtok
- $0.140 / $0.280
akashml/fp8fp8 - OpenInference90.85%Degraded24h 93.85%
- 7d
- 94.77%
- 30d
- 94.77%
- p50
- 3.78s
- p99
- 30.9s
- Throughput
- 10 tps
- Context
- 262K
- $/Mtok
- $0.065 / $0.180
open-inference/fp4fp4
Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
Price changes
- DeepSeek V4 Flash 0731DeepSeekdeepseek$0.440 / $1.32 → $0.220 / $0.6602026-08-21 10:10 UTC
- DeepSeek V4 Flash 0731OpenInferenceopen-inference/fp4$0.060 / $0.180 → $0.065 / $0.1802026-08-21 08:05 UTC
- DeepSeek V4 Flash 0731Morphmorph/bf16$0.120 / $0.278 → $0.120 / $0.2782026-08-21 08:05 UTC
- DeepSeek V4 Flash 0731OpenInferenceopen-inference/fp4$0.080 / $0.180 → $0.060 / $0.1802026-08-21 07:55 UTC
- DeepSeek V4 Flash 0731OpenInferenceopen-inference/fp4$0.065 / $0.140 → $0.080 / $0.1802026-08-21 06:25 UTC
- DeepSeek V4 Flash 0731DeepSeekdeepseek$0.220 / $0.660 → $0.440 / $1.322026-08-21 06:06 UTC
- DeepSeek V4 Flash 0731Fireworksfireworks$0.220 / $0.660 → $0.140 / $0.2802026-08-21 05:25 UTC
- DeepSeek V4 Flash 0731Fireworksfireworks$0.140 / $0.280 → $0.220 / $0.6602026-08-21 04:50 UTC
- DeepSeek V4 Flash 0731DeepSeekdeepseek$0.440 / $1.32 → $0.220 / $0.6602026-08-21 04:10 UTC
- DeepSeek V4 Flash 0731DeepSeekdeepseek$0.220 / $0.660 → $0.440 / $1.322026-08-21 01:10 UTC
- DeepSeek V4 Flash 0731Decartdecart/fp4$0.066 / $0.131 → $0.077 / $0.1552026-08-21 00:50 UTC
- DeepSeek V4 Flash 0731Morphmorph/bf16$0.139 / $0.278 → $0.120 / $0.2782026-08-21 00:45 UTC
- DeepSeek V4 Flash 0731AtlasCloudatlas-cloud/fp4$0.140 / $0.280 → $0.440 / $1.322026-08-21 00:10 UTC
- DeepSeek V4 Flash 0731Alibabaalibaba$0.201 / $0.603 → $0.402 / $1.212026-08-21 00:05 UTC
- DeepSeek V4 Flash 0731StreamLakestreamlake/fp8$0.067 / $0.134 → $0.079 / $0.1572026-08-20 23:50 UTC
- DeepSeek V4 Flash 0731Baidubaidu/fp8$0.069 / $0.137 → $0.140 / $0.2802026-08-20 23:40 UTC
- DeepSeek V4 Flash 0731Decartdecart/fp4$0.076 / $0.153 → $0.066 / $0.1312026-08-20 19:55 UTC
- DeepSeek V4 Flash 0731Ambientambient/fp4$0.800 / $0.180 → $0.080 / $0.1802026-08-20 19:30 UTC
- DeepSeek V4 Flash 0731StreamLakestreamlake/fp8$0.078 / $0.157 → $0.067 / $0.1342026-08-20 19:05 UTC
- DeepSeek V4 Flash 0731Ambientambient/fp4$0.140 / $0.280 → $0.800 / $0.1802026-08-20 18:50 UTC
- DeepSeek V4 Flash 0731GMICloudgmicloud/fp8$0.112 / $0.224 → $0.084 / $0.1682026-08-20 18:45 UTC
- DeepSeek V4 Flash 0731Baidubaidu/fp8$0.080 / $0.160 → $0.069 / $0.1372026-08-20 18:45 UTC
- DeepSeek V4 Flash 0731Alibabaalibaba$0.242 / $0.726 → $0.201 / $0.6032026-08-20 16:35 UTC
- DeepSeek V4 Flash 0731Alibabaalibaba$0.484 / $1.45 → $0.242 / $0.7262026-08-20 14:10 UTC
- DeepSeek V4 Flash 0731StreamLakestreamlake/fp8$0.079 / $0.157 → $0.078 / $0.1572026-08-20 13:05 UTC
- DeepSeek V4 Flash 0731Baidubaidu/fp8$0.140 / $0.280 → $0.080 / $0.1602026-08-20 12:50 UTC
- DeepSeek V4 Flash 0731DeepSeekdeepseek$0.440 / $1.32 → $0.220 / $0.6602026-08-20 10:10 UTC
- DeepSeek V4 Flash 0731Io Netio-net/fp8$0.149 / $0.320 → $0.189 / $0.4202026-08-20 09:25 UTC
- DeepSeek V4 Flash 0731Rekareka/fp4$0.220 / $0.660 → $0.220 / $0.6602026-08-20 08:05 UTC
- DeepSeek V4 Flash 0731DeepSeekdeepseek$0.220 / $0.660 → $0.440 / $1.322026-08-20 06:10 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.