DeepSeek V4 Flash 0731: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100%◆ (best) | 99.90% | 99.89% | 99.65% | 1.30s | 3.21s | 84 tps | 1.0M | $0.440 / $1.32 | |
| Healthy | 100%◆ (best) | 97.42% | 99.66% | 98.37% | 989ms | 12.3s | 84 tps | 1.0M | $0.130 / $0.260 | |
Cloudflarecloudflare | Healthy | 100%◆ (best) | 99.97% | 99.95% | 99.69% | 985ms | 29.9s | 61 tps | 1.0M | $0.440 / $1.32 |
| Healthy | 100%◆ (best) | 99.99% | 99.98% | 99.91% | 465ms | 4.86s | 100 tps | 262K | $0.130 / $0.280 | |
| Healthy | 100%◆ (best) | 99.94% | 99.91% | 99.75% | 841ms | 8.33s | 29 tps | 1.0M | $0.060 / $0.180 | |
| Healthy | 100%◆ (best) | 99.99% | 99.99% | 96.44% | 1.97s | 5.60s | 66 tps | 1.0M | $0.286 / $0.858 | |
| Healthy | 100%◆ (best) | 99.92% | 99.93% | 98.97% | 642ms | 9.73s | 46 tps | 1.0M | $0.050 / $0.650 | |
| Healthy | 100%◆ (best) | 99.33% | 99.23% | 97.85% | 1.20s | 10.6s | 42 tps | 1.0M | $0.200 / $0.600 | |
| Healthy | 100%◆ (best) | 93.31% | 95.70% | 98.06% | 1.49s | 30.0s | 19 tps | 1.0M | $0.142 / $0.400 | |
| Healthy | 100%◆ (best) | 99.82% | 99.96% | 99.54% | 2.36s | 5.14s | 57 tps | 1.0M | $0.352 / $1.06 | |
| Healthy | 100%◆ (best) | 100% | 99.99%◆ (best) | 99.99% | 1.24s | 7.56s | 50 tps | 1.0M | $0.409 / $1.23 | |
| Healthy | 100%◆ (best) | 99.50% | 99.52% | 98.72% | 1.42s | 7.45s | 56 tps | 1.0M | $0.220 / $0.660 | |
Waferwafer/fast | Healthy | 100%◆ (best) | 99.96% | 99.99% | 99.46% | 523ms | 1.29s◆ (best) | 80 tps | 1.0M | $0.200 / $0.840 |
| Healthy | 99.98% | 99.92% | 99.22% | 99.47% | 853ms | 4.82s | 107 tps◆ (best) | 1.0M | $0.440 / $1.32 | |
| Healthy | 99.97% | 99.90% | 99.30% | 99.31% | 732ms | 7.89s | 42 tps | 1.0M | $0.015 / $1.28 | |
Togethertogether | Healthy | 99.95% | 99.69% | 99.70% | 99.51% | 931ms | 30.3s | 36 tps | 1.0M | $0.140 / $0.280 |
DigitalOceandigitalocean | Healthy | 99.85% | 99.94% | 99.86% | 99.65% | 573ms | 10.9s | 47 tps | 1.0M | $0.119 / $0.238 |
Alibabaalibaba | Healthy | 99.85% | 99.08% | 99.14% | 99.64% | 1.42s | 6.72s | 89 tps | 1.0M | $0.176 / $0.528 |
| Healthy | 99.77% | 99.69% | 99.65% | 99.12% | 1.31s | 9.25s | 40 tps | 1.0M | $0.044 / $0.132 | |
| Healthy | 99.71% | 99.63% | 98.79% | 98.79% | 1.06s | 7.79s | 34 tps | 1.0M | $0.020 / $1.66 | |
| Healthy | 99.70% | 99.57% | 99.54% | 99.63% | 688ms | 4.78s | 100 tps | 1.0M | $0.140 / $0.280 | |
Rekareka | Healthy | 99.68% | 99.86% | 99.71% | 99.73% | 717ms | 12.2s | 84 tps | 262K | $0.021 / $0.528 |
Coherecohere | Healthy | 99.51% | 99.65% | 99.69% | 99.63% | 451ms◆ (best) | 14.1s | 107 tps◆ (best) | 1.0M | $0.140 / $0.280 |
Venicevenice | Healthy | 99.07% | 99.55% | 99.63% | 99.26% | 1.21s | 12.1s | 37 tps | 1.0M | $0.175 / $0.350 |
| Healthy | 97.54% | 97.81% | 98.38% | 98.88% | 3.39s | 16.7s | 24 tps | 1.0M | $0.019 / $0.300 | |
| Healthy | 96.89% | 96.57% | 97.62% | 96.49% | 3.39s | 17.9s | 25 tps | 1.0M | $0.019 / $0.420 | |
| No data | — | — | — | — | — | — | — | 1.0M | $0.065 / $0.180 | |
| No data | — | — | — | — | — | — | — | 1.0M | $0.080 / $0.180 | |
| No data | — | — | — | — | — | — | — | 262K | $0.064 / $0.128 | |
DeepSeekdeepseek | No data | — | — | — | 99.99%◆ (best) | — | — | — | 1.0M | $0.440 / $1.32 |
Fireworksfireworks | No data | — | — | — | 88.18% | — | — | — | 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 | — | — | 98.81% | 98.27% | — | — | — | 1.0M | $0.090 / $0.195 |
Morphmorph | No data | — | — | — | 97.50% | — | — | — | 1.0M | $0.142 / $0.400 |
| No data | — | — | 89.54% | 87.88% | — | — | — | 1.0M | $0.140 / $0.280 | |
| No data | — | — | 95.84% | 98.38% | — | — | — | 1.0M | $0.004 / $1.04◆ (best) | |
Phalaphala | No data | — | 99.85% | 99.93% | 98.50% | 2.21s | 3.68s | 42 tps | 1.0M | $0.308 / $0.924 |
| No data | — | — | — | 99.44% | — | — | — | 262K | $0.088 / $0.528 |
- AtlasCloud100%◆ (best)Healthy24h 99.90%
- 7d
- 99.89%
- 30d
- 99.65%
- p50
- 1.30s
- p99
- 3.21s
- Throughput
- 84 tps
- Context
- 1.0M
- $/Mtok
- $0.440 / $1.32
atlas-cloud/fp4fp4 - BaseTen100%◆ (best)Healthy24h 97.42%
- 7d
- 99.66%
- 30d
- 98.37%
- p50
- 989ms
- p99
- 12.3s
- Throughput
- 84 tps
- Context
- 1.0M
- $/Mtok
- $0.130 / $0.260
baseten/fp8fp8 - Cloudflare100%◆ (best)Healthy24h 99.97%
- 7d
- 99.95%
- 30d
- 99.69%
- p50
- 985ms
- p99
- 29.9s
- Throughput
- 61 tps
- Context
- 1.0M
- $/Mtok
- $0.440 / $1.32
cloudflare - CoreWeave100%◆ (best)Healthy24h 99.99%
- 7d
- 99.98%
- 30d
- 99.91%
- p50
- 465ms
- p99
- 4.86s
- Throughput
- 100 tps
- Context
- 262K
- $/Mtok
- $0.130 / $0.280
coreweave/fp8fp8 - DeepInfra100%◆ (best)Healthy24h 99.94%
- 7d
- 99.91%
- 30d
- 99.75%
- p50
- 841ms
- p99
- 8.33s
- Throughput
- 29 tps
- Context
- 1.0M
- $/Mtok
- $0.060 / $0.180
deepinfra/fp8fp8 - GMICloud100%◆ (best)Healthy24h 99.99%
- 7d
- 99.99%
- 30d
- 96.44%
- p50
- 1.97s
- p99
- 5.60s
- Throughput
- 66 tps
- Context
- 1.0M
- $/Mtok
- $0.286 / $0.858
gmicloud/fp8fp8 - Inceptron100%◆ (best)Healthy24h 99.92%
- 7d
- 99.93%
- 30d
- 98.97%
- p50
- 642ms
- p99
- 9.73s
- Throughput
- 46 tps
- Context
- 1.0M
- $/Mtok
- $0.050 / $0.650
inceptron/fp4fp4 - Mancer 2100%◆ (best)Healthy24h 99.33%
- 7d
- 99.23%
- 30d
- 97.85%
- p50
- 1.20s
- p99
- 10.6s
- Throughput
- 42 tps
- Context
- 1.0M
- $/Mtok
- $0.200 / $0.600
mancer/fp8fp8 - Morph100%◆ (best)Healthy24h 93.31%
- 7d
- 95.70%
- 30d
- 98.06%
- p50
- 1.49s
- p99
- 30.0s
- Throughput
- 19 tps
- Context
- 1.0M
- $/Mtok
- $0.142 / $0.400
morph/bf16bf16 - NextBit100%◆ (best)Healthy24h 99.82%
- 7d
- 99.96%
- 30d
- 99.54%
- p50
- 2.36s
- p99
- 5.14s
- Throughput
- 57 tps
- Context
- 1.0M
- $/Mtok
- $0.352 / $1.06
nextbit/fp8fp8 - Novita100%◆ (best)Healthy24h 100%
- 7d
- 99.99%◆ (best)
- 30d
- 99.99%
- p50
- 1.24s
- p99
- 7.56s
- Throughput
- 50 tps
- Context
- 1.0M
- $/Mtok
- $0.409 / $1.23
novita/fp8fp8 - SiliconFlow100%◆ (best)Healthy24h 99.50%
- 7d
- 99.52%
- 30d
- 98.72%
- p50
- 1.42s
- p99
- 7.45s
- Throughput
- 56 tps
- Context
- 1.0M
- $/Mtok
- $0.220 / $0.660
siliconflow/fp8fp8 - Wafer100%◆ (best)Healthy24h 99.96%
- 7d
- 99.99%
- 30d
- 99.46%
- p50
- 523ms
- p99
- 1.29s◆ (best)
- Throughput
- 80 tps
- Context
- 1.0M
- $/Mtok
- $0.200 / $0.840
wafer/fast - Baidu99.98%Healthy24h 99.92%
- 7d
- 99.22%
- 30d
- 99.47%
- p50
- 853ms
- p99
- 4.82s
- Throughput
- 107 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $0.440 / $1.32
baidu/fp8fp8 - Relace99.97%Healthy24h 99.90%
- 7d
- 99.30%
- 30d
- 99.31%
- p50
- 732ms
- p99
- 7.89s
- Throughput
- 42 tps
- Context
- 1.0M
- $/Mtok
- $0.015 / $1.28
relace/fp4fp4 - Together99.95%Healthy24h 99.69%
- 7d
- 99.70%
- 30d
- 99.51%
- p50
- 931ms
- p99
- 30.3s
- Throughput
- 36 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
together - DigitalOcean99.85%Healthy24h 99.94%
- 7d
- 99.86%
- 30d
- 99.65%
- p50
- 573ms
- p99
- 10.9s
- Throughput
- 47 tps
- Context
- 1.0M
- $/Mtok
- $0.119 / $0.238
digitalocean - Alibaba99.85%Healthy24h 99.08%
- 7d
- 99.14%
- 30d
- 99.64%
- p50
- 1.42s
- p99
- 6.72s
- Throughput
- 89 tps
- Context
- 1.0M
- $/Mtok
- $0.176 / $0.528
alibaba - StreamLake99.77%Healthy24h 99.69%
- 7d
- 99.65%
- 30d
- 99.12%
- p50
- 1.31s
- p99
- 9.25s
- Throughput
- 40 tps
- Context
- 1.0M
- $/Mtok
- $0.044 / $0.132
streamlake/fp8fp8 - OpenInference99.71%Healthy24h 99.63%
- 7d
- 98.79%
- 30d
- 98.79%
- p50
- 1.06s
- p99
- 7.79s
- Throughput
- 34 tps
- Context
- 1.0M
- $/Mtok
- $0.020 / $1.66
open-inference/fp4fp4 - Parasail99.70%Healthy24h 99.57%
- 7d
- 99.54%
- 30d
- 99.63%
- p50
- 688ms
- p99
- 4.78s
- Throughput
- 100 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
parasail/fp8fp8 - Reka99.68%Healthy24h 99.86%
- 7d
- 99.71%
- 30d
- 99.73%
- p50
- 717ms
- p99
- 12.2s
- Throughput
- 84 tps
- Context
- 262K
- $/Mtok
- $0.021 / $0.528
reka - Cohere99.51%Healthy24h 99.65%
- 7d
- 99.69%
- 30d
- 99.63%
- p50
- 451ms◆ (best)
- p99
- 14.1s
- Throughput
- 107 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
cohere - Venice99.07%Healthy24h 99.55%
- 7d
- 99.63%
- 30d
- 99.26%
- p50
- 1.21s
- p99
- 12.1s
- Throughput
- 37 tps
- Context
- 1.0M
- $/Mtok
- $0.175 / $0.350
venice - Sail Research97.54%Healthy24h 97.81%
- 7d
- 98.38%
- 30d
- 98.88%
- p50
- 3.39s
- p99
- 16.7s
- Throughput
- 24 tps
- Context
- 1.0M
- $/Mtok
- $0.019 / $0.300
sail-research/fp4fp4 - Sail Research96.89%Healthy24h 96.57%
- 7d
- 97.62%
- 30d
- 96.49%
- p50
- 3.39s
- p99
- 17.9s
- Throughput
- 25 tps
- Context
- 1.0M
- $/Mtok
- $0.019 / $0.420
sail-research/usfp4 - 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 —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.064 / $0.128
decart/fp4fp4 - No data24h —
- 7d
- —
- 30d
- 99.99%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.440 / $1.32
deepseek - No data24h —
- 7d
- —
- 30d
- 88.18%
- 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
- 98.81%
- 30d
- 98.27%
- 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
- 89.54%
- 30d
- 87.88%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
nebius/fp8fp8 - No data24h —
- 7d
- 95.84%
- 30d
- 98.38%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.004 / $1.04◆ (best)
open-inference/fp8fp8 - No data24h 99.85%
- 7d
- 99.93%
- 30d
- 98.50%
- p50
- 2.21s
- p99
- 3.68s
- Throughput
- 42 tps
- Context
- 1.0M
- $/Mtok
- $0.308 / $0.924
phala - Reka—No data24h —
- 7d
- —
- 30d
- 99.44%
- 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. ◆ marks the best value in each column among these endpoints.
Price vs latency
One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag
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.