DeepSeek V4 Pro 0813: 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) | 99.47% | 99.57% | 99.65% | 570ms◆ (best) | 3.92s | 104 tps | 1.0M | $1.31 / $3.96 | |
| Degraded | 100%◆ (best) | 98.96% | 99.47% | 99.24% | 1.46s | 43.9s | 48 tps | 1.0M | $1.30 / $2.60 | |
DeepSeekdeepseek | Healthy | 100%◆ (best) | 99.98% | 99.97% | 99.97%◆ (best) | 1.20s | 10.7s | 33 tps | 1.0M | $1.32 / $3.96 |
DigitalOceandigitalocean | Healthy | 100%◆ (best) | 99.97% | 99.89% | 99.70% | 586ms | 1.96s◆ (best) | 45 tps | 1.0M | $1.32 / $3.96 |
| Healthy | 100%◆ (best) | 99.87% | 99.95% | 99.77% | 3.89s | 39.0s | 30 tps | 1.0M | $1.06 / $3.17 | |
Ionstreamionstream | Healthy | 100%◆ (best) | 99.38% | 98.48% | 98.90% | 1.81s | 25.1s | 33 tps | 1.0M | $0.380 / $1.98 |
| Healthy | 100%◆ (best) | 99.93% | 99.95% | 99.47% | 3.26s | 11.5s | 43 tps | 1.0M | $1.06 / $3.17 | |
| Healthy | 100%◆ (best) | 99.88% | 99.96% | 99.92% | 1.28s | 6.40s | 89 tps | 1.0M | $0.990 / $2.97 | |
| Healthy | 100%◆ (best) | 94.20% | 97.45% | 99.15% | 1.10s | 21.0s | 50 tps | 1.0M | $1.32 / $3.96 | |
Phalaphala | Healthy | 100%◆ (best) | 98.18% | 99.13% | 99.46% | 3.67s | 16.8s | 45 tps | 1.0M | $1.45 / $4.36 |
| Healthy | 100%◆ (best) | 99.92% | 98.97% | 98.65% | 845ms | 5.89s | 115 tps◆ (best) | 1.0M | $0.296 / $4.20◆ (best) | |
Togethertogether | Healthy | 100%◆ (best) | 97.78% | 98.43% | 99.07% | 905ms | 9.63s | 61 tps | 1.0M | $1.32 / $3.96 |
Waferwafer | Healthy | 99.93% | 99.63% | 99.22% | 99.20% | 719ms | 5.98s | 100 tps | 1.0M | $0.400 / $5.00 |
StreamLakestreamlake | Healthy | 99.35% | 99.47% | 99.62% | 99.70% | 2.33s | 11.2s | 44 tps | 1.0M | $0.660 / $1.98 |
| Healthy | 97.37% | 99.36% | 98.96% | 99.39% | 1.52s | 5.60s | 64 tps | 1.0M | $1.32 / $3.96 | |
Alibabaalibaba | Degraded | 95.31% | 96.84% | 98.13% | 99.30% | 1.26s | 3.42s | 71 tps | 1.0M | $1.12 / $3.37 |
| No data | — | 99.95% | 99.92% | 99.92% | 1.12s | 73.0s | 47 tps | 1.0M | $1.32 / $3.96 | |
| No data | — | — | — | 98.89% | — | — | — | 1.0M | $1.32 / $3.96 | |
Cloudflarecloudflare | No data | — | 99.25% | 99.39% | 98.27% | 1.31s | 8.73s | 37 tps | 1.0M | $1.32 / $3.96 |
Fireworksfireworks | No data | — | — | — | 96.18% | — | — | — | 1.0M | $1.32 / $3.96 |
| No data | — | — | 99.38% | 99.59% | — | — | — | 262K | $0.490 / $2.45 | |
| No data | — | — | — | 99.94% | — | — | — | 1.0M | $1.10 / $3.30 | |
| No data | — | 99.18% | 99.00% | 88.84% | 1.23s | 10.1s | 90 tps | 979K | $1.32 / $3.96 | |
Rekareka | No data | — | — | 99.51% | 99.51% | — | — | — | 1.0M | $1.12 / $3.37 |
| No data | — | — | — | 99.40% | — | — | — | 1.0M | $0.400 / $4.30 | |
| No data | — | — | — | 99.09% | — | — | — | 1.0M | $0.400 / $4.30 | |
| No data | — | 100% | 100%◆ (best) | 99.18% | 1.49s | 2.58s | 76 tps | 1.0M | $1.32 / $3.96 | |
Venicevenice | No data | — | 90.38% | 94.82% | 97.62% | 1.76s | 12.7s | 49 tps | 1.0M | $1.65 / $4.95 |
- CoreWeave100%◆ (best)Healthy24h 99.47%
- 7d
- 99.57%
- 30d
- 99.65%
- p50
- 570ms◆ (best)
- p99
- 3.92s
- Throughput
- 104 tps
- Context
- 1.0M
- $/Mtok
- $1.31 / $3.96
coreweave/fp8fp8 - DeepInfra100%◆ (best)Degraded24h 98.96%
- 7d
- 99.47%
- 30d
- 99.24%
- p50
- 1.46s
- p99
- 43.9s
- Throughput
- 48 tps
- Context
- 1.0M
- $/Mtok
- $1.30 / $2.60
deepinfra/fp8fp8 - DeepSeek100%◆ (best)Healthy24h 99.98%
- 7d
- 99.97%
- 30d
- 99.97%◆ (best)
- p50
- 1.20s
- p99
- 10.7s
- Throughput
- 33 tps
- Context
- 1.0M
- $/Mtok
- $1.32 / $3.96
deepseek - DigitalOcean100%◆ (best)Healthy24h 99.97%
- 7d
- 99.89%
- 30d
- 99.70%
- p50
- 586ms
- p99
- 1.96s◆ (best)
- Throughput
- 45 tps
- Context
- 1.0M
- $/Mtok
- $1.32 / $3.96
digitalocean - GMICloud100%◆ (best)Healthy24h 99.87%
- 7d
- 99.95%
- 30d
- 99.77%
- p50
- 3.89s
- p99
- 39.0s
- Throughput
- 30 tps
- Context
- 1.0M
- $/Mtok
- $1.06 / $3.17
gmicloud/fp8fp8 - Ionstream100%◆ (best)Healthy24h 99.38%
- 7d
- 98.48%
- 30d
- 98.90%
- p50
- 1.81s
- p99
- 25.1s
- Throughput
- 33 tps
- Context
- 1.0M
- $/Mtok
- $0.380 / $1.98
ionstream - NextBit100%◆ (best)Healthy24h 99.93%
- 7d
- 99.95%
- 30d
- 99.47%
- p50
- 3.26s
- p99
- 11.5s
- Throughput
- 43 tps
- Context
- 1.0M
- $/Mtok
- $1.06 / $3.17
nextbit/fp8fp8 - Novita100%◆ (best)Healthy24h 99.88%
- 7d
- 99.96%
- 30d
- 99.92%
- p50
- 1.28s
- p99
- 6.40s
- Throughput
- 89 tps
- Context
- 1.0M
- $/Mtok
- $0.990 / $2.97
novita/fp8fp8 - Parasail100%◆ (best)Healthy24h 94.20%
- 7d
- 97.45%
- 30d
- 99.15%
- p50
- 1.10s
- p99
- 21.0s
- Throughput
- 50 tps
- Context
- 1.0M
- $/Mtok
- $1.32 / $3.96
parasail/fp8fp8 - Phala100%◆ (best)Healthy24h 98.18%
- 7d
- 99.13%
- 30d
- 99.46%
- p50
- 3.67s
- p99
- 16.8s
- Throughput
- 45 tps
- Context
- 1.0M
- $/Mtok
- $1.45 / $4.36
phala - Relace100%◆ (best)Healthy24h 99.92%
- 7d
- 98.97%
- 30d
- 98.65%
- p50
- 845ms
- p99
- 5.89s
- Throughput
- 115 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $0.296 / $4.20◆ (best)
relace/fp4fp4 - Together100%◆ (best)Healthy24h 97.78%
- 7d
- 98.43%
- 30d
- 99.07%
- p50
- 905ms
- p99
- 9.63s
- Throughput
- 61 tps
- Context
- 1.0M
- $/Mtok
- $1.32 / $3.96
together - Wafer99.93%Healthy24h 99.63%
- 7d
- 99.22%
- 30d
- 99.20%
- p50
- 719ms
- p99
- 5.98s
- Throughput
- 100 tps
- Context
- 1.0M
- $/Mtok
- $0.400 / $5.00
wafer - StreamLake99.35%Healthy24h 99.47%
- 7d
- 99.62%
- 30d
- 99.70%
- p50
- 2.33s
- p99
- 11.2s
- Throughput
- 44 tps
- Context
- 1.0M
- $/Mtok
- $0.660 / $1.98
streamlake - AtlasCloud97.37%Healthy24h 99.36%
- 7d
- 98.96%
- 30d
- 99.39%
- p50
- 1.52s
- p99
- 5.60s
- Throughput
- 64 tps
- Context
- 1.0M
- $/Mtok
- $1.32 / $3.96
atlas-cloud/fp8fp8 - Alibaba95.31%Degraded24h 96.84%
- 7d
- 98.13%
- 30d
- 99.30%
- p50
- 1.26s
- p99
- 3.42s
- Throughput
- 71 tps
- Context
- 1.0M
- $/Mtok
- $1.12 / $3.37
alibaba - No data24h 99.95%
- 7d
- 99.92%
- 30d
- 99.92%
- p50
- 1.12s
- p99
- 73.0s
- Throughput
- 47 tps
- Context
- 1.0M
- $/Mtok
- $1.32 / $3.96
baidu/fp8fp8 - No data24h —
- 7d
- —
- 30d
- 98.89%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $1.32 / $3.96
baseten/fp4fp4 - No data24h 99.25%
- 7d
- 99.39%
- 30d
- 98.27%
- p50
- 1.31s
- p99
- 8.73s
- Throughput
- 37 tps
- Context
- 1.0M
- $/Mtok
- $1.32 / $3.96
cloudflare - No data24h —
- 7d
- —
- 30d
- 96.18%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $1.32 / $3.96
fireworks - No data24h —
- 7d
- 99.38%
- 30d
- 99.59%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.490 / $2.45
io-net/fp8fp8 - No data24h —
- 7d
- —
- 30d
- 99.94%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $1.10 / $3.30
ionstream/fp4fp4 - No data24h 99.18%
- 7d
- 99.00%
- 30d
- 88.84%
- p50
- 1.23s
- p99
- 10.1s
- Throughput
- 90 tps
- Context
- 979K
- $/Mtok
- $1.32 / $3.96
nebius/fp8fp8 - Reka—No data24h —
- 7d
- 99.51%
- 30d
- 99.51%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $1.12 / $3.37
reka - No data24h —
- 7d
- —
- 30d
- 99.40%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.400 / $4.30
sail-research/fp4fp4 - No data24h —
- 7d
- —
- 30d
- 99.09%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.400 / $4.30
sail-research/usfp4 - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 99.18%
- p50
- 1.49s
- p99
- 2.58s
- Throughput
- 76 tps
- Context
- 1.0M
- $/Mtok
- $1.32 / $3.96
siliconflow/fp8fp8 - No data24h 90.38%
- 7d
- 94.82%
- 30d
- 97.62%
- p50
- 1.76s
- p99
- 12.7s
- Throughput
- 49 tps
- Context
- 1.0M
- $/Mtok
- $1.65 / $4.95
venice
Measured 3m 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.