DeepSeek V4 Flash 0731
deepseek/deepseek-v4-flash-0731InputOutput
Compare its 40 providersIncident RSSCompare with DeepSeek V4 Flash 0423, DeepSeek V4 Flash Vision Exp, DeepSeek V4.1 Flash
CompareDeepSeek V4 Flash 0731
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Alibabaalibaba | Healthy | 100% | 97.66% | 97.88% | 99.22% | 1.12s | 10.2s | 100 tps | 1.0M | $0.352 / $1.06 |
Alibabaalibaba/us-east-1 | Healthy | 100% | 99.90% | 99.14% | 99.14% | 1.51s | 6.77s | 99 tps | 1.0M | $0.374 / $1.12 |
| Healthy | 100% | 100% | 99.90% | 99.89% | 1.58s | 5.52s | 57 tps | 1.0M | $0.440 / $1.32 | |
| Healthy | 100% | 99.93% | 99.96% | 99.53% | 725ms | 5.27s | 90 tps | 1.0M | $0.440 / $1.32 | |
| Healthy | 100% | 95.62% | 99.02% | 99.58% | 655ms | 9.47s | 131 tps | 1.0M | $0.130 / $0.260 | |
Coherecohere | Healthy | 100% | 99.79% | 99.49% | 99.58% | 563ms | 11.3s | 92 tps | 1.0M | $0.140 / $0.280 |
| Healthy | 100% | 100% | 99.85% | 99.89% | 612ms | 8.27s | 89 tps | 262K | $0.130 / $0.280 | |
| Degraded | 100% | 99.86% | 99.88% | 99.83% | 9.26s | 23.8s | 16 tps | 1.0M | $0.060 / $0.180 | |
DigitalOceandigitalocean | Healthy | 100% | 100% | 99.98% | 99.84% | 892ms | 141s | 34 tps | 1.0M | $0.119 / $0.238 |
| Healthy | 100% | 100% | 100% | 99.93% | 1.74s | 6.90s | 53 tps | 1.0M | $0.286 / $0.858 | |
| Healthy | 100% | 100% | 99.66% | 99.01% | 611ms | 28.9s | 56 tps | 1.0M | $0.131 / $0.600 | |
| Healthy | 100% | 100% | 99.99% | 99.99% | 2.01s | 16.8s | 65 tps | 1.0M | $0.409 / $1.23 | |
| Degraded | 100% | 99.24% | 99.33% | 99.16% | 2.83s | 21.1s | 12 tps | 1.0M | $0.013 / $0.768 | |
| Healthy | 100% | 99.93% | 99.82% | 99.62% | 785ms | 6.27s | 65 tps | 1.0M | $0.140 / $0.280 | |
Phalaphala | Healthy | 100% | 100% | 99.30% | 99.54% | 2.87s | 50.8s | 63 tps | 1.0M | $0.308 / $0.924 |
Rekareka | Healthy | 100% | 100% | 99.45% | 99.62% | 823ms | 22.6s | 72 tps | 262K | $0.021 / $0.528 |
| Healthy | 100% | 100% | 99.97% | 99.64% | 703ms | 8.12s | 44 tps | 1.0M | $0.016 / $0.640 | |
| Healthy | 100% | 100% | 97.56% | 98.43% | 2.23s | 7.03s | 26 tps | 1.0M | $0.100 / $0.300 | |
| Healthy | 100% | 100% | 97.65% | 96.93% | 2.20s | 8.22s | 31 tps | 1.0M | $0.019 / $0.420 | |
| Healthy | 100% | 99.86% | 99.46% | 98.77% | 1.58s | 7.07s | 27 tps | 1.0M | $0.220 / $0.660 | |
| Healthy | 100% | 100% | 99.89% | 99.20% | 2.00s | 15.3s | 36 tps | 1.0M | $0.132 / $0.396 | |
Togethertogether | Healthy | 100% | 100% | 99.44% | 99.44% | 1.15s | 51.5s | 29 tps | 1.0M | $0.140 / $0.280 |
Waferwafer/fast | Healthy | 100% | 100% | 100% | 99.86% | 566ms | 15.3s | 65 tps | 1.0M | $0.130 / $0.230 |
Venicevenice | Down | 80.00% | 99.38% | 99.49% | 99.48% | 9.35s | 20.8s | 22 tps | 1.0M | $0.130 / $0.260 |
| Down | 50.00% | 99.35% | 99.03% | 98.19% | 9.29s | 20.4s | 24 tps | 1.0M | $0.200 / $0.600 | |
| No data | — | — | — | — | — | — | — | 1.0M | $0.065 / $0.180 | |
| No data | — | — | — | — | — | — | — | 1.0M | $0.080 / $0.180 | |
Cloudflarecloudflare | No data | — | 100% | 99.47% | 99.58% | 2.66s | 66.4s | 40 tps | 1.0M | $0.440 / $1.32 |
| No data | — | — | — | — | — | — | — | 262K | $0.064 / $0.128 | |
DeepSeekdeepseek | No data | — | — | — | — | — | — | — | 1.0M | $0.440 / $1.32 |
Fireworksfireworks | No data | — | — | — | 84.12% | — | — | — | 1.0M | $0.220 / $0.660 |
| No data | — | — | — | 99.75% | — | — | — | 1.0M | $0.286 / $0.858 | |
| No data | — | — | — | — | — | — | — | 262K | $0.219 / $0.490 | |
Makoramakora | No data | — | — | — | 98.54% | — | — | — | 1.0M | $0.090 / $0.195 |
Morphmorph | No data | — | — | — | 97.50% | — | — | — | 1.0M | $0.142 / $0.400 |
| No data | — | — | 85.54% | 97.20% | — | — | — | 1.0M | $0.142 / $0.400 | |
| No data | — | — | 81.84% | 87.49% | — | — | — | 1.0M | $0.140 / $0.280 | |
| No data | — | — | 99.92% | 99.45% | — | — | — | 1.0M | $0.352 / $1.06 | |
| No data | — | — | — | 98.17% | — | — | — | 1.0M | $0.004 / $1.04 | |
| No data | — | — | — | 99.46% | — | — | — | 262K | $0.088 / $0.528 |
- Alibaba100%Healthy24h 97.66%
- 7d
- 97.88%
- 30d
- 99.22%
- p50
- 1.12s
- p99
- 10.2s
- Throughput
- 100 tps
- Context
- 1.0M
- $/Mtok
- $0.352 / $1.06
alibaba - Alibaba100%Healthy24h 99.90%
- 7d
- 99.14%
- 30d
- 99.14%
- p50
- 1.51s
- p99
- 6.77s
- Throughput
- 99 tps
- Context
- 1.0M
- $/Mtok
- $0.374 / $1.12
alibaba/us-east-1 - AtlasCloud100%Healthy24h 100%
- 7d
- 99.90%
- 30d
- 99.89%
- p50
- 1.58s
- p99
- 5.52s
- Throughput
- 57 tps
- Context
- 1.0M
- $/Mtok
- $0.440 / $1.32
atlas-cloud/fp4fp4 - Baidu100%Healthy24h 99.93%
- 7d
- 99.96%
- 30d
- 99.53%
- p50
- 725ms
- p99
- 5.27s
- Throughput
- 90 tps
- Context
- 1.0M
- $/Mtok
- $0.440 / $1.32
baidu/fp8fp8 - BaseTen100%Healthy24h 95.62%
- 7d
- 99.02%
- 30d
- 99.58%
- p50
- 655ms
- p99
- 9.47s
- Throughput
- 131 tps
- Context
- 1.0M
- $/Mtok
- $0.130 / $0.260
baseten/fp8fp8 - Cohere100%Healthy24h 99.79%
- 7d
- 99.49%
- 30d
- 99.58%
- p50
- 563ms
- p99
- 11.3s
- Throughput
- 92 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
cohere - CoreWeave100%Healthy24h 100%
- 7d
- 99.85%
- 30d
- 99.89%
- p50
- 612ms
- p99
- 8.27s
- Throughput
- 89 tps
- Context
- 262K
- $/Mtok
- $0.130 / $0.280
coreweave/fp8fp8 - DeepInfra100%Degraded24h 99.86%
- 7d
- 99.88%
- 30d
- 99.83%
- p50
- 9.26s
- p99
- 23.8s
- Throughput
- 16 tps
- Context
- 1.0M
- $/Mtok
- $0.060 / $0.180
deepinfra/fp8fp8 - DigitalOcean100%Healthy24h 100%
- 7d
- 99.98%
- 30d
- 99.84%
- p50
- 892ms
- p99
- 141s
- Throughput
- 34 tps
- Context
- 1.0M
- $/Mtok
- $0.119 / $0.238
digitalocean - GMICloud100%Healthy24h 100%
- 7d
- 100%
- 30d
- 99.93%
- p50
- 1.74s
- p99
- 6.90s
- Throughput
- 53 tps
- Context
- 1.0M
- $/Mtok
- $0.286 / $0.858
gmicloud/fp8fp8 - Inceptron100%Healthy24h 100%
- 7d
- 99.66%
- 30d
- 99.01%
- p50
- 611ms
- p99
- 28.9s
- Throughput
- 56 tps
- Context
- 1.0M
- $/Mtok
- $0.131 / $0.600
inceptron/fp4fp4 - Novita100%Healthy24h 100%
- 7d
- 99.99%
- 30d
- 99.99%
- p50
- 2.01s
- p99
- 16.8s
- Throughput
- 65 tps
- Context
- 1.0M
- $/Mtok
- $0.409 / $1.23
novita/fp8fp8 - OpenInference100%Degraded24h 99.24%
- 7d
- 99.33%
- 30d
- 99.16%
- p50
- 2.83s
- p99
- 21.1s
- Throughput
- 12 tps
- Context
- 1.0M
- $/Mtok
- $0.013 / $0.768
open-inference/fp4fp4 - Parasail100%Healthy24h 99.93%
- 7d
- 99.82%
- 30d
- 99.62%
- p50
- 785ms
- p99
- 6.27s
- Throughput
- 65 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
parasail/fp8fp8 - Phala100%Healthy24h 100%
- 7d
- 99.30%
- 30d
- 99.54%
- p50
- 2.87s
- p99
- 50.8s
- Throughput
- 63 tps
- Context
- 1.0M
- $/Mtok
- $0.308 / $0.924
phala - Reka100%Healthy24h 100%
- 7d
- 99.45%
- 30d
- 99.62%
- p50
- 823ms
- p99
- 22.6s
- Throughput
- 72 tps
- Context
- 262K
- $/Mtok
- $0.021 / $0.528
reka - Relace100%Healthy24h 100%
- 7d
- 99.97%
- 30d
- 99.64%
- p50
- 703ms
- p99
- 8.12s
- Throughput
- 44 tps
- Context
- 1.0M
- $/Mtok
- $0.016 / $0.640
relace/fp4fp4 - Sail Research100%Healthy24h 100%
- 7d
- 97.56%
- 30d
- 98.43%
- p50
- 2.23s
- p99
- 7.03s
- Throughput
- 26 tps
- Context
- 1.0M
- $/Mtok
- $0.100 / $0.300
sail-research/fp4fp4 - Sail Research100%Healthy24h 100%
- 7d
- 97.65%
- 30d
- 96.93%
- p50
- 2.20s
- p99
- 8.22s
- Throughput
- 31 tps
- Context
- 1.0M
- $/Mtok
- $0.019 / $0.420
sail-research/usfp4 - SiliconFlow100%Healthy24h 99.86%
- 7d
- 99.46%
- 30d
- 98.77%
- p50
- 1.58s
- p99
- 7.07s
- Throughput
- 27 tps
- Context
- 1.0M
- $/Mtok
- $0.220 / $0.660
siliconflow/fp8fp8 - StreamLake100%Healthy24h 100%
- 7d
- 99.89%
- 30d
- 99.20%
- p50
- 2.00s
- p99
- 15.3s
- Throughput
- 36 tps
- Context
- 1.0M
- $/Mtok
- $0.132 / $0.396
streamlake/fp8fp8 - Together100%Healthy24h 100%
- 7d
- 99.44%
- 30d
- 99.44%
- p50
- 1.15s
- p99
- 51.5s
- Throughput
- 29 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
together - Wafer100%Healthy24h 100%
- 7d
- 100%
- 30d
- 99.86%
- p50
- 566ms
- p99
- 15.3s
- Throughput
- 65 tps
- Context
- 1.0M
- $/Mtok
- $0.130 / $0.230
wafer/fast - Venice80.00%Down24h 99.38%
- 7d
- 99.49%
- 30d
- 99.48%
- p50
- 9.35s
- p99
- 20.8s
- Throughput
- 22 tps
- Context
- 1.0M
- $/Mtok
- $0.130 / $0.260
venice - Mancer 250.00%Down24h 99.35%
- 7d
- 99.03%
- 30d
- 98.19%
- p50
- 9.29s
- p99
- 20.4s
- Throughput
- 24 tps
- Context
- 1.0M
- $/Mtok
- $0.200 / $0.600
mancer/fp8fp8 - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.065 / $0.180
akashml/fp8fp8 - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.080 / $0.180
ambient/fp4fp4 - No data24h 100%
- 7d
- 99.47%
- 30d
- 99.58%
- p50
- 2.66s
- p99
- 66.4s
- Throughput
- 40 tps
- Context
- 1.0M
- $/Mtok
- $0.440 / $1.32
cloudflare - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.064 / $0.128
decart/fp4fp4 - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.440 / $1.32
deepseek - No data24h —
- 7d
- —
- 30d
- 84.12%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.220 / $0.660
fireworks - No data24h —
- 7d
- —
- 30d
- 99.75%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.286 / $0.858
gmicloud/fp4fp4 - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.219 / $0.490
io-net/fp8fp8 - No data24h —
- 7d
- —
- 30d
- 98.54%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.090 / $0.195
makora - No data24h —
- 7d
- —
- 30d
- 97.50%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.142 / $0.400
morph - No data24h —
- 7d
- 85.54%
- 30d
- 97.20%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.142 / $0.400
morph/bf16bf16 - No data24h —
- 7d
- 81.84%
- 30d
- 87.49%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
nebius/fp8fp8 - No data24h —
- 7d
- 99.92%
- 30d
- 99.45%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.352 / $1.06
nextbit/fp8fp8 - No data24h —
- 7d
- —
- 30d
- 98.17%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.004 / $1.04
open-inference/fp8fp8 - Reka—No data24h —
- 7d
- —
- 30d
- 99.46%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.088 / $0.528
reka/fp4fp4
Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
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, averaged over the hour.
Throughput
Median tokens per second.
Daily availability
One row per endpoint · one dot per day · last 90 days.
Jul
Aug
Sep
Oct
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 40 endpoints · 55 days with data, 241 endpoint-days below 90%.
Price changes
- DeepSeek V4 Flash 0731Phalaphala$0.440 → $0.308 / $1.32 → $0.924cache read $0.028 → $0.0202026-10-12 10:10 UTC
- DeepSeek V4 Flash 0731Inceptroninceptron/fp4$0.038 → $0.131 / $0.6002026-10-12 03:50 UTC
- DeepSeek V4 Flash 0731OpenInferenceopen-inference/fp4$0.013 / $1.44 → $0.7682026-10-12 03:45 UTC
- DeepSeek V4 Flash 0731Waferwafer/fast$0.017 → $0.130 / $1.20 → $0.230cache read $0.016 → $0.1202026-10-12 03:35 UTC
- DeepSeek V4 Flash 0731OpenInferenceopen-inference/fp4$0.004 → $0.013 / $1.44cache read $0.004 → $0.0132026-10-12 03:30 UTC
- DeepSeek V4 Flash 0731Inceptroninceptron/fp4$0.047 → $0.038 / $0.6002026-10-12 03:30 UTC
- DeepSeek V4 Flash 0731Relacerelace/fp4$0.005 → $0.016 / $0.640cache read $0.005 → $0.0162026-10-12 03:20 UTC
- DeepSeek V4 Flash 0731Inceptroninceptron/fp4$0.049 → $0.047 / $0.6002026-10-12 03:20 UTC
- DeepSeek V4 Flash 0731OpenInferenceopen-inference/fp4$0.005 → $0.004 / $1.44cache read $0.005 → $0.0042026-10-12 03:10 UTC
- DeepSeek V4 Flash 0731Inceptroninceptron/fp4$0.061 → $0.049 / $0.6002026-10-12 03:10 UTC
- DeepSeek V4 Flash 0731Relacerelace/fp4$0.006 → $0.005 / $0.640cache read $0.006 → $0.0052026-10-12 03:00 UTC
- DeepSeek V4 Flash 0731Inceptroninceptron/fp4$0.065 → $0.061 / $0.6002026-10-12 03:00 UTC
- DeepSeek V4 Flash 0731OpenInferenceopen-inference/fp4$0.006 → $0.005 / $1.44cache read $0.006 → $0.0052026-10-12 02:50 UTC
- DeepSeek V4 Flash 0731Inceptroninceptron/fp4$0.080 → $0.065 / $0.6002026-10-12 02:50 UTC
- DeepSeek V4 Flash 0731Relacerelace/fp4$0.008 → $0.006 / $0.640cache read $0.008 → $0.0062026-10-12 02:40 UTC
- DeepSeek V4 Flash 0731Inceptroninceptron/fp4$0.101 → $0.080 / $0.6002026-10-12 02:40 UTC
- DeepSeek V4 Flash 0731OpenInferenceopen-inference/fp4$0.008 → $0.006 / $1.44cache read $0.008 → $0.0062026-10-12 02:30 UTC
- DeepSeek V4 Flash 0731Inceptroninceptron/fp4$0.107 → $0.101 / $0.6002026-10-12 02:30 UTC
- DeepSeek V4 Flash 0731OpenInferenceopen-inference/fp4$0.008 → $0.008 / $1.44cache read $0.008 → $0.0082026-10-12 02:25 UTC
- DeepSeek V4 Flash 0731Relacerelace/fp4$0.010 → $0.008 / $0.640cache read $0.010 → $0.0082026-10-12 02:20 UTC
- DeepSeek V4 Flash 0731Inceptroninceptron/fp4$0.112 → $0.107 / $0.6002026-10-12 02:20 UTC
- DeepSeek V4 Flash 0731Relacerelace/fp4$0.010 → $0.010 / $0.640cache read $0.010 → $0.0102026-10-12 02:15 UTC
- DeepSeek V4 Flash 0731StreamLakestreamlake/fp8$0.088 → $0.132 / $0.264 → $0.396cache read $0.003 → $0.0042026-10-12 02:10 UTC
- DeepSeek V4 Flash 0731OpenInferenceopen-inference/fp4$0.010 → $0.008 / $1.44cache read $0.010 → $0.0082026-10-12 02:10 UTC
- DeepSeek V4 Flash 0731Inceptroninceptron/fp4$0.139 → $0.112 / $0.6002026-10-12 02:10 UTC
- DeepSeek V4 Flash 0731OpenInferenceopen-inference/fp4$0.011 → $0.010 / $1.44cache read $0.011 → $0.0102026-10-12 02:05 UTC
- DeepSeek V4 Flash 0731Relacerelace/fp4$0.013 → $0.010 / $0.640cache read $0.013 → $0.0102026-10-12 02:00 UTC
- DeepSeek V4 Flash 0731Inceptroninceptron/fp4$0.148 → $0.139 / $0.6002026-10-12 02:00 UTC
- DeepSeek V4 Flash 0731Relacerelace/fp4$0.014 → $0.013 / $0.640cache read $0.014 → $0.0132026-10-12 01:55 UTC
- DeepSeek V4 Flash 0731OpenInferenceopen-inference/fp4$0.014 → $0.011 / $1.44cache read $0.014 → $0.0112026-10-12 01:50 UTC