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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 96.17% | 97.82% | 97.82% | 455ms | 4.04s | 67 tps | 1.0M | $0.130 / $0.260 | |
Cloudflarecloudflare | Healthy | 100% | 96.78% | 98.07% | 98.07% | 756ms | 10.9s | 68 tps | 1.3M | $0.440 / $1.32 |
| Healthy | 100% | 99.42% | 99.37% | 99.37% | 1.14s | 7.93s | 65 tps | 1.0M | $0.140 / $0.280 | |
DeepSeekdeepseek | Healthy | 99.99% | 98.76% | 83.98% | 83.98% | 902ms | 3.92s | 74 tps | 1.0M | $0.220 / $0.660 |
| Healthy | 99.96% | 99.51% | 98.63% | 98.63% | 1.70s | 30.9s | 14 tps | 1.0M | $0.120 / $0.278 | |
| Healthy | 99.96% | 98.83% | 99.20% | 99.20% | 2.38s | 13.1s | 61 tps | 1.0M | $0.084 / $0.168 | |
| Healthy | 99.92% | 99.57% | 99.02% | 99.02% | 1.02s | 4.08s | 119 tps | 262K | $0.220 / $0.660 | |
| Healthy | 99.90% | 99.64% | 99.65% | 99.65% | 814ms | 5.29s | 74 tps | 1.0M | $0.070 / $0.140 | |
| Healthy | 99.88% | 99.54% | 99.53% | 99.53% | 1.46s | 14.9s | 94 tps | 1.0M | $0.440 / $1.32 | |
| Healthy | 99.87% | 99.75% | 99.18% | 99.18% | 786ms | 7.15s | 34 tps | 1.0M | $0.130 / $0.280 | |
| Healthy | 99.83% | 99.36% | 97.41% | 97.41% | 795ms | 3.87s | 11 tps | 1.0M | $0.080 / $0.180 | |
| Healthy | 99.44% | 99.01% | 98.57% | 98.57% | 702ms | 14.7s | 46 tps | 1.0M | $0.080 / $0.180 | |
| Healthy | 99.42% | 99.63% | 99.81% | 99.81% | 958ms | 12.4s | 71 tps | 262K | $0.130 / $0.280 | |
Alibabaalibaba | Healthy | 99.33% | 99.20% | 98.75% | 98.75% | 1.73s | 12.2s | 55 tps | 1.0M | $0.402 / $1.21 |
| Healthy | 99.21% | 98.60% | 98.76% | 98.76% | 1.76s | 8.21s | 46 tps | 1.0M | $0.140 / $0.280 | |
| Healthy | 99.21% | 98.29% | 98.21% | 98.21% | 833ms | 18.1s | 51 tps | 1.0M | $0.140 / $0.280 | |
Togethertogether | Healthy | 98.92% | 97.42% | 97.24% | 97.24% | 772ms | 11.9s | 57 tps | 1.0M | $0.140 / $0.280 |
Phalaphala | Healthy | 98.85% | 98.52% | 97.85% | 97.85% | 862ms | 10.7s | 39 tps | 1.0M | $0.200 / $0.400 |
| Healthy | 98.77% | 99.24% | 99.46% | 99.46% | 811ms | 4.67s | 95 tps | 1.0M | $0.140 / $0.280 | |
| Healthy | 98.72% | 97.83% | 98.58% | 98.58% | 4.22s | 55.0s | 14 tps | 1.0M | $0.065 / $0.180 | |
| Healthy | 98.57% | 95.74% | 95.50% | 95.50% | 943ms | 9.78s | 50 tps | 1.0M | $0.145 / $0.450 | |
Waferwafer/fast | Healthy | 98.56% | 98.39% | 98.62% | 98.62% | 3.39s | 19.8s | 49 tps | 1.0M | $0.280 / $0.560 |
Venicevenice | Healthy | 98.55% | 97.47% | 97.48% | 97.48% | 840ms | 9.76s | 60 tps | 1.0M | $0.175 / $0.350 |
| Healthy | 98.49% | 97.08% | 97.76% | 97.76% | 944ms | 15.0s | 50 tps | 262K | $0.189 / $0.420 | |
| Healthy | 98.31% | 98.86% | 97.34% | 97.34% | 1.70s | 57.6s | 32 tps | 1.0M | $0.079 / $0.157 | |
| Degraded | 98.00% | 98.20% | 97.88% | 97.88% | 1.77s | 17.7s | 28 tps | 131K | $0.140 / $0.280 | |
DigitalOceandigitalocean | Healthy | 97.34% | 97.25% | 95.90% | 95.90% | 878ms | 6.47s | 11 tps | 1.0M | $0.080 / $0.252 |
Fireworksfireworks | Healthy | 96.45% | 98.79% | 97.43% | 97.43% | 816ms | 12.3s | 67 tps | 1.0M | $0.140 / $0.280 |
| Degraded | 93.59% | 93.77% | 94.77% | 94.77% | 3.04s | 28.5s | 9.0 tps | 262K | $0.065 / $0.180 | |
| Down | 43.63% | 88.26% | 79.48% | 79.48% | 818ms | 24.6s | 40 tps | 262K | $0.077 / $0.155 |
- BaseTen100%Healthy24h 96.17%
- 7d
- 97.82%
- 30d
- 97.82%
- p50
- 455ms
- p99
- 4.04s
- Throughput
- 67 tps
- Context
- 1.0M
- $/Mtok
- $0.130 / $0.260
baseten/fp8fp8 - Cloudflare100%Healthy24h 96.78%
- 7d
- 98.07%
- 30d
- 98.07%
- p50
- 756ms
- p99
- 10.9s
- Throughput
- 68 tps
- Context
- 1.3M
- $/Mtok
- $0.440 / $1.32
cloudflare - Novita100%Healthy24h 99.42%
- 7d
- 99.37%
- 30d
- 99.37%
- p50
- 1.14s
- p99
- 7.93s
- Throughput
- 65 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
novita/fp8fp8 - DeepSeek99.99%Healthy24h 98.76%
- 7d
- 83.98%
- 30d
- 83.98%
- p50
- 902ms
- p99
- 3.92s
- Throughput
- 74 tps
- Context
- 1.0M
- $/Mtok
- $0.220 / $0.660
deepseek - Morph99.96%Healthy24h 99.51%
- 7d
- 98.63%
- 30d
- 98.63%
- p50
- 1.70s
- p99
- 30.9s
- Throughput
- 14 tps
- Context
- 1.0M
- $/Mtok
- $0.120 / $0.278
morph/bf16bf16 - GMICloud99.96%Healthy24h 98.83%
- 7d
- 99.20%
- 30d
- 99.20%
- p50
- 2.38s
- p99
- 13.1s
- Throughput
- 61 tps
- Context
- 1.0M
- $/Mtok
- $0.084 / $0.168
gmicloud/fp8fp8 - Reka99.92%Healthy24h 99.57%
- 7d
- 99.02%
- 30d
- 99.02%
- p50
- 1.02s
- p99
- 4.08s
- Throughput
- 119 tps
- Context
- 262K
- $/Mtok
- $0.220 / $0.660
reka/fp4fp4 - Relace99.90%Healthy24h 99.64%
- 7d
- 99.65%
- 30d
- 99.65%
- p50
- 814ms
- p99
- 5.29s
- Throughput
- 74 tps
- Context
- 1.0M
- $/Mtok
- $0.070 / $0.140
relace/fp4fp4 - AtlasCloud99.88%Healthy24h 99.54%
- 7d
- 99.53%
- 30d
- 99.53%
- p50
- 1.46s
- p99
- 14.9s
- Throughput
- 94 tps
- Context
- 1.0M
- $/Mtok
- $0.440 / $1.32
atlas-cloud/fp4fp4 - Inceptron99.87%Healthy24h 99.75%
- 7d
- 99.18%
- 30d
- 99.18%
- p50
- 786ms
- p99
- 7.15s
- Throughput
- 34 tps
- Context
- 1.0M
- $/Mtok
- $0.130 / $0.280
inceptron/fp4fp4 - Ambient99.83%Healthy24h 99.36%
- 7d
- 97.41%
- 30d
- 97.41%
- p50
- 795ms
- p99
- 3.87s
- Throughput
- 11 tps
- Context
- 1.0M
- $/Mtok
- $0.080 / $0.180
ambient/fp4fp4 - DeepInfra99.44%Healthy24h 99.01%
- 7d
- 98.57%
- 30d
- 98.57%
- p50
- 702ms
- p99
- 14.7s
- Throughput
- 46 tps
- Context
- 1.0M
- $/Mtok
- $0.080 / $0.180
deepinfra/fp8fp8 - CoreWeave99.42%Healthy24h 99.63%
- 7d
- 99.81%
- 30d
- 99.81%
- p50
- 958ms
- p99
- 12.4s
- Throughput
- 71 tps
- Context
- 262K
- $/Mtok
- $0.130 / $0.280
coreweave/fp8fp8 - Alibaba99.33%Healthy24h 99.20%
- 7d
- 98.75%
- 30d
- 98.75%
- p50
- 1.73s
- p99
- 12.2s
- Throughput
- 55 tps
- Context
- 1.0M
- $/Mtok
- $0.402 / $1.21
alibaba - SiliconFlow99.21%Healthy24h 98.60%
- 7d
- 98.76%
- 30d
- 98.76%
- p50
- 1.76s
- p99
- 8.21s
- Throughput
- 46 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
siliconflow/fp8fp8 - Parasail99.21%Healthy24h 98.29%
- 7d
- 98.21%
- 30d
- 98.21%
- p50
- 833ms
- p99
- 18.1s
- Throughput
- 51 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
parasail/fp8fp8 - Together98.92%Healthy24h 97.42%
- 7d
- 97.24%
- 30d
- 97.24%
- p50
- 772ms
- p99
- 11.9s
- Throughput
- 57 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
together - Phala98.85%Healthy24h 98.52%
- 7d
- 97.85%
- 30d
- 97.85%
- p50
- 862ms
- p99
- 10.7s
- Throughput
- 39 tps
- Context
- 1.0M
- $/Mtok
- $0.200 / $0.400
phala - Baidu98.77%Healthy24h 99.24%
- 7d
- 99.46%
- 30d
- 99.46%
- p50
- 811ms
- p99
- 4.67s
- Throughput
- 95 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
baidu/fp8fp8 - Sail Research98.72%Healthy24h 97.83%
- 7d
- 98.58%
- 30d
- 98.58%
- p50
- 4.22s
- p99
- 55.0s
- Throughput
- 14 tps
- Context
- 1.0M
- $/Mtok
- $0.065 / $0.180
sail-research/fp4fp4 - Mancer 298.57%Healthy24h 95.74%
- 7d
- 95.50%
- 30d
- 95.50%
- p50
- 943ms
- p99
- 9.78s
- Throughput
- 50 tps
- Context
- 1.0M
- $/Mtok
- $0.145 / $0.450
mancer/fp8fp8 - Wafer98.56%Healthy24h 98.39%
- 7d
- 98.62%
- 30d
- 98.62%
- p50
- 3.39s
- p99
- 19.8s
- Throughput
- 49 tps
- Context
- 1.0M
- $/Mtok
- $0.280 / $0.560
wafer/fast - Venice98.55%Healthy24h 97.47%
- 7d
- 97.48%
- 30d
- 97.48%
- p50
- 840ms
- p99
- 9.76s
- Throughput
- 60 tps
- Context
- 1.0M
- $/Mtok
- $0.175 / $0.350
venice - Io Net98.49%Healthy24h 97.08%
- 7d
- 97.76%
- 30d
- 97.76%
- p50
- 944ms
- p99
- 15.0s
- Throughput
- 50 tps
- Context
- 262K
- $/Mtok
- $0.189 / $0.420
io-net/fp8fp8 - StreamLake98.31%Healthy24h 98.86%
- 7d
- 97.34%
- 30d
- 97.34%
- p50
- 1.70s
- p99
- 57.6s
- Throughput
- 32 tps
- Context
- 1.0M
- $/Mtok
- $0.079 / $0.157
streamlake/fp8fp8 - AkashML98.00%Degraded24h 98.20%
- 7d
- 97.88%
- 30d
- 97.88%
- p50
- 1.77s
- p99
- 17.7s
- Throughput
- 28 tps
- Context
- 131K
- $/Mtok
- $0.140 / $0.280
akashml/fp8fp8 - DigitalOcean97.34%Healthy24h 97.25%
- 7d
- 95.90%
- 30d
- 95.90%
- p50
- 878ms
- p99
- 6.47s
- Throughput
- 11 tps
- Context
- 1.0M
- $/Mtok
- $0.080 / $0.252
digitalocean - Fireworks96.45%Healthy24h 98.79%
- 7d
- 97.43%
- 30d
- 97.43%
- p50
- 816ms
- p99
- 12.3s
- Throughput
- 67 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
fireworks - OpenInference93.59%Degraded24h 93.77%
- 7d
- 94.77%
- 30d
- 94.77%
- p50
- 3.04s
- p99
- 28.5s
- Throughput
- 9.0 tps
- Context
- 262K
- $/Mtok
- $0.065 / $0.180
open-inference/fp4fp4 - Decart43.63%Down24h 88.26%
- 7d
- 79.48%
- 30d
- 79.48%
- p50
- 818ms
- p99
- 24.6s
- Throughput
- 40 tps
- Context
- 262K
- $/Mtok
- $0.077 / $0.155
decart/fp4fp4
Measured 1m 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.