DeepSeek V4 Flash 0731
deepseek/deepseek-v4-flash-0731InputOutput
Compare its 39 providersIncident RSSCompare with DeepSeek V4 Flash 0423, DeepSeek V4 Flash Vision Exp, DeepSeek V4.1 Flash
CompareDeepSeek V4 Flash 0731
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 99.96% | 99.19% | 99.46% | 686ms | 3.82s | 100 tps | 1.0M | $0.440 / $1.32 | |
| Healthy | 100% | 99.97% | 99.93% | 98.28% | 441ms | 4.20s | 198 tps | 1.0M | $0.130 / $0.260 | |
Cloudflarecloudflare | Healthy | 100% | 99.99% | 99.89% | 99.69% | 2.21s | 8.43s | 52 tps | 1.0M | $0.440 / $1.32 |
Coherecohere | Healthy | 100% | 99.90% | 99.66% | 99.60% | 677ms | 4.72s | 190 tps | 1.0M | $0.140 / $0.280 |
DigitalOceandigitalocean | Healthy | 100% | 99.89% | 99.84% | 99.65% | 583ms | 2.74s | 31 tps | 1.0M | $0.119 / $0.238 |
| Healthy | 100% | 100% | 99.95% | 94.98% | 1.70s | 4.79s | 66 tps | 1.0M | $0.286 / $0.858 | |
| Healthy | 100% | 99.90% | 99.83% | 98.92% | 478ms | 3.15s | 87 tps | 1.0M | $0.050 / $0.650 | |
| Healthy | 100% | 99.38% | 99.24% | 97.78% | 938ms | 3.37s | 80 tps | 1.0M | $0.200 / $0.600 | |
| Healthy | 100% | 99.99% | 99.99% | 99.98% | 1.76s | 6.16s | 70 tps | 1.0M | $0.409 / $1.23 | |
Rekareka | Healthy | 100% | 99.91% | 99.67% | 99.71% | 581ms | 6.61s | 109 tps | 262K | $0.021 / $0.528 |
| Healthy | 100% | 98.01% | 99.30% | 99.29% | 960ms | 10.1s | 32 tps | 1.0M | $0.015 / $1.28 | |
| Healthy | 100% | 99.66% | 99.46% | 98.74% | 1.38s | 6.53s | 53 tps | 1.0M | $0.220 / $0.660 | |
Togethertogether | Healthy | 100% | 99.77% | 99.71% | 99.51% | 568ms | 11.4s | 74 tps | 1.0M | $0.140 / $0.280 |
Venicevenice | Healthy | 100% | 99.77% | 99.65% | 99.10% | 1.15s | 30.2s | 57 tps | 1.0M | $0.175 / $0.350 |
Waferwafer/fast | Healthy | 100% | 100% | 99.99% | 99.40% | 477ms | 2.39s | 113 tps | 1.0M | $0.120 / $0.840 |
| Healthy | 99.99% | 100% | 99.98% | 99.90% | 448ms | 6.01s | 120 tps | 262K | $0.130 / $0.280 | |
| Healthy | 99.97% | 99.94% | 99.87% | 99.72% | 689ms | 5.76s | 51 tps | 1.0M | $0.060 / $0.180 | |
| Healthy | 99.95% | 99.83% | 99.46% | 99.64% | 1.29s | 41.2s | 109 tps | 1.0M | $0.140 / $0.280 | |
| Healthy | 99.94% | 98.75% | 97.69% | 96.29% | 1.53s | 7.33s | 35 tps | 1.0M | $0.019 / $0.420 | |
| Healthy | 99.87% | 99.70% | 99.63% | 99.12% | 1.25s | 7.54s | 41 tps | 1.0M | $0.044 / $0.132 | |
| Healthy | 99.87% | 99.43% | 98.46% | 98.96% | 1.93s | 19.2s | 32 tps | 1.0M | $0.019 / $0.300 | |
| Healthy | 99.74% | 99.75% | 97.42% | 97.42% | 1.14s | 7.91s | 35 tps | 1.0M | $0.020 / $1.66 | |
| Down | 41.75% | 98.52% | 97.79% | 97.88% | 746ms | 7.23s | 53 tps | 1.0M | $0.142 / $0.400 | |
| No data | — | — | — | 96.04% | — | — | — | 1.0M | $0.065 / $0.180 | |
Alibabaalibaba | No data | — | 98.83% | 99.28% | 99.68% | 1.40s | 6.28s | 82 tps | 1.0M | $0.352 / $1.06 |
| No data | — | — | — | — | — | — | — | 1.0M | $0.080 / $0.180 | |
| No data | — | 99.95% | 99.87% | 99.62% | 1.34s | 1.99s | 90 tps | 1.0M | $0.440 / $1.32 | |
| No data | — | — | — | — | — | — | — | 262K | $0.064 / $0.128 | |
DeepSeekdeepseek | No data | — | — | — | 99.99% | — | — | — | 1.0M | $0.440 / $1.32 |
Fireworksfireworks | No data | — | — | 0.00% | 88.65% | — | — | — | 1.0M | $0.220 / $0.660 |
| No data | — | — | — | 99.27% | — | — | — | 1.0M | $0.286 / $0.858 | |
| No data | — | — | — | — | — | — | — | 262K | $0.219 / $0.490 | |
Makoramakora | No data | — | — | 98.86% | 97.50% | — | — | — | 1.0M | $0.090 / $0.195 |
Morphmorph | No data | — | — | — | 97.50% | — | — | — | 1.0M | $0.142 / $0.400 |
| No data | — | — | 91.90% | 87.88% | — | — | — | 1.0M | $0.140 / $0.280 | |
| No data | — | 100% | 99.97% | 99.53% | 2.29s | 5.77s | 80 tps | 1.0M | $0.352 / $1.06 | |
| No data | — | — | 96.45% | 98.47% | — | — | — | 1.0M | $0.004 / $1.04 | |
Phalaphala | No data | — | 99.90% | 99.65% | 97.76% | 3.00s | 23.0s | 42 tps | 1.0M | $0.440 / $1.32 |
| No data | — | — | — | 99.37% | — | — | — | 262K | $0.088 / $0.528 |
- Baidu100%Healthy24h 99.96%
- 7d
- 99.19%
- 30d
- 99.46%
- p50
- 686ms
- p99
- 3.82s
- Throughput
- 100 tps
- Context
- 1.0M
- $/Mtok
- $0.440 / $1.32
baidu/fp8fp8 - BaseTen100%Healthy24h 99.97%
- 7d
- 99.93%
- 30d
- 98.28%
- p50
- 441ms
- p99
- 4.20s
- Throughput
- 198 tps
- Context
- 1.0M
- $/Mtok
- $0.130 / $0.260
baseten/fp8fp8 - Cloudflare100%Healthy24h 99.99%
- 7d
- 99.89%
- 30d
- 99.69%
- p50
- 2.21s
- p99
- 8.43s
- Throughput
- 52 tps
- Context
- 1.0M
- $/Mtok
- $0.440 / $1.32
cloudflare - Cohere100%Healthy24h 99.90%
- 7d
- 99.66%
- 30d
- 99.60%
- p50
- 677ms
- p99
- 4.72s
- Throughput
- 190 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
cohere - DigitalOcean100%Healthy24h 99.89%
- 7d
- 99.84%
- 30d
- 99.65%
- p50
- 583ms
- p99
- 2.74s
- Throughput
- 31 tps
- Context
- 1.0M
- $/Mtok
- $0.119 / $0.238
digitalocean - GMICloud100%Healthy24h 100%
- 7d
- 99.95%
- 30d
- 94.98%
- p50
- 1.70s
- p99
- 4.79s
- Throughput
- 66 tps
- Context
- 1.0M
- $/Mtok
- $0.286 / $0.858
gmicloud/fp8fp8 - Inceptron100%Healthy24h 99.90%
- 7d
- 99.83%
- 30d
- 98.92%
- p50
- 478ms
- p99
- 3.15s
- Throughput
- 87 tps
- Context
- 1.0M
- $/Mtok
- $0.050 / $0.650
inceptron/fp4fp4 - Mancer 2100%Healthy24h 99.38%
- 7d
- 99.24%
- 30d
- 97.78%
- p50
- 938ms
- p99
- 3.37s
- Throughput
- 80 tps
- Context
- 1.0M
- $/Mtok
- $0.200 / $0.600
mancer/fp8fp8 - Novita100%Healthy24h 99.99%
- 7d
- 99.99%
- 30d
- 99.98%
- p50
- 1.76s
- p99
- 6.16s
- Throughput
- 70 tps
- Context
- 1.0M
- $/Mtok
- $0.409 / $1.23
novita/fp8fp8 - Reka100%Healthy24h 99.91%
- 7d
- 99.67%
- 30d
- 99.71%
- p50
- 581ms
- p99
- 6.61s
- Throughput
- 109 tps
- Context
- 262K
- $/Mtok
- $0.021 / $0.528
reka - Relace100%Healthy24h 98.01%
- 7d
- 99.30%
- 30d
- 99.29%
- p50
- 960ms
- p99
- 10.1s
- Throughput
- 32 tps
- Context
- 1.0M
- $/Mtok
- $0.015 / $1.28
relace/fp4fp4 - SiliconFlow100%Healthy24h 99.66%
- 7d
- 99.46%
- 30d
- 98.74%
- p50
- 1.38s
- p99
- 6.53s
- Throughput
- 53 tps
- Context
- 1.0M
- $/Mtok
- $0.220 / $0.660
siliconflow/fp8fp8 - Together100%Healthy24h 99.77%
- 7d
- 99.71%
- 30d
- 99.51%
- p50
- 568ms
- p99
- 11.4s
- Throughput
- 74 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
together - Venice100%Healthy24h 99.77%
- 7d
- 99.65%
- 30d
- 99.10%
- p50
- 1.15s
- p99
- 30.2s
- Throughput
- 57 tps
- Context
- 1.0M
- $/Mtok
- $0.175 / $0.350
venice - Wafer100%Healthy24h 100%
- 7d
- 99.99%
- 30d
- 99.40%
- p50
- 477ms
- p99
- 2.39s
- Throughput
- 113 tps
- Context
- 1.0M
- $/Mtok
- $0.120 / $0.840
wafer/fast - CoreWeave99.99%Healthy24h 100%
- 7d
- 99.98%
- 30d
- 99.90%
- p50
- 448ms
- p99
- 6.01s
- Throughput
- 120 tps
- Context
- 262K
- $/Mtok
- $0.130 / $0.280
coreweave/fp8fp8 - DeepInfra99.97%Healthy24h 99.94%
- 7d
- 99.87%
- 30d
- 99.72%
- p50
- 689ms
- p99
- 5.76s
- Throughput
- 51 tps
- Context
- 1.0M
- $/Mtok
- $0.060 / $0.180
deepinfra/fp8fp8 - Parasail99.95%Healthy24h 99.83%
- 7d
- 99.46%
- 30d
- 99.64%
- p50
- 1.29s
- p99
- 41.2s
- Throughput
- 109 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
parasail/fp8fp8 - Sail Research99.94%Healthy24h 98.75%
- 7d
- 97.69%
- 30d
- 96.29%
- p50
- 1.53s
- p99
- 7.33s
- Throughput
- 35 tps
- Context
- 1.0M
- $/Mtok
- $0.019 / $0.420
sail-research/usfp4 - StreamLake99.87%Healthy24h 99.70%
- 7d
- 99.63%
- 30d
- 99.12%
- p50
- 1.25s
- p99
- 7.54s
- Throughput
- 41 tps
- Context
- 1.0M
- $/Mtok
- $0.044 / $0.132
streamlake/fp8fp8 - Sail Research99.87%Healthy24h 99.43%
- 7d
- 98.46%
- 30d
- 98.96%
- p50
- 1.93s
- p99
- 19.2s
- Throughput
- 32 tps
- Context
- 1.0M
- $/Mtok
- $0.019 / $0.300
sail-research/fp4fp4 - OpenInference99.74%Healthy24h 99.75%
- 7d
- 97.42%
- 30d
- 97.42%
- p50
- 1.14s
- p99
- 7.91s
- Throughput
- 35 tps
- Context
- 1.0M
- $/Mtok
- $0.020 / $1.66
open-inference/fp4fp4 - Morph41.75%Down24h 98.52%
- 7d
- 97.79%
- 30d
- 97.88%
- p50
- 746ms
- p99
- 7.23s
- Throughput
- 53 tps
- Context
- 1.0M
- $/Mtok
- $0.142 / $0.400
morph/bf16bf16 - No data24h —
- 7d
- —
- 30d
- 96.04%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.065 / $0.180
akashml/fp8fp8 - No data24h 98.83%
- 7d
- 99.28%
- 30d
- 99.68%
- p50
- 1.40s
- p99
- 6.28s
- Throughput
- 82 tps
- Context
- 1.0M
- $/Mtok
- $0.352 / $1.06
alibaba - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.080 / $0.180
ambient/fp4fp4 - No data24h 99.95%
- 7d
- 99.87%
- 30d
- 99.62%
- p50
- 1.34s
- p99
- 1.99s
- Throughput
- 90 tps
- Context
- 1.0M
- $/Mtok
- $0.440 / $1.32
atlas-cloud/fp4fp4 - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.064 / $0.128
decart/fp4fp4 - No data24h —
- 7d
- —
- 30d
- 99.99%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.440 / $1.32
deepseek - No data24h —
- 7d
- 0.00%
- 30d
- 88.65%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.220 / $0.660
fireworks - No data24h —
- 7d
- —
- 30d
- 99.27%
- 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
- 98.86%
- 30d
- 97.50%
- 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
- 91.90%
- 30d
- 87.88%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
nebius/fp8fp8 - No data24h 100%
- 7d
- 99.97%
- 30d
- 99.53%
- p50
- 2.29s
- p99
- 5.77s
- Throughput
- 80 tps
- Context
- 1.0M
- $/Mtok
- $0.352 / $1.06
nextbit/fp8fp8 - No data24h —
- 7d
- 96.45%
- 30d
- 98.47%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.004 / $1.04
open-inference/fp8fp8 - No data24h 99.90%
- 7d
- 99.65%
- 30d
- 97.76%
- p50
- 3.00s
- p99
- 23.0s
- Throughput
- 42 tps
- Context
- 1.0M
- $/Mtok
- $0.440 / $1.32
phala - Reka—No data24h —
- 7d
- —
- 30d
- 99.37%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.088 / $0.528
reka/fp4fp4
Measured 5m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
12 endpoints have no chartable data in this range.
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.
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 · 39 endpoints · 47 days with data, 211 endpoint-days below 90%.
Price changes
- DeepSeek V4 Flash 0731OpenInferenceopen-inference/fp4$0.020 / $1.66cache read $0.018 → $0.0202026-10-04 05:25 UTC
- DeepSeek V4 Flash 0731Relacerelace/fp4$0.015 / $1.28cache read $0.014 → $0.0152026-10-04 05:20 UTC
- DeepSeek V4 Flash 0731Phalaphala$0.308 → $0.440 / $0.924 → $1.32cache read $0.020 → $0.0282026-10-04 01:15 UTC
- DeepSeek V4 Flash 0731Alibabaalibaba$0.176 → $0.352 / $0.528 → $1.06cache read $0.018 → $0.0352026-10-04 00:10 UTC
- DeepSeek V4 Flash 0731OpenInferenceopen-inference/fp4$0.024 → $0.020 / $1.66cache read $0.022 → $0.0182026-10-03 22:05 UTC
- DeepSeek V4 Flash 0731Relacerelace/fp4$0.019 → $0.015 / $1.28cache read $0.017 → $0.0142026-10-03 22:01 UTC
- DeepSeek V4 Flash 0731Waferwafer/fast$0.120 / $0.700 → $0.8402026-10-03 21:55 UTC
- DeepSeek V4 Flash 0731OpenInferenceopen-inference/fp4$0.024 / $1.66cache read $0.024 → $0.0222026-10-03 21:45 UTC
- DeepSeek V4 Flash 0731Relacerelace/fp4$0.019 / $1.28cache read $0.019 → $0.0172026-10-03 21:40 UTC
- DeepSeek V4 Flash 0731Waferwafer/fast$0.120 / $0.840 → $0.7002026-10-03 21:40 UTC
- DeepSeek V4 Flash 0731Waferwafer/fast$0.120 / $1.00 → $0.8402026-10-03 19:20 UTC
- DeepSeek V4 Flash 0731Alibabaalibaba$0.352 → $0.176 / $1.06 → $0.528cache read $0.035 → $0.0182026-10-03 14:05 UTC
- DeepSeek V4 Flash 0731Phalaphala$0.440 → $0.308 / $1.32 → $0.924cache read $0.028 → $0.0202026-10-03 10:05 UTC
- DeepSeek V4 Flash 0731OpenInferenceopen-inference/fp4$0.022 → $0.024 / $1.66cache read $0.022 → $0.0242026-10-03 09:15 UTC
- DeepSeek V4 Flash 0731Relacerelace/fp4$0.017 → $0.019 / $1.28cache read $0.017 → $0.0192026-10-03 09:10 UTC
- DeepSeek V4 Flash 0731OpenInferenceopen-inference/fp4$0.022 / $1.66cache read $0.020 → $0.0222026-10-03 08:15 UTC
- DeepSeek V4 Flash 0731Relacerelace/fp4$0.017 / $1.28cache read $0.015 → $0.0172026-10-03 08:10 UTC
- DeepSeek V4 Flash 0731OpenInferenceopen-inference/fp4$0.021 → $0.022 / $1.66cache read $0.019 → $0.0202026-10-03 06:30 UTC
- DeepSeek V4 Flash 0731Relacerelace/fp4$0.016 → $0.017 / $1.28cache read $0.015 → $0.0152026-10-03 06:25 UTC
- DeepSeek V4 Flash 0731OpenInferenceopen-inference/fp4$0.016 → $0.021 / $1.66cache read $0.015 → $0.0192026-10-03 06:10 UTC
- DeepSeek V4 Flash 0731Relacerelace/fp4$0.012 → $0.016 / $1.28cache read $0.011 → $0.0152026-10-03 06:01 UTC
- DeepSeek V4 Flash 0731OpenInferenceopen-inference/fp4$0.018 → $0.016 / $1.66cache read $0.016 → $0.0152026-10-03 05:50 UTC
- DeepSeek V4 Flash 0731OpenInferenceopen-inference/fp4$0.014 → $0.018 / $1.28 → $1.66cache read $0.012 → $0.0162026-10-03 05:40 UTC
- DeepSeek V4 Flash 0731Relacerelace/fp4$0.014 → $0.012 / $1.28cache read $0.012 → $0.0112026-10-03 05:40 UTC
- DeepSeek V4 Flash 0731OpenInferenceopen-inference/fp4$0.015 → $0.014 / $1.28cache read $0.014 → $0.0122026-10-03 05:31 UTC
- DeepSeek V4 Flash 0731Relacerelace/fp4$0.015 → $0.014 / $1.28cache read $0.014 → $0.0122026-10-03 05:25 UTC
- DeepSeek V4 Flash 0731OpenInferenceopen-inference/fp4$0.017 → $0.015 / $1.28cache read $0.015 → $0.0142026-10-03 05:15 UTC
- DeepSeek V4 Flash 0731Relacerelace/fp4$0.017 → $0.015 / $1.28cache read $0.015 → $0.0142026-10-03 05:10 UTC
- DeepSeek V4 Flash 0731OpenInferenceopen-inference/fp4$0.020 → $0.017 / $0.603 → $1.28cache read $0.010 → $0.0152026-10-03 05:01 UTC
- DeepSeek V4 Flash 0731Relacerelace/fp4$0.011 → $0.017 / $1.28cache read $0.010 → $0.0152026-10-03 04:45 UTC