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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Cloudflarecloudflare | Healthy | 100% | 96.75% | 98.07% | 98.07% | 964ms | 13.6s | 66 tps | 1.3M | $0.440 / $1.32 |
DeepSeekdeepseek | Healthy | 100% | 98.81% | 83.98% | 83.98% | 697ms | 3.04s | 83 tps | 1.0M | $0.440 / $1.32 |
| Healthy | 100% | 97.03% | 97.76% | 97.76% | 995ms | 10.5s | 54 tps | 262K | $0.189 / $0.420 | |
| Healthy | 100% | 99.52% | 98.63% | 98.63% | 1.69s | 34.1s | 15 tps | 1.0M | $0.120 / $0.278 | |
Phalaphala | Healthy | 100% | 98.48% | 97.85% | 97.85% | 803ms | 10.3s | 44 tps | 1.0M | $0.200 / $0.400 |
| Healthy | 100% | 99.56% | 99.02% | 99.02% | 1.99s | 7.85s | 68 tps | 262K | $0.220 / $0.660 | |
Waferwafer/fast | Healthy | 100% | 98.38% | 98.62% | 98.62% | 4.27s | 21.1s | 41 tps | 1.0M | $0.280 / $0.560 |
| Healthy | 99.99% | 99.42% | 99.37% | 99.37% | 1.15s | 7.50s | 96 tps | 1.0M | $0.140 / $0.280 | |
| Healthy | 99.96% | 99.63% | 99.81% | 99.81% | 1.19s | 11.7s | 63 tps | 262K | $0.130 / $0.280 | |
| Healthy | 99.96% | 99.75% | 99.18% | 99.18% | 754ms | 5.85s | 36 tps | 1.0M | $0.130 / $0.280 | |
| Healthy | 99.87% | 99.52% | 99.53% | 99.53% | 1.31s | 10.4s | 109 tps | 1.0M | $0.440 / $1.32 | |
| Healthy | 99.84% | 99.64% | 99.65% | 99.65% | 811ms | 5.83s | 70 tps | 1.0M | $0.070 / $0.140 | |
| Healthy | 99.79% | 99.32% | 97.41% | 97.41% | 1.09s | 11.4s | 8.0 tps | 1.0M | $0.080 / $0.180 | |
Alibabaalibaba | Healthy | 99.74% | 99.17% | 98.75% | 98.75% | 1.95s | 14.1s | 60 tps | 1.0M | $0.402 / $1.21 |
Venicevenice | Healthy | 99.72% | 97.44% | 97.48% | 97.48% | 912ms | 12.0s | 63 tps | 1.0M | $0.175 / $0.350 |
| Healthy | 99.63% | 98.84% | 99.20% | 99.20% | 2.39s | 13.1s | 66 tps | 1.0M | $0.084 / $0.168 | |
| Healthy | 99.52% | 99.24% | 99.46% | 99.46% | 929ms | 11.9s | 98 tps | 1.0M | $0.140 / $0.280 | |
| Healthy | 99.46% | 95.63% | 95.50% | 95.50% | 913ms | 10.6s | 50 tps | 1.0M | $0.145 / $0.450 | |
| Healthy | 99.45% | 96.13% | 97.82% | 97.82% | 476ms | 3.98s | 66 tps | 1.0M | $0.130 / $0.260 | |
| Healthy | 99.32% | 98.97% | 98.57% | 98.57% | 685ms | 11.9s | 51 tps | 1.0M | $0.080 / $0.180 | |
Fireworksfireworks | Healthy | 99.12% | 98.80% | 97.43% | 97.43% | 823ms | 12.7s | 69 tps | 1.0M | $0.140 / $0.280 |
| Healthy | 99.01% | 97.80% | 98.58% | 98.58% | 4.66s | 56.5s | 14 tps | 1.0M | $0.065 / $0.180 | |
| Healthy | 98.72% | 98.89% | 97.34% | 97.34% | 1.99s | 83.6s | 33 tps | 1.0M | $0.079 / $0.157 | |
| Healthy | 98.56% | 98.59% | 98.76% | 98.76% | 1.74s | 12.2s | 51 tps | 1.0M | $0.140 / $0.280 | |
DigitalOceandigitalocean | Healthy | 97.53% | 97.33% | 95.90% | 95.90% | 802ms | 6.42s | 11 tps | 1.0M | $0.080 / $0.252 |
| Healthy | 97.52% | 98.26% | 98.21% | 98.21% | 983ms | 21.6s | 49 tps | 1.0M | $0.140 / $0.280 | |
| Degraded | 95.66% | 88.38% | 79.48% | 79.48% | 4.15s | 28.5s | 32 tps | 262K | $0.077 / $0.155 | |
Togethertogether | Degraded | 94.59% | 97.35% | 97.24% | 97.24% | 981ms | 12.4s | 46 tps | 1.0M | $0.140 / $0.280 |
| Degraded | 94.09% | 98.27% | 97.88% | 97.88% | 1.21s | 14.1s | 30 tps | 131K | $0.140 / $0.280 | |
| Degraded | 91.73% | 93.86% | 94.77% | 94.77% | 3.79s | 30.7s | 10 tps | 262K | $0.065 / $0.180 |
- Cloudflare100%Healthy24h 96.75%
- 7d
- 98.07%
- 30d
- 98.07%
- p50
- 964ms
- p99
- 13.6s
- Throughput
- 66 tps
- Context
- 1.3M
- $/Mtok
- $0.440 / $1.32
cloudflare - DeepSeek100%Healthy24h 98.81%
- 7d
- 83.98%
- 30d
- 83.98%
- p50
- 697ms
- p99
- 3.04s
- Throughput
- 83 tps
- Context
- 1.0M
- $/Mtok
- $0.440 / $1.32
deepseek - Io Net100%Healthy24h 97.03%
- 7d
- 97.76%
- 30d
- 97.76%
- p50
- 995ms
- p99
- 10.5s
- Throughput
- 54 tps
- Context
- 262K
- $/Mtok
- $0.189 / $0.420
io-net/fp8fp8 - Morph100%Healthy24h 99.52%
- 7d
- 98.63%
- 30d
- 98.63%
- p50
- 1.69s
- p99
- 34.1s
- Throughput
- 15 tps
- Context
- 1.0M
- $/Mtok
- $0.120 / $0.278
morph/bf16bf16 - Phala100%Healthy24h 98.48%
- 7d
- 97.85%
- 30d
- 97.85%
- p50
- 803ms
- p99
- 10.3s
- Throughput
- 44 tps
- Context
- 1.0M
- $/Mtok
- $0.200 / $0.400
phala - Reka100%Healthy24h 99.56%
- 7d
- 99.02%
- 30d
- 99.02%
- p50
- 1.99s
- p99
- 7.85s
- Throughput
- 68 tps
- Context
- 262K
- $/Mtok
- $0.220 / $0.660
reka/fp4fp4 - Wafer100%Healthy24h 98.38%
- 7d
- 98.62%
- 30d
- 98.62%
- p50
- 4.27s
- p99
- 21.1s
- Throughput
- 41 tps
- Context
- 1.0M
- $/Mtok
- $0.280 / $0.560
wafer/fast - Novita99.99%Healthy24h 99.42%
- 7d
- 99.37%
- 30d
- 99.37%
- p50
- 1.15s
- p99
- 7.50s
- Throughput
- 96 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
novita/fp8fp8 - CoreWeave99.96%Healthy24h 99.63%
- 7d
- 99.81%
- 30d
- 99.81%
- p50
- 1.19s
- p99
- 11.7s
- Throughput
- 63 tps
- Context
- 262K
- $/Mtok
- $0.130 / $0.280
coreweave/fp8fp8 - Inceptron99.96%Healthy24h 99.75%
- 7d
- 99.18%
- 30d
- 99.18%
- p50
- 754ms
- p99
- 5.85s
- Throughput
- 36 tps
- Context
- 1.0M
- $/Mtok
- $0.130 / $0.280
inceptron/fp4fp4 - AtlasCloud99.87%Healthy24h 99.52%
- 7d
- 99.53%
- 30d
- 99.53%
- p50
- 1.31s
- p99
- 10.4s
- Throughput
- 109 tps
- Context
- 1.0M
- $/Mtok
- $0.440 / $1.32
atlas-cloud/fp4fp4 - Relace99.84%Healthy24h 99.64%
- 7d
- 99.65%
- 30d
- 99.65%
- p50
- 811ms
- p99
- 5.83s
- Throughput
- 70 tps
- Context
- 1.0M
- $/Mtok
- $0.070 / $0.140
relace/fp4fp4 - Ambient99.79%Healthy24h 99.32%
- 7d
- 97.41%
- 30d
- 97.41%
- p50
- 1.09s
- p99
- 11.4s
- Throughput
- 8.0 tps
- Context
- 1.0M
- $/Mtok
- $0.080 / $0.180
ambient/fp4fp4 - Alibaba99.74%Healthy24h 99.17%
- 7d
- 98.75%
- 30d
- 98.75%
- p50
- 1.95s
- p99
- 14.1s
- Throughput
- 60 tps
- Context
- 1.0M
- $/Mtok
- $0.402 / $1.21
alibaba - Venice99.72%Healthy24h 97.44%
- 7d
- 97.48%
- 30d
- 97.48%
- p50
- 912ms
- p99
- 12.0s
- Throughput
- 63 tps
- Context
- 1.0M
- $/Mtok
- $0.175 / $0.350
venice - GMICloud99.63%Healthy24h 98.84%
- 7d
- 99.20%
- 30d
- 99.20%
- p50
- 2.39s
- p99
- 13.1s
- Throughput
- 66 tps
- Context
- 1.0M
- $/Mtok
- $0.084 / $0.168
gmicloud/fp8fp8 - Baidu99.52%Healthy24h 99.24%
- 7d
- 99.46%
- 30d
- 99.46%
- p50
- 929ms
- p99
- 11.9s
- Throughput
- 98 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
baidu/fp8fp8 - Mancer 299.46%Healthy24h 95.63%
- 7d
- 95.50%
- 30d
- 95.50%
- p50
- 913ms
- p99
- 10.6s
- Throughput
- 50 tps
- Context
- 1.0M
- $/Mtok
- $0.145 / $0.450
mancer/fp8fp8 - BaseTen99.45%Healthy24h 96.13%
- 7d
- 97.82%
- 30d
- 97.82%
- p50
- 476ms
- p99
- 3.98s
- Throughput
- 66 tps
- Context
- 1.0M
- $/Mtok
- $0.130 / $0.260
baseten/fp8fp8 - DeepInfra99.32%Healthy24h 98.97%
- 7d
- 98.57%
- 30d
- 98.57%
- p50
- 685ms
- p99
- 11.9s
- Throughput
- 51 tps
- Context
- 1.0M
- $/Mtok
- $0.080 / $0.180
deepinfra/fp8fp8 - Fireworks99.12%Healthy24h 98.80%
- 7d
- 97.43%
- 30d
- 97.43%
- p50
- 823ms
- p99
- 12.7s
- Throughput
- 69 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
fireworks - Sail Research99.01%Healthy24h 97.80%
- 7d
- 98.58%
- 30d
- 98.58%
- p50
- 4.66s
- p99
- 56.5s
- Throughput
- 14 tps
- Context
- 1.0M
- $/Mtok
- $0.065 / $0.180
sail-research/fp4fp4 - StreamLake98.72%Healthy24h 98.89%
- 7d
- 97.34%
- 30d
- 97.34%
- p50
- 1.99s
- p99
- 83.6s
- Throughput
- 33 tps
- Context
- 1.0M
- $/Mtok
- $0.079 / $0.157
streamlake/fp8fp8 - SiliconFlow98.56%Healthy24h 98.59%
- 7d
- 98.76%
- 30d
- 98.76%
- p50
- 1.74s
- p99
- 12.2s
- Throughput
- 51 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
siliconflow/fp8fp8 - DigitalOcean97.53%Healthy24h 97.33%
- 7d
- 95.90%
- 30d
- 95.90%
- p50
- 802ms
- p99
- 6.42s
- Throughput
- 11 tps
- Context
- 1.0M
- $/Mtok
- $0.080 / $0.252
digitalocean - Parasail97.52%Healthy24h 98.26%
- 7d
- 98.21%
- 30d
- 98.21%
- p50
- 983ms
- p99
- 21.6s
- Throughput
- 49 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
parasail/fp8fp8 - Decart95.66%Degraded24h 88.38%
- 7d
- 79.48%
- 30d
- 79.48%
- p50
- 4.15s
- p99
- 28.5s
- Throughput
- 32 tps
- Context
- 262K
- $/Mtok
- $0.077 / $0.155
decart/fp4fp4 - Together94.59%Degraded24h 97.35%
- 7d
- 97.24%
- 30d
- 97.24%
- p50
- 981ms
- p99
- 12.4s
- Throughput
- 46 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
together - AkashML94.09%Degraded24h 98.27%
- 7d
- 97.88%
- 30d
- 97.88%
- p50
- 1.21s
- p99
- 14.1s
- Throughput
- 30 tps
- Context
- 131K
- $/Mtok
- $0.140 / $0.280
akashml/fp8fp8 - OpenInference91.73%Degraded24h 93.86%
- 7d
- 94.77%
- 30d
- 94.77%
- p50
- 3.79s
- p99
- 30.7s
- 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 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
- DeepSeek V4 Flash 0731Cloudflarecloudflare$0.080 / $0.180 → $0.440 / $1.322026-08-20 05:50 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.