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) | 99.95% | 99.18% | 99.30% | 956ms | 15.2s | 59 tps | 1.0M | $1.69 / $3.38 | |
Cloudflarecloudflare | Healthy | 100%◆ (best) | 98.19% | 97.84% | 95.61% | 1.62s | 24.4s | 36 tps | 1.0M | $1.15 / $2.55 |
| Healthy | 100%◆ (best) | 99.76% | 99.73% | 99.41% | 1.16s | 8.80s | 50 tps | 1.0M | $1.30 / $2.60 | |
DigitalOceandigitalocean | Healthy | 100%◆ (best) | 99.58% | 99.63% | 99.25% | 1.67s | 35.6s | 32 tps | 1.0M | $1.04 / $2.09 |
| Healthy | 100%◆ (best) | 99.11% | 98.49% | 98.75% | 4.23s | 9.66s | 46 tps | 1.0M | $1.74 / $3.48 | |
| Healthy | 100%◆ (best) | 99.93% | 99.95%◆ (best) | 99.91%◆ (best) | 2.01s | 27.3s | 62 tps | 1.0M | $1.60 / $3.20 | |
Rekareka | Healthy | 100%◆ (best) | 99.45% | 95.68% | 95.68% | 1.13s | 15.3s | 29 tps | 1.0M | $0.900 / $9.00 |
| Healthy | 100%◆ (best) | 99.11% | 99.48% | 98.52% | 1.45s | 6.93s | 40 tps | 1.0M | $1.50 / $3.14 | |
Venicevenice | Healthy | 100%◆ (best) | 97.00% | 98.46% | 96.15% | 1.38s | 14.5s | 65 tps | 1.0M | $1.65 / $3.30 |
| Healthy | 99.94% | 98.59% | 99.13% | 98.82% | 2.90s | 23.7s | 33 tps | 1.0M | $0.209 / $0.418 | |
| Healthy | 99.94% | 99.90% | 99.25% | 99.29% | 983ms | 7.31s | 82 tps◆ (best) | 1.0M | $0.207 / $4.20◆ (best) | |
| Healthy | 98.98% | 97.95% | 98.97% | 99.37% | 667ms◆ (best) | 23.5s | 58 tps | 1.0M | $0.450 / $3.48 | |
| Healthy | 98.85% | 87.32% | 96.23% | 98.65% | 1.80s | 3.65s◆ (best) | 51 tps | 1.0M | $1.42 / $2.83 | |
| Healthy | 98.51% | 95.90% | 98.92% | 98.80% | 3.66s | 32.7s | 25 tps | 1.0M | $0.957 / $1.91 | |
| Healthy | 97.37% | 98.92% | 98.92% | 98.66% | 1.43s | 13.7s | 38 tps | 1.0M | $1.68 / $3.38 | |
Azureazure/us | Healthy | 96.15% | 98.98% | 99.09% | 98.52% | 1.76s | 42.6s | 55 tps | 1.0M | $1.91 / $3.83 |
| No data | — | — | — | 99.33% | — | — | — | 1.0M | $1.74 / $3.48 | |
| No data | — | — | — | — | — | — | — | 1.0M | $1.15 / $2.55 | |
| No data | — | — | — | — | — | — | — | 1.0M | $1.74 / $3.48 | |
DeepSeekdeepseek | No data | — | — | — | — | — | — | — | 1.0M | $0.660 / $1.98 |
Fireworksfireworks | No data | — | — | — | 0.00% | — | — | — | 1.0M | $1.20 / $1.20 |
| No data | — | — | — | 99.90% | — | — | — | 1.0M | $1.13 / $2.26 | |
Togethertogether | No data | — | — | — | — | — | — | — | 512K | $1.74 / $3.48 |
- Baidu100%◆ (best)Healthy24h 99.95%
- 7d
- 99.18%
- 30d
- 99.30%
- p50
- 956ms
- p99
- 15.2s
- Throughput
- 59 tps
- Context
- 1.0M
- $/Mtok
- $1.69 / $3.38
baidu/fp8fp8 - Cloudflare100%◆ (best)Healthy24h 98.19%
- 7d
- 97.84%
- 30d
- 95.61%
- p50
- 1.62s
- p99
- 24.4s
- Throughput
- 36 tps
- Context
- 1.0M
- $/Mtok
- $1.15 / $2.55
cloudflare - DeepInfra100%◆ (best)Healthy24h 99.76%
- 7d
- 99.73%
- 30d
- 99.41%
- p50
- 1.16s
- p99
- 8.80s
- Throughput
- 50 tps
- Context
- 1.0M
- $/Mtok
- $1.30 / $2.60
deepinfra/fp8fp8 - DigitalOcean100%◆ (best)Healthy24h 99.58%
- 7d
- 99.63%
- 30d
- 99.25%
- p50
- 1.67s
- p99
- 35.6s
- Throughput
- 32 tps
- Context
- 1.0M
- $/Mtok
- $1.04 / $2.09
digitalocean - NextBit100%◆ (best)Healthy24h 99.11%
- 7d
- 98.49%
- 30d
- 98.75%
- p50
- 4.23s
- p99
- 9.66s
- Throughput
- 46 tps
- Context
- 1.0M
- $/Mtok
- $1.74 / $3.48
nextbit/fp8fp8 - Novita100%◆ (best)Healthy24h 99.93%
- 7d
- 99.95%◆ (best)
- 30d
- 99.91%◆ (best)
- p50
- 2.01s
- p99
- 27.3s
- Throughput
- 62 tps
- Context
- 1.0M
- $/Mtok
- $1.60 / $3.20
novita/fp8fp8 - Reka100%◆ (best)Healthy24h 99.45%
- 7d
- 95.68%
- 30d
- 95.68%
- p50
- 1.13s
- p99
- 15.3s
- Throughput
- 29 tps
- Context
- 1.0M
- $/Mtok
- $0.900 / $9.00
reka - SiliconFlow100%◆ (best)Healthy24h 99.11%
- 7d
- 99.48%
- 30d
- 98.52%
- p50
- 1.45s
- p99
- 6.93s
- Throughput
- 40 tps
- Context
- 1.0M
- $/Mtok
- $1.50 / $3.14
siliconflow/fp8fp8 - Venice100%◆ (best)Healthy24h 97.00%
- 7d
- 98.46%
- 30d
- 96.15%
- p50
- 1.38s
- p99
- 14.5s
- Throughput
- 65 tps
- Context
- 1.0M
- $/Mtok
- $1.65 / $3.30
venice - StreamLake99.94%Healthy24h 98.59%
- 7d
- 99.13%
- 30d
- 98.82%
- p50
- 2.90s
- p99
- 23.7s
- Throughput
- 33 tps
- Context
- 1.0M
- $/Mtok
- $0.209 / $0.418
streamlake/fp8fp8 - Relace99.94%Healthy24h 99.90%
- 7d
- 99.25%
- 30d
- 99.29%
- p50
- 983ms
- p99
- 7.31s
- Throughput
- 82 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $0.207 / $4.20◆ (best)
relace/fp4fp4 - Parasail98.98%Healthy24h 97.95%
- 7d
- 98.97%
- 30d
- 99.37%
- p50
- 667ms◆ (best)
- p99
- 23.5s
- Throughput
- 58 tps
- Context
- 1.0M
- $/Mtok
- $0.450 / $3.48
parasail/fp8fp8 - Alibaba98.85%Healthy24h 87.32%
- 7d
- 96.23%
- 30d
- 98.65%
- p50
- 1.80s
- p99
- 3.65s◆ (best)
- Throughput
- 51 tps
- Context
- 1.0M
- $/Mtok
- $1.42 / $2.83
alibaba/fp8fp8 - GMICloud98.51%Healthy24h 95.90%
- 7d
- 98.92%
- 30d
- 98.80%
- p50
- 3.66s
- p99
- 32.7s
- Throughput
- 25 tps
- Context
- 1.0M
- $/Mtok
- $0.957 / $1.91
gmicloud/fp8fp8 - AtlasCloud97.37%Healthy24h 98.92%
- 7d
- 98.92%
- 30d
- 98.66%
- p50
- 1.43s
- p99
- 13.7s
- Throughput
- 38 tps
- Context
- 1.0M
- $/Mtok
- $1.68 / $3.38
atlas-cloud/fp4fp4 - Azure96.15%Healthy24h 98.98%
- 7d
- 99.09%
- 30d
- 98.52%
- p50
- 1.76s
- p99
- 42.6s
- Throughput
- 55 tps
- Context
- 1.0M
- $/Mtok
- $1.91 / $3.83
azure/us - No data24h —
- 7d
- —
- 30d
- 99.33%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $1.74 / $3.48
baseten/fp4fp4 - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $1.15 / $2.55
coreweave/fp8fp8 - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $1.74 / $3.48
crusoe/fp8fp8 - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.660 / $1.98
deepseek - No data24h —
- 7d
- —
- 30d
- 0.00%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $1.20 / $1.20
fireworks - No data24h —
- 7d
- —
- 30d
- 99.90%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $1.13 / $2.26
ionstream/fp4fp4 - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 512K
- $/Mtok
- $1.74 / $3.48
together
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.
Throughput
Median tokens per second.