DeepSeek V4 Flash 0423
deepseek/deepseek-v4-flashInputOutput
Compare its 25 providersIncident RSSCompare with DeepSeek V4 Flash 0731, DeepSeek V4 Flash Vision Exp, DeepSeek V4.1 Flash
CompareDeepSeek V4 Flash 0423
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 99.91% | 99.97% | 99.69% | 1.67s | 5.75s | 53 tps | 1.0M | $0.091 / $0.182 | |
| Healthy | 99.97% | 99.96% | 99.95% | 99.93% | 1.52s | 5.36s | 56 tps | 1.0M | $0.140 / $0.280 | |
| Healthy | 99.95% | 99.93% | 99.64% | 99.73% | 536ms | 6.07s | 102 tps | 1.0M | $0.030 / $1.28 | |
| Healthy | 99.91% | 99.54% | 89.47% | 96.37% | 1.15s | 12.2s | 65 tps | 1.0M | $0.140 / $0.280 | |
DigitalOceandigitalocean | Healthy | 99.83% | 99.79% | 99.82% | 99.83% | 1.20s | 42.6s | 14 tps | 1.0M | $0.098 / $0.196 |
| Healthy | 99.74% | 99.04% | 99.04% | 97.67% | 1.47s | 12.0s | 59 tps | 1.0M | $0.042 / $0.084 | |
| Healthy | 99.72% | 98.78% | 98.41% | 99.26% | 1.83s | 9.54s | 58 tps | 1.0M | $0.140 / $0.280 | |
| Healthy | 99.67% | 99.75% | 99.81% | 99.72% | 847ms | 8.13s | 57 tps | 1.0M | $0.140 / $0.280 | |
| Healthy | 99.57% | 99.59% | 98.61% | 98.61% | 870ms | 11.1s | 34 tps | 1.0M | $0.039 / $1.66 | |
| Healthy | 99.49% | 99.41% | 99.73% | 98.28% | 1.15s | 10.1s | 44 tps | 1.0M | $0.130 / $0.280 | |
Cloudflarecloudflare | Degraded | 99.38% | 99.12% | 99.78% | 99.78% | 4.12s | 28.3s | 53 tps | 384K | $0.440 / $1.32 |
Azureazure/us | Healthy | 99.12% | 96.91% | 97.60% | 95.91% | 2.60s | 35.5s | 45 tps | 1.0M | $0.210 / $0.560 |
| Healthy | 98.86% | 98.97% | 98.78% | 99.11% | 855ms | 5.11s | 95 tps | 1.0M | $0.134 / $0.268 | |
Venicevenice | Down | 80.43% | 98.51% | 98.92% | 98.40% | 1.21s | 19.0s | 51 tps | 1.0M | $0.097 / $0.193 |
| Down | 63.20% | 96.92% | 97.36% | 97.97% | 885ms | 17.1s | 20 tps | 1.0M | $0.190 / $0.500 | |
| No data | — | — | — | — | — | — | — | 1.0M | $0.140 / $0.280 | |
| No data | — | — | — | — | — | — | — | 1.0M | $0.140 / $0.280 | |
| No data | — | 99.82% | 99.55% | 99.49% | 9.42s | 26.7s | 10 tps | 1.0M | $0.090 / $0.180 | |
DeepSeekdeepseek | No data | — | — | — | — | — | — | — | 1.0M | $0.220 / $0.660 |
| No data | — | — | — | 99.35% | — | — | — | 1.0M | $0.150 / $0.300 | |
| No data | — | — | 95.36% | 97.88% | — | — | — | 1.0M | $0.002 / $1.31 | |
Phalaphala | No data | — | — | — | 99.71% | — | — | — | 1.0M | $0.200 / $0.400 |
Rekareka | No data | — | — | 98.07% | 98.07% | — | — | — | 1.0M | $0.130 / $0.260 |
| No data | — | — | — | — | — | — | — | 1.0M | $0.090 / $0.180 | |
Waferwafer | No data | — | — | — | 99.43% | — | — | — | 1.0M | $0.100 / $0.250 |
- GMICloud100%Healthy24h 99.91%
- 7d
- 99.97%
- 30d
- 99.69%
- p50
- 1.67s
- p99
- 5.75s
- Throughput
- 53 tps
- Context
- 1.0M
- $/Mtok
- $0.091 / $0.182
gmicloud/fp8fp8 - Novita99.97%Healthy24h 99.96%
- 7d
- 99.95%
- 30d
- 99.93%
- p50
- 1.52s
- p99
- 5.36s
- Throughput
- 56 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
novita/fp8fp8 - Relace99.95%Healthy24h 99.93%
- 7d
- 99.64%
- 30d
- 99.73%
- p50
- 536ms
- p99
- 6.07s
- Throughput
- 102 tps
- Context
- 1.0M
- $/Mtok
- $0.030 / $1.28
relace/fp4fp4 - Baidu99.91%Healthy24h 99.54%
- 7d
- 89.47%
- 30d
- 96.37%
- p50
- 1.15s
- p99
- 12.2s
- Throughput
- 65 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
baidu/fp8fp8 - DigitalOcean99.83%Healthy24h 99.79%
- 7d
- 99.82%
- 30d
- 99.83%
- p50
- 1.20s
- p99
- 42.6s
- Throughput
- 14 tps
- Context
- 1.0M
- $/Mtok
- $0.098 / $0.196
digitalocean - StreamLake99.74%Healthy24h 99.04%
- 7d
- 99.04%
- 30d
- 97.67%
- p50
- 1.47s
- p99
- 12.0s
- Throughput
- 59 tps
- Context
- 1.0M
- $/Mtok
- $0.042 / $0.084
streamlake/fp8fp8 - AtlasCloud99.72%Healthy24h 98.78%
- 7d
- 98.41%
- 30d
- 99.26%
- p50
- 1.83s
- p99
- 9.54s
- Throughput
- 58 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
atlas-cloud/fp4fp4 - Parasail99.67%Healthy24h 99.75%
- 7d
- 99.81%
- 30d
- 99.72%
- p50
- 847ms
- p99
- 8.13s
- Throughput
- 57 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
parasail/fp8fp8 - OpenInference99.57%Healthy24h 99.59%
- 7d
- 98.61%
- 30d
- 98.61%
- p50
- 870ms
- p99
- 11.1s
- Throughput
- 34 tps
- Context
- 1.0M
- $/Mtok
- $0.039 / $1.66
open-inference/fp4fp4 - SiliconFlow99.49%Healthy24h 99.41%
- 7d
- 99.73%
- 30d
- 98.28%
- p50
- 1.15s
- p99
- 10.1s
- Throughput
- 44 tps
- Context
- 1.0M
- $/Mtok
- $0.130 / $0.280
siliconflow/fp8fp8 - Cloudflare99.38%Degraded24h 99.12%
- 7d
- 99.78%
- 30d
- 99.78%
- p50
- 4.12s
- p99
- 28.3s
- Throughput
- 53 tps
- Context
- 384K
- $/Mtok
- $0.440 / $1.32
cloudflare - Azure99.12%Healthy24h 96.91%
- 7d
- 97.60%
- 30d
- 95.91%
- p50
- 2.60s
- p99
- 35.5s
- Throughput
- 45 tps
- Context
- 1.0M
- $/Mtok
- $0.210 / $0.560
azure/us - Alibaba98.86%Healthy24h 98.97%
- 7d
- 98.78%
- 30d
- 99.11%
- p50
- 855ms
- p99
- 5.11s
- Throughput
- 95 tps
- Context
- 1.0M
- $/Mtok
- $0.134 / $0.268
alibaba/fp8fp8 - Venice80.43%Down24h 98.51%
- 7d
- 98.92%
- 30d
- 98.40%
- p50
- 1.21s
- p99
- 19.0s
- Throughput
- 51 tps
- Context
- 1.0M
- $/Mtok
- $0.097 / $0.193
venice - Mancer 263.20%Down24h 96.92%
- 7d
- 97.36%
- 30d
- 97.97%
- p50
- 885ms
- p99
- 17.1s
- Throughput
- 20 tps
- Context
- 1.0M
- $/Mtok
- $0.190 / $0.500
mancer/fp8fp8 - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
coreweave/fp8fp8 - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
crusoe/fp8fp8 - No data24h 99.82%
- 7d
- 99.55%
- 30d
- 99.49%
- p50
- 9.42s
- p99
- 26.7s
- Throughput
- 10 tps
- Context
- 1.0M
- $/Mtok
- $0.090 / $0.180
deepinfra/fp8fp8 - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.220 / $0.660
deepseek - No data24h —
- 7d
- —
- 30d
- 99.35%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.150 / $0.300
nextbit/fp8fp8 - No data24h —
- 7d
- 95.36%
- 30d
- 97.88%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.002 / $1.31
open-inference/fp8fp8 - No data24h —
- 7d
- —
- 30d
- 99.71%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.200 / $0.400
phala - Reka—No data24h —
- 7d
- 98.07%
- 30d
- 98.07%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.130 / $0.260
reka - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.090 / $0.180
sail-research/fp4fp4 - No data24h —
- 7d
- —
- 30d
- 99.43%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.100 / $0.250
wafer
Measured 5m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
9 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.
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 24 endpoints · 48 days with data, 137 endpoint-days below 90%.
Price changes
- DeepSeek V4 Flash 0423OpenInferenceopen-inference/fp4$0.038 → $0.039 / $1.66cache read $0.038 → $0.0392026-10-05 05:05 UTC
- DeepSeek V4 Flash 0423Relacerelace/fp4$0.029 → $0.030 / $1.28cache read $0.029 → $0.0302026-10-05 05:01 UTC
- DeepSeek V4 Flash 0423OpenInferenceopen-inference/fp4$0.039 → $0.038 / $1.66cache read $0.039 → $0.0382026-10-05 04:55 UTC
- DeepSeek V4 Flash 0423Relacerelace/fp4$0.030 → $0.029 / $1.28cache read $0.030 → $0.0292026-10-05 04:50 UTC
- DeepSeek V4 Flash 0423OpenInferenceopen-inference/fp4$0.037 → $0.039 / $1.66cache read $0.037 → $0.0392026-10-05 04:50 UTC
- DeepSeek V4 Flash 0423Relacerelace/fp4$0.028 → $0.030 / $1.28cache read $0.028 → $0.0302026-10-05 04:45 UTC
- DeepSeek V4 Flash 0423OpenInferenceopen-inference/fp4$0.039 → $0.037 / $1.66cache read $0.039 → $0.0372026-10-05 04:40 UTC
- DeepSeek V4 Flash 0423Relacerelace/fp4$0.030 → $0.028 / $1.28cache read $0.030 → $0.0282026-10-05 04:35 UTC
- DeepSeek V4 Flash 0423OpenInferenceopen-inference/fp4$0.035 → $0.039 / $1.66cache read $0.035 → $0.0392026-10-05 04:35 UTC
- DeepSeek V4 Flash 0423Relacerelace/fp4$0.027 → $0.030 / $1.28cache read $0.027 → $0.0302026-10-05 04:30 UTC
- DeepSeek V4 Flash 0423OpenInferenceopen-inference/fp4$0.038 → $0.035 / $1.66cache read $0.038 → $0.0352026-10-05 04:25 UTC
- DeepSeek V4 Flash 0423Relacerelace/fp4$0.029 → $0.027 / $1.28cache read $0.029 → $0.0272026-10-05 04:20 UTC
- DeepSeek V4 Flash 0423OpenInferenceopen-inference/fp4$0.034 → $0.038 / $1.66cache read $0.034 → $0.0382026-10-05 04:20 UTC
- DeepSeek V4 Flash 0423Relacerelace/fp4$0.026 → $0.029 / $1.28cache read $0.026 → $0.0292026-10-05 04:16 UTC
- DeepSeek V4 Flash 0423OpenInferenceopen-inference/fp4$0.037 → $0.034 / $1.66cache read $0.037 → $0.0342026-10-05 04:10 UTC
- DeepSeek V4 Flash 0423Relacerelace/fp4$0.028 → $0.026 / $1.28cache read $0.028 → $0.0262026-10-05 04:05 UTC
- DeepSeek V4 Flash 0423OpenInferenceopen-inference/fp4$0.033 → $0.037 / $1.66cache read $0.033 → $0.0372026-10-05 04:05 UTC
- DeepSeek V4 Flash 0423Relacerelace/fp4$0.025 → $0.028 / $1.28cache read $0.025 → $0.0282026-10-05 04:00 UTC
- DeepSeek V4 Flash 0423OpenInferenceopen-inference/fp4$0.035 → $0.033 / $1.66cache read $0.035 → $0.0332026-10-05 04:00 UTC
- DeepSeek V4 Flash 0423Relacerelace/fp4$0.027 → $0.025 / $1.28cache read $0.027 → $0.0252026-10-05 03:55 UTC
- DeepSeek V4 Flash 0423OpenInferenceopen-inference/fp4$0.034 → $0.035 / $1.66cache read $0.034 → $0.0352026-10-05 03:45 UTC
- DeepSeek V4 Flash 0423Relacerelace/fp4$0.026 → $0.027 / $1.28cache read $0.026 → $0.0272026-10-05 03:40 UTC
- DeepSeek V4 Flash 0423OpenInferenceopen-inference/fp4$0.033 → $0.034 / $1.66cache read $0.033 → $0.0342026-10-05 03:25 UTC
- DeepSeek V4 Flash 0423Relacerelace/fp4$0.025 → $0.026 / $1.28cache read $0.025 → $0.0262026-10-05 03:20 UTC
- DeepSeek V4 Flash 0423OpenInferenceopen-inference/fp4$0.031 → $0.033 / $1.66cache read $0.031 → $0.0332026-10-05 03:10 UTC
- DeepSeek V4 Flash 0423Relacerelace/fp4$0.024 → $0.025 / $1.28cache read $0.024 → $0.0252026-10-05 03:05 UTC
- DeepSeek V4 Flash 0423OpenInferenceopen-inference/fp4$0.030 → $0.031 / $1.66cache read $0.030 → $0.0312026-10-05 02:55 UTC
- DeepSeek V4 Flash 0423Relacerelace/fp4$0.023 → $0.024 / $1.28cache read $0.023 → $0.0242026-10-05 02:50 UTC
- DeepSeek V4 Flash 0423OpenInferenceopen-inference/fp4$0.029 → $0.030 / $1.66cache read $0.029 → $0.0302026-10-05 02:45 UTC
- DeepSeek V4 Flash 0423Relacerelace/fp4$0.022 → $0.023 / $1.28cache read $0.022 → $0.0232026-10-05 02:40 UTC