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) | 99.36% | 98.96% | 99.39% | 1.50s | 5.84s | 74 tps | 1.0M | $1.32 / $3.96 | |
| Healthy | 100%◆ (best) | 99.95% | 99.92% | 99.92% | 1.10s | 70.0s | 48 tps | 1.0M | $1.32 / $3.96 | |
| Healthy | 100%◆ (best) | 98.96% | 99.47% | 99.24% | 1.35s | 17.8s | 54 tps | 1.0M | $1.30 / $2.60 | |
DeepSeekdeepseek | Healthy | 100%◆ (best) | 99.98% | 99.97% | 99.97%◆ (best) | 1.20s | 10.7s | 32 tps | 1.0M | $1.32 / $3.96 |
DigitalOceandigitalocean | Healthy | 100%◆ (best) | 99.97% | 99.89% | 99.70% | 547ms◆ (best) | 2.08s◆ (best) | 44 tps | 1.0M | $1.32 / $3.96 |
| Healthy | 100%◆ (best) | 99.87% | 99.95% | 99.77% | 3.88s | 39.4s | 30 tps | 1.0M | $1.06 / $3.17 | |
Ionstreamionstream | Healthy | 100%◆ (best) | 99.38% | 98.48% | 98.90% | 1.73s | 21.5s | 33 tps | 1.0M | $0.380 / $1.98 |
| Healthy | 100%◆ (best) | 99.93% | 99.95% | 99.47% | 3.19s | 9.84s | 51 tps | 1.0M | $1.06 / $3.17 | |
| Healthy | 100%◆ (best) | 99.88% | 99.96% | 99.92% | 1.32s | 6.55s | 86 tps | 1.0M | $0.990 / $2.97 | |
| Healthy | 100%◆ (best) | 94.22% | 97.45% | 99.15% | 1.03s | 9.51s | 49 tps | 1.0M | $1.32 / $3.96 | |
Phalaphala | Healthy | 100%◆ (best) | 98.21% | 99.13% | 99.46% | 3.40s | 17.1s | 49 tps | 1.0M | $1.45 / $4.36 |
| Healthy | 100%◆ (best) | 99.92% | 98.97% | 98.65% | 829ms | 6.07s | 116 tps◆ (best) | 1.0M | $0.296 / $4.20◆ (best) | |
| Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 99.18% | 1.48s | 2.65s | 79 tps | 1.0M | $1.32 / $3.96 | |
Togethertogether | Healthy | 100%◆ (best) | 97.79% | 98.43% | 99.07% | 963ms | 7.90s | 56 tps | 1.0M | $1.32 / $3.96 |
Waferwafer | Healthy | 99.89% | 99.63% | 99.22% | 99.20% | 722ms | 4.02s | 100 tps | 1.0M | $0.400 / $5.00 |
StreamLakestreamlake | Healthy | 99.84% | 99.47% | 99.62% | 99.70% | 2.29s | 11.3s | 45 tps | 1.0M | $0.660 / $1.98 |
| Healthy | 99.82% | 99.47% | 99.57% | 99.65% | 557ms | 3.55s | 114 tps | 1.0M | $1.31 / $3.96 | |
Alibabaalibaba | Healthy | 98.35% | 96.85% | 98.13% | 99.30% | 1.25s | 3.37s | 75 tps | 1.0M | $1.12 / $3.37 |
| No data | — | — | — | 98.89% | — | — | — | 1.0M | $1.32 / $3.96 | |
Cloudflarecloudflare | No data | — | 99.25% | 99.39% | 98.27% | 1.30s | 10.3s | 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 | — | 99.19% | 99.00% | 88.84% | 1.21s | 9.40s | 87 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 | |
Venicevenice | No data | — | 90.40% | 94.82% | 97.62% | 1.80s | 12.5s | 51 tps | 1.0M | $1.65 / $4.95 |
- AtlasCloud100%◆ (best)Healthy24h 99.36%
- 7d
- 98.96%
- 30d
- 99.39%
- p50
- 1.50s
- p99
- 5.84s
- Throughput
- 74 tps
- Context
- 1.0M
- $/Mtok
- $1.32 / $3.96
atlas-cloud/fp8fp8 - Baidu100%◆ (best)Healthy24h 99.95%
- 7d
- 99.92%
- 30d
- 99.92%
- p50
- 1.10s
- p99
- 70.0s
- Throughput
- 48 tps
- Context
- 1.0M
- $/Mtok
- $1.32 / $3.96
baidu/fp8fp8 - DeepInfra100%◆ (best)Healthy24h 98.96%
- 7d
- 99.47%
- 30d
- 99.24%
- p50
- 1.35s
- p99
- 17.8s
- Throughput
- 54 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
- 32 tps
- Context
- 1.0M
- $/Mtok
- $1.32 / $3.96
deepseek - DigitalOcean100%◆ (best)Healthy24h 99.97%
- 7d
- 99.89%
- 30d
- 99.70%
- p50
- 547ms◆ (best)
- p99
- 2.08s◆ (best)
- Throughput
- 44 tps
- Context
- 1.0M
- $/Mtok
- $1.32 / $3.96
digitalocean - GMICloud100%◆ (best)Healthy24h 99.87%
- 7d
- 99.95%
- 30d
- 99.77%
- p50
- 3.88s
- p99
- 39.4s
- 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
- 1.73s
- p99
- 21.5s
- Throughput
- 33 tps
- Context
- 1.0M
- $/Mtok
- $0.380 / $1.98
ionstream - NextBit100%◆ (best)Healthy24h 99.93%
- 7d
- 99.95%
- 30d
- 99.47%
- p50
- 3.19s
- p99
- 9.84s
- Throughput
- 51 tps
- Context
- 1.0M
- $/Mtok
- $1.06 / $3.17
nextbit/fp8fp8 - Novita100%◆ (best)Healthy24h 99.88%
- 7d
- 99.96%
- 30d
- 99.92%
- p50
- 1.32s
- p99
- 6.55s
- Throughput
- 86 tps
- Context
- 1.0M
- $/Mtok
- $0.990 / $2.97
novita/fp8fp8 - Parasail100%◆ (best)Healthy24h 94.22%
- 7d
- 97.45%
- 30d
- 99.15%
- p50
- 1.03s
- p99
- 9.51s
- Throughput
- 49 tps
- Context
- 1.0M
- $/Mtok
- $1.32 / $3.96
parasail/fp8fp8 - Phala100%◆ (best)Healthy24h 98.21%
- 7d
- 99.13%
- 30d
- 99.46%
- p50
- 3.40s
- p99
- 17.1s
- Throughput
- 49 tps
- Context
- 1.0M
- $/Mtok
- $1.45 / $4.36
phala - Relace100%◆ (best)Healthy24h 99.92%
- 7d
- 98.97%
- 30d
- 98.65%
- p50
- 829ms
- p99
- 6.07s
- Throughput
- 116 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $0.296 / $4.20◆ (best)
relace/fp4fp4 - SiliconFlow100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 99.18%
- p50
- 1.48s
- p99
- 2.65s
- Throughput
- 79 tps
- Context
- 1.0M
- $/Mtok
- $1.32 / $3.96
siliconflow/fp8fp8 - Together100%◆ (best)Healthy24h 97.79%
- 7d
- 98.43%
- 30d
- 99.07%
- p50
- 963ms
- p99
- 7.90s
- Throughput
- 56 tps
- Context
- 1.0M
- $/Mtok
- $1.32 / $3.96
together - Wafer99.89%Healthy24h 99.63%
- 7d
- 99.22%
- 30d
- 99.20%
- p50
- 722ms
- p99
- 4.02s
- Throughput
- 100 tps
- Context
- 1.0M
- $/Mtok
- $0.400 / $5.00
wafer - StreamLake99.84%Healthy24h 99.47%
- 7d
- 99.62%
- 30d
- 99.70%
- p50
- 2.29s
- p99
- 11.3s
- Throughput
- 45 tps
- Context
- 1.0M
- $/Mtok
- $0.660 / $1.98
streamlake - CoreWeave99.82%Healthy24h 99.47%
- 7d
- 99.57%
- 30d
- 99.65%
- p50
- 557ms
- p99
- 3.55s
- Throughput
- 114 tps
- Context
- 1.0M
- $/Mtok
- $1.31 / $3.96
coreweave/fp8fp8 - Alibaba98.35%Healthy24h 96.85%
- 7d
- 98.13%
- 30d
- 99.30%
- p50
- 1.25s
- p99
- 3.37s
- Throughput
- 75 tps
- Context
- 1.0M
- $/Mtok
- $1.12 / $3.37
alibaba - 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
- 1.30s
- p99
- 10.3s
- 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 99.19%
- 7d
- 99.00%
- 30d
- 88.84%
- p50
- 1.21s
- p99
- 9.40s
- Throughput
- 87 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 90.40%
- 7d
- 94.82%
- 30d
- 97.62%
- p50
- 1.80s
- p99
- 12.5s
- Throughput
- 51 tps
- Context
- 1.0M
- $/Mtok
- $1.65 / $4.95
venice
Measured 1m 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.