DeepSeek V3.2
deepseek/deepseek-v3.2
Compare with DeepSeek V3, DeepSeek V3.2 Exp, DeepSeek V3.1
CompareDeepSeek V3.2
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 99.95% | 99.96% | 99.96% | 1.56s | 7.85s | 20 tps | 164K | $0.260 / $0.380 | |
| Healthy | 100% | 99.90% | 99.94% | 99.94% | 1.89s | 14.2s | 26 tps | 131K | $0.280 / $0.420 | |
DigitalOceandigitalocean | Healthy | 100% | 96.99% | 97.21% | 97.21% | 1.66s | 14.2s | 12 tps | 164K | $0.250 / $0.800 |
Friendlifriendli | Healthy | 100% | 99.89% | 91.36% | 91.36% | 564ms | 8.31s | 33 tps | 164K | $0.500 / $1.50 |
Googlegoogle-vertex | Healthy | 100% | 99.45% | 99.68% | 99.68% | 1.11s | 7.43s | 20 tps | 164K | $0.560 / $1.68 |
| Healthy | 100% | 99.98% | 99.99% | 99.99% | 1.19s | 5.31s | 26 tps | 164K | $0.269 / $0.400 | |
| Healthy | 99.56% | 99.47% | 99.54% | 99.54% | 2.03s | 24.1s | 26 tps | 164K | $0.209 / $0.310 | |
| Healthy | 99.33% | 99.15% | 99.67% | 99.67% | 1.47s | 12.1s | 25 tps | 128K | $0.214 / $0.322 | |
| Healthy | 98.57% | 98.84% | 99.50% | 99.50% | 1.87s | 9.26s | 23 tps | 164K | $0.259 / $0.420 | |
| Degraded | 95.45% | 97.99% | 94.31% | 94.31% | 1.43s | 33.1s | 12 tps | 164K | $0.260 / $0.380 | |
| Healthy | 95.07% | 97.97% | 98.41% | 98.41% | 906ms | 12.3s | 55 tps | 131K | $0.370 / $1.11 | |
Venicevenice | Down | 89.83% | 82.18% | 75.24% | 75.24% | 1.56s | 21.8s | 13 tps | 160K | $0.330 / $0.480 |
Phalaphala | No data | — | 98.58% | 99.06% | 99.06% | 3.00s | 350s | 6.0 tps | 164K | $1.00 / $1.00 |
SambaNovasambanova | No data | — | 94.70% | 97.00% | 97.00% | 2.28s | 25.1s | 20 tps | 33K | $3.00 / $4.50 |
- AtlasCloud100%Healthy24h 99.95%
- 7d
- 99.96%
- 30d
- 99.96%
- p50
- 1.56s
- p99
- 7.85s
- Throughput
- 20 tps
- Context
- 164K
- $/Mtok
- $0.260 / $0.380
atlas-cloud/fp8fp8 - Baidu100%Healthy24h 99.90%
- 7d
- 99.94%
- 30d
- 99.94%
- p50
- 1.89s
- p99
- 14.2s
- Throughput
- 26 tps
- Context
- 131K
- $/Mtok
- $0.280 / $0.420
baidu/fp8fp8 - DigitalOcean100%Healthy24h 96.99%
- 7d
- 97.21%
- 30d
- 97.21%
- p50
- 1.66s
- p99
- 14.2s
- Throughput
- 12 tps
- Context
- 164K
- $/Mtok
- $0.250 / $0.800
digitalocean - Friendli100%Healthy24h 99.89%
- 7d
- 91.36%
- 30d
- 91.36%
- p50
- 564ms
- p99
- 8.31s
- Throughput
- 33 tps
- Context
- 164K
- $/Mtok
- $0.500 / $1.50
friendli - Google100%Healthy24h 99.45%
- 7d
- 99.68%
- 30d
- 99.68%
- p50
- 1.11s
- p99
- 7.43s
- Throughput
- 20 tps
- Context
- 164K
- $/Mtok
- $0.560 / $1.68
google-vertex - Novita100%Healthy24h 99.98%
- 7d
- 99.99%
- 30d
- 99.99%
- p50
- 1.19s
- p99
- 5.31s
- Throughput
- 26 tps
- Context
- 164K
- $/Mtok
- $0.269 / $0.400
novita/fp8fp8 - GMICloud99.56%Healthy24h 99.47%
- 7d
- 99.54%
- 30d
- 99.54%
- p50
- 2.03s
- p99
- 24.1s
- Throughput
- 26 tps
- Context
- 164K
- $/Mtok
- $0.209 / $0.310
gmicloud/fp8fp8 - StreamLake99.33%Healthy24h 99.15%
- 7d
- 99.67%
- 30d
- 99.67%
- p50
- 1.47s
- p99
- 12.1s
- Throughput
- 25 tps
- Context
- 128K
- $/Mtok
- $0.214 / $0.322
streamlake/fp8fp8 - SiliconFlow98.57%Healthy24h 98.84%
- 7d
- 99.50%
- 30d
- 99.50%
- p50
- 1.87s
- p99
- 9.26s
- Throughput
- 23 tps
- Context
- 164K
- $/Mtok
- $0.259 / $0.420
siliconflow/fp8fp8 - DeepInfra95.45%Degraded24h 97.99%
- 7d
- 94.31%
- 30d
- 94.31%
- p50
- 1.43s
- p99
- 33.1s
- Throughput
- 12 tps
- Context
- 164K
- $/Mtok
- $0.260 / $0.380
deepinfra/fp4fp4 - Alibaba95.07%Healthy24h 97.97%
- 7d
- 98.41%
- 30d
- 98.41%
- p50
- 906ms
- p99
- 12.3s
- Throughput
- 55 tps
- Context
- 131K
- $/Mtok
- $0.370 / $1.11
alibaba/fp8fp8 - Venice89.83%Down24h 82.18%
- 7d
- 75.24%
- 30d
- 75.24%
- p50
- 1.56s
- p99
- 21.8s
- Throughput
- 13 tps
- Context
- 160K
- $/Mtok
- $0.330 / $0.480
venice - No data24h 98.58%
- 7d
- 99.06%
- 30d
- 99.06%
- p50
- 3.00s
- p99
- 350s
- Throughput
- 6.0 tps
- Context
- 164K
- $/Mtok
- $1.00 / $1.00
phala - No data24h 94.70%
- 7d
- 97.00%
- 30d
- 97.00%
- p50
- 2.28s
- p99
- 25.1s
- Throughput
- 20 tps
- Context
- 33K
- $/Mtok
- $3.00 / $4.50
sambanova
Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
2 endpoints reporting no data are omitted from the charts.
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.