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% | 99.24% | 99.45% | 99.45% | 880ms | 5.11s | 94 tps | 1.0M | $0.140 / $0.280 | |
| Healthy | 100% | 95.94% | 97.74% | 97.74% | 481ms | 4.02s | 66 tps | 1.0M | $0.130 / $0.260 | |
Cloudflarecloudflare | Healthy | 100% | 96.74% | 98.00% | 98.00% | 735ms | 8.52s | 61 tps | 1.3M | $0.440 / $1.32 |
| Healthy | 100% | 99.63% | 99.80% | 99.80% | 785ms | 7.57s | 126 tps | 262K | $0.130 / $0.280 | |
DeepSeekdeepseek | Healthy | 100% | 99.02% | 83.38% | 83.38% | 782ms | 3.73s | 78 tps | 1.0M | $0.440 / $1.32 |
| Healthy | 99.98% | 99.42% | 99.35% | 99.35% | 1.27s | 10.2s | 96 tps | 1.0M | $0.140 / $0.280 | |
| Healthy | 99.89% | 98.58% | 98.73% | 98.73% | 1.64s | 13.4s | 56 tps | 1.0M | $0.140 / $0.280 | |
| Healthy | 99.86% | 99.75% | 99.15% | 99.15% | 711ms | 6.15s | 45 tps | 1.0M | $0.130 / $0.280 | |
| Healthy | 99.86% | 99.60% | 99.64% | 99.64% | 880ms | 5.87s | 64 tps | 1.0M | $0.070 / $0.140 | |
| Healthy | 99.73% | 95.36% | 95.39% | 95.39% | 912ms | 9.56s | 53 tps | 1.0M | $0.145 / $0.450 | |
| Healthy | 99.68% | 99.18% | 97.33% | 97.33% | 943ms | 14.6s | 16 tps | 1.0M | $0.080 / $0.180 | |
| Healthy | 99.62% | 99.48% | 99.51% | 99.51% | 1.41s | 9.11s | 86 tps | 1.0M | $0.440 / $1.32 | |
| Healthy | 99.60% | 98.91% | 97.28% | 97.28% | 1.63s | 31.0s | 43 tps | 1.0M | $0.079 / $0.157 | |
| Healthy | 99.54% | 98.86% | 99.18% | 99.18% | 2.40s | 13.0s | 60 tps | 1.0M | $0.084 / $0.168 | |
| Healthy | 99.51% | 99.52% | 98.59% | 98.59% | 1.63s | 23.9s | 13 tps | 1.0M | $0.120 / $0.278 | |
Alibabaalibaba | Healthy | 99.46% | 99.13% | 98.68% | 98.68% | 2.51s | 14.9s | 63 tps | 1.0M | $0.402 / $1.21 |
| Healthy | 99.35% | 99.51% | 98.98% | 98.98% | 1.38s | 7.47s | 171 tps | 262K | $0.220 / $0.660 | |
| Healthy | 99.35% | 98.89% | 98.54% | 98.54% | 646ms | 14.1s | 46 tps | 1.0M | $0.080 / $0.180 | |
Fireworksfireworks | Healthy | 99.29% | 98.84% | 97.41% | 97.41% | 857ms | 16.1s | 54 tps | 1.0M | $0.140 / $0.280 |
Togethertogether | Healthy | 99.22% | 97.37% | 97.24% | 97.24% | 721ms | 8.31s | 71 tps | 1.0M | $0.140 / $0.280 |
| Healthy | 99.12% | 98.21% | 98.18% | 98.18% | 807ms | 13.2s | 56 tps | 1.0M | $0.140 / $0.280 | |
| Healthy | 98.13% | 98.20% | 97.93% | 97.93% | 1.66s | 13.5s | 33 tps | 131K | $0.140 / $0.280 | |
| Healthy | 98.11% | 97.75% | 98.58% | 98.58% | 3.35s | 50.7s | 15 tps | 1.0M | $0.065 / $0.180 | |
| Healthy | 97.90% | 96.96% | 97.73% | 97.73% | 886ms | 13.5s | 59 tps | 262K | $0.189 / $0.420 | |
Venicevenice | Healthy | 97.65% | 97.34% | 97.45% | 97.45% | 811ms | 11.9s | 78 tps | 1.0M | $0.175 / $0.350 |
DigitalOceandigitalocean | Healthy | 97.39% | 97.33% | 95.79% | 95.79% | 839ms | 5.97s | 10 tps | 1.0M | $0.080 / $0.252 |
Phalaphala | Healthy | 96.86% | 98.43% | 97.80% | 97.80% | 1.38s | 9.63s | 50 tps | 1.0M | $0.200 / $0.400 |
Waferwafer/fast | Degraded | 90.47% | 98.39% | 98.62% | 98.62% | 952ms | 13.4s | 169 tps | 1.0M | $0.280 / $0.560 |
| Down | 88.19% | 94.06% | 94.87% | 94.87% | 3.60s | 34.9s | 8.0 tps | 262K | $0.065 / $0.180 | |
| Down | 80.26% | 88.64% | 79.13% | 79.13% | 1.23s | 31.4s | 36 tps | 262K | $0.077 / $0.155 |
- Baidu100%Healthy24h 99.24%
- 7d
- 99.45%
- 30d
- 99.45%
- p50
- 880ms
- p99
- 5.11s
- Throughput
- 94 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
baidu/fp8fp8 - BaseTen100%Healthy24h 95.94%
- 7d
- 97.74%
- 30d
- 97.74%
- p50
- 481ms
- p99
- 4.02s
- Throughput
- 66 tps
- Context
- 1.0M
- $/Mtok
- $0.130 / $0.260
baseten/fp8fp8 - Cloudflare100%Healthy24h 96.74%
- 7d
- 98.00%
- 30d
- 98.00%
- p50
- 735ms
- p99
- 8.52s
- Throughput
- 61 tps
- Context
- 1.3M
- $/Mtok
- $0.440 / $1.32
cloudflare - CoreWeave100%Healthy24h 99.63%
- 7d
- 99.80%
- 30d
- 99.80%
- p50
- 785ms
- p99
- 7.57s
- Throughput
- 126 tps
- Context
- 262K
- $/Mtok
- $0.130 / $0.280
coreweave/fp8fp8 - DeepSeek100%Healthy24h 99.02%
- 7d
- 83.38%
- 30d
- 83.38%
- p50
- 782ms
- p99
- 3.73s
- Throughput
- 78 tps
- Context
- 1.0M
- $/Mtok
- $0.440 / $1.32
deepseek - Novita99.98%Healthy24h 99.42%
- 7d
- 99.35%
- 30d
- 99.35%
- p50
- 1.27s
- p99
- 10.2s
- Throughput
- 96 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
novita/fp8fp8 - SiliconFlow99.89%Healthy24h 98.58%
- 7d
- 98.73%
- 30d
- 98.73%
- p50
- 1.64s
- p99
- 13.4s
- Throughput
- 56 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
siliconflow/fp8fp8 - Inceptron99.86%Healthy24h 99.75%
- 7d
- 99.15%
- 30d
- 99.15%
- p50
- 711ms
- p99
- 6.15s
- Throughput
- 45 tps
- Context
- 1.0M
- $/Mtok
- $0.130 / $0.280
inceptron/fp4fp4 - Relace99.86%Healthy24h 99.60%
- 7d
- 99.64%
- 30d
- 99.64%
- p50
- 880ms
- p99
- 5.87s
- Throughput
- 64 tps
- Context
- 1.0M
- $/Mtok
- $0.070 / $0.140
relace/fp4fp4 - Mancer 299.73%Healthy24h 95.36%
- 7d
- 95.39%
- 30d
- 95.39%
- p50
- 912ms
- p99
- 9.56s
- Throughput
- 53 tps
- Context
- 1.0M
- $/Mtok
- $0.145 / $0.450
mancer/fp8fp8 - Ambient99.68%Healthy24h 99.18%
- 7d
- 97.33%
- 30d
- 97.33%
- p50
- 943ms
- p99
- 14.6s
- Throughput
- 16 tps
- Context
- 1.0M
- $/Mtok
- $0.080 / $0.180
ambient/fp4fp4 - AtlasCloud99.62%Healthy24h 99.48%
- 7d
- 99.51%
- 30d
- 99.51%
- p50
- 1.41s
- p99
- 9.11s
- Throughput
- 86 tps
- Context
- 1.0M
- $/Mtok
- $0.440 / $1.32
atlas-cloud/fp4fp4 - StreamLake99.60%Healthy24h 98.91%
- 7d
- 97.28%
- 30d
- 97.28%
- p50
- 1.63s
- p99
- 31.0s
- Throughput
- 43 tps
- Context
- 1.0M
- $/Mtok
- $0.079 / $0.157
streamlake/fp8fp8 - GMICloud99.54%Healthy24h 98.86%
- 7d
- 99.18%
- 30d
- 99.18%
- p50
- 2.40s
- p99
- 13.0s
- Throughput
- 60 tps
- Context
- 1.0M
- $/Mtok
- $0.084 / $0.168
gmicloud/fp8fp8 - Morph99.51%Healthy24h 99.52%
- 7d
- 98.59%
- 30d
- 98.59%
- p50
- 1.63s
- p99
- 23.9s
- Throughput
- 13 tps
- Context
- 1.0M
- $/Mtok
- $0.120 / $0.278
morph/bf16bf16 - Alibaba99.46%Healthy24h 99.13%
- 7d
- 98.68%
- 30d
- 98.68%
- p50
- 2.51s
- p99
- 14.9s
- Throughput
- 63 tps
- Context
- 1.0M
- $/Mtok
- $0.402 / $1.21
alibaba - Reka99.35%Healthy24h 99.51%
- 7d
- 98.98%
- 30d
- 98.98%
- p50
- 1.38s
- p99
- 7.47s
- Throughput
- 171 tps
- Context
- 262K
- $/Mtok
- $0.220 / $0.660
reka/fp4fp4 - DeepInfra99.35%Healthy24h 98.89%
- 7d
- 98.54%
- 30d
- 98.54%
- p50
- 646ms
- p99
- 14.1s
- Throughput
- 46 tps
- Context
- 1.0M
- $/Mtok
- $0.080 / $0.180
deepinfra/fp8fp8 - Fireworks99.29%Healthy24h 98.84%
- 7d
- 97.41%
- 30d
- 97.41%
- p50
- 857ms
- p99
- 16.1s
- Throughput
- 54 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
fireworks - Together99.22%Healthy24h 97.37%
- 7d
- 97.24%
- 30d
- 97.24%
- p50
- 721ms
- p99
- 8.31s
- Throughput
- 71 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
together - Parasail99.12%Healthy24h 98.21%
- 7d
- 98.18%
- 30d
- 98.18%
- p50
- 807ms
- p99
- 13.2s
- Throughput
- 56 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
parasail/fp8fp8 - AkashML98.13%Healthy24h 98.20%
- 7d
- 97.93%
- 30d
- 97.93%
- p50
- 1.66s
- p99
- 13.5s
- Throughput
- 33 tps
- Context
- 131K
- $/Mtok
- $0.140 / $0.280
akashml/fp8fp8 - Sail Research98.11%Healthy24h 97.75%
- 7d
- 98.58%
- 30d
- 98.58%
- p50
- 3.35s
- p99
- 50.7s
- Throughput
- 15 tps
- Context
- 1.0M
- $/Mtok
- $0.065 / $0.180
sail-research/fp4fp4 - Io Net97.90%Healthy24h 96.96%
- 7d
- 97.73%
- 30d
- 97.73%
- p50
- 886ms
- p99
- 13.5s
- Throughput
- 59 tps
- Context
- 262K
- $/Mtok
- $0.189 / $0.420
io-net/fp8fp8 - Venice97.65%Healthy24h 97.34%
- 7d
- 97.45%
- 30d
- 97.45%
- p50
- 811ms
- p99
- 11.9s
- Throughput
- 78 tps
- Context
- 1.0M
- $/Mtok
- $0.175 / $0.350
venice - DigitalOcean97.39%Healthy24h 97.33%
- 7d
- 95.79%
- 30d
- 95.79%
- p50
- 839ms
- p99
- 5.97s
- Throughput
- 10 tps
- Context
- 1.0M
- $/Mtok
- $0.080 / $0.252
digitalocean - Phala96.86%Healthy24h 98.43%
- 7d
- 97.80%
- 30d
- 97.80%
- p50
- 1.38s
- p99
- 9.63s
- Throughput
- 50 tps
- Context
- 1.0M
- $/Mtok
- $0.200 / $0.400
phala - Wafer90.47%Degraded24h 98.39%
- 7d
- 98.62%
- 30d
- 98.62%
- p50
- 952ms
- p99
- 13.4s
- Throughput
- 169 tps
- Context
- 1.0M
- $/Mtok
- $0.280 / $0.560
wafer/fast - OpenInference88.19%Down24h 94.06%
- 7d
- 94.87%
- 30d
- 94.87%
- p50
- 3.60s
- p99
- 34.9s
- Throughput
- 8.0 tps
- Context
- 262K
- $/Mtok
- $0.065 / $0.180
open-inference/fp4fp4 - Decart80.26%Down24h 88.64%
- 7d
- 79.13%
- 30d
- 79.13%
- p50
- 1.23s
- p99
- 31.4s
- Throughput
- 36 tps
- Context
- 262K
- $/Mtok
- $0.077 / $0.155
decart/fp4fp4
Measured 5m 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.