DeepSeek V4 Pro 0423: 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) | 97.45% | 98.37% | 98.37% | 1.45s | 6.13s | 51 tps | 1.0M | $1.42 / $2.83 | |
| Healthy | 100%◆ (best) | 94.75% | 96.76% | 96.76% | 1.81s | 15.7s | 38 tps | 1.0M | $1.68 / $3.38 | |
Fireworksfireworks | Healthy | 100%◆ (best) | 95.24% | 96.49% | 96.49% | 1.43s | 11.7s | 59 tps | 1.0M | $1.74 / $3.48 |
| Healthy | 100%◆ (best) | 92.90% | 92.72% | 92.72% | 419ms◆ (best) | 3.38s | 55 tps | 1.0M | $1.74 / $3.48 | |
Venicevenice | Healthy | 100%◆ (best) | 81.72% | 84.13% | 84.13% | 1.21s | 9.50s | 51 tps | 1.0M | $1.65 / $3.30 |
| Healthy | 99.98% | 99.03% | 98.03% | 98.03% | 1.10s | 7.76s | 48 tps | 1.0M | $0.642 / $1.28◆ (best) | |
| Healthy | 99.94% | 98.92% | 98.36% | 98.36% | 2.23s | 17.4s | 32 tps | 1.0M | $0.650 / $1.30 | |
| Healthy | 99.83% | 95.59% | 96.14% | 96.14% | 2.63s | 15.4s | 25 tps | 1.0M | $1.13 / $2.26 | |
DigitalOceandigitalocean | Healthy | 99.72% | 95.35% | 63.07% | 63.07% | 2.15s | 13.8s | 8.0 tps | 1.0M | $0.870 / $1.74 |
| Healthy | 99.71% | 99.52% | 98.71% | 98.71% | 805ms | 8.75s | 38 tps | 1.0M | $1.30 / $2.60 | |
| Healthy | 99.69% | 99.86% | 99.88%◆ (best) | 99.88%◆ (best) | 429ms | 4.09s | 62 tps◆ (best) | 1.0M | $1.74 / $3.48 | |
Togethertogether | Healthy | 99.67% | 96.20% | 97.59% | 97.59% | 548ms | 9.48s | 58 tps | 512K | $1.74 / $3.48 |
Azureazure/us | Healthy | 99.31% | 94.65% | 94.61% | 94.61% | 1.56s | 18.0s | 47 tps | 1.0M | $1.91 / $3.83 |
| Healthy | 99.18% | 97.96% | 97.44% | 97.44% | 2.44s | 18.7s | 40 tps | 1.0M | $1.50 / $3.14 | |
| Healthy | 98.74% | 96.43% | 97.09% | 97.09% | 3.35s | 8.69s | 26 tps | 1.0M | $0.792 / $2.38 | |
| Degraded | 98.60% | 98.69% | 99.16% | 99.16% | 1.79s | 17.5s | 46 tps | 1.0M | $1.60 / $3.20 | |
| No data | — | 96.61% | 99.52% | 99.52% | 565ms | 3.30s◆ (best) | 62 tps | 1.0M | $1.15 / $2.55 | |
DeepSeekdeepseek | No data | — | — | 86.30% | 86.30% | — | — | — | 1.0M | $0.660 / $1.98 |
- Alibaba100%◆ (best)Healthy24h 97.45%
- 7d
- 98.37%
- 30d
- 98.37%
- p50
- 1.45s
- p99
- 6.13s
- Throughput
- 51 tps
- Context
- 1.0M
- $/Mtok
- $1.42 / $2.83
alibaba/fp8fp8 - AtlasCloud100%◆ (best)Healthy24h 94.75%
- 7d
- 96.76%
- 30d
- 96.76%
- p50
- 1.81s
- p99
- 15.7s
- Throughput
- 38 tps
- Context
- 1.0M
- $/Mtok
- $1.68 / $3.38
atlas-cloud/fp4fp4 - Fireworks100%◆ (best)Healthy24h 95.24%
- 7d
- 96.49%
- 30d
- 96.49%
- p50
- 1.43s
- p99
- 11.7s
- Throughput
- 59 tps
- Context
- 1.0M
- $/Mtok
- $1.74 / $3.48
fireworks - Parasail100%◆ (best)Healthy24h 92.90%
- 7d
- 92.72%
- 30d
- 92.72%
- p50
- 419ms◆ (best)
- p99
- 3.38s
- Throughput
- 55 tps
- Context
- 1.0M
- $/Mtok
- $1.74 / $3.48
parasail/fp8fp8 - Venice100%◆ (best)Healthy24h 81.72%
- 7d
- 84.13%
- 30d
- 84.13%
- p50
- 1.21s
- p99
- 9.50s
- Throughput
- 51 tps
- Context
- 1.0M
- $/Mtok
- $1.65 / $3.30
venice - Baidu99.98%Healthy24h 99.03%
- 7d
- 98.03%
- 30d
- 98.03%
- p50
- 1.10s
- p99
- 7.76s
- Throughput
- 48 tps
- Context
- 1.0M
- $/Mtok
- $0.642 / $1.28◆ (best)
baidu/fp8fp8 - StreamLake99.94%Healthy24h 98.92%
- 7d
- 98.36%
- 30d
- 98.36%
- p50
- 2.23s
- p99
- 17.4s
- Throughput
- 32 tps
- Context
- 1.0M
- $/Mtok
- $0.650 / $1.30
streamlake/fp8fp8 - Ionstream99.83%Healthy24h 95.59%
- 7d
- 96.14%
- 30d
- 96.14%
- p50
- 2.63s
- p99
- 15.4s
- Throughput
- 25 tps
- Context
- 1.0M
- $/Mtok
- $1.13 / $2.26
ionstream/fp4fp4 - DigitalOcean99.72%Healthy24h 95.35%
- 7d
- 63.07%
- 30d
- 63.07%
- p50
- 2.15s
- p99
- 13.8s
- Throughput
- 8.0 tps
- Context
- 1.0M
- $/Mtok
- $0.870 / $1.74
digitalocean - DeepInfra99.71%Healthy24h 99.52%
- 7d
- 98.71%
- 30d
- 98.71%
- p50
- 805ms
- p99
- 8.75s
- Throughput
- 38 tps
- Context
- 1.0M
- $/Mtok
- $1.30 / $2.60
deepinfra/fp8fp8 - BaseTen99.69%Healthy24h 99.86%
- 7d
- 99.88%◆ (best)
- 30d
- 99.88%◆ (best)
- p50
- 429ms
- p99
- 4.09s
- Throughput
- 62 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $1.74 / $3.48
baseten/fp4fp4 - Together99.67%Healthy24h 96.20%
- 7d
- 97.59%
- 30d
- 97.59%
- p50
- 548ms
- p99
- 9.48s
- Throughput
- 58 tps
- Context
- 512K
- $/Mtok
- $1.74 / $3.48
together - Azure99.31%Healthy24h 94.65%
- 7d
- 94.61%
- 30d
- 94.61%
- p50
- 1.56s
- p99
- 18.0s
- Throughput
- 47 tps
- Context
- 1.0M
- $/Mtok
- $1.91 / $3.83
azure/us - SiliconFlow99.18%Healthy24h 97.96%
- 7d
- 97.44%
- 30d
- 97.44%
- p50
- 2.44s
- p99
- 18.7s
- Throughput
- 40 tps
- Context
- 1.0M
- $/Mtok
- $1.50 / $3.14
siliconflow/fp8fp8 - GMICloud98.74%Healthy24h 96.43%
- 7d
- 97.09%
- 30d
- 97.09%
- p50
- 3.35s
- p99
- 8.69s
- Throughput
- 26 tps
- Context
- 1.0M
- $/Mtok
- $0.792 / $2.38
gmicloud/fp8fp8 - Novita98.60%Degraded24h 98.69%
- 7d
- 99.16%
- 30d
- 99.16%
- p50
- 1.79s
- p99
- 17.5s
- Throughput
- 46 tps
- Context
- 1.0M
- $/Mtok
- $1.60 / $3.20
novita/fp8fp8 - No data24h 96.61%
- 7d
- 99.52%
- 30d
- 99.52%
- p50
- 565ms
- p99
- 3.30s◆ (best)
- Throughput
- 62 tps
- Context
- 1.0M
- $/Mtok
- $1.15 / $2.55
coreweave/fp8fp8 - No data24h —
- 7d
- 86.30%
- 30d
- 86.30%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.660 / $1.98
deepseek
Measured 4m 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.
Throughput
Median tokens per second.