DeepSeek V3.2
deepseek/deepseek-v3.2
Compare with DeepSeek V3, DeepSeek V3.2 Exp, DeepSeek V3.1
CompareDeepSeek V3.2
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Baidubaidu/fp8fp8 | Healthy | 100% | 99.92% | 1.02s | 4.15s | 45 tps | 131K | $0.280 / $0.420 |
DeepInfradeepinfra/fp4fp4 | Healthy | 100% | 96.53% | 1.16s | 10.6s | 9.0 tps | 164K | $0.260 / $0.380 |
DigitalOceandigitalocean | Healthy | 100% | 95.54% | 1.25s | 14.6s | 11 tps | 164K | $0.250 / $0.800 |
Friendlifriendli | Healthy | 100% | 95.82% | 589ms | 6.89s | 42 tps | 164K | $0.500 / $1.50 |
Googlegoogle-vertex | Healthy | 100% | 99.69% | 1.39s | 8.55s | 11 tps | 164K | $0.560 / $1.68 |
Novitanovita/fp8fp8 | Healthy | 100% | 99.99% | 1.28s | 5.98s | 24 tps | 164K | $0.269 / $0.400 |
Phalaphala | Healthy | 100% | 99.53% | 4.69s | 13.1s | 6.0 tps | 164K | $1.00 / $1.00 |
StreamLakestreamlake/fp8fp8 | Healthy | 99.96% | 99.87% | 1.43s | 8.92s | 26 tps | 128K | $0.214 / $0.322 |
AtlasCloudatlas-cloud/fp8fp8 | Healthy | 99.96% | 99.92% | 1.54s | 8.72s | 20 tps | 164K | $0.260 / $0.380 |
GMICloudgmicloud/fp8fp8 | Healthy | 99.94% | 98.33% | 2.27s | 6.80s | 33 tps | 164K | $0.209 / $0.310 |
SiliconFlowsiliconflow/fp8fp8 | Healthy | 99.83% | 99.78% | 2.09s | 8.43s | 25 tps | 164K | $0.259 / $0.420 |
Alibabaalibaba/fp8fp8 | Healthy | 99.42% | 98.21% | 745ms | 12.2s | 51 tps | 131K | $0.370 / $1.11 |
SambaNovasambanova | No data | — | 84.46% | 3.99s | 15.8s | 30 tps | 33K | $3.00 / $4.50 |
Venicevenice | No data | — | 92.66% | 1.35s | 20.3s | 6.5 tps | 160K | $0.330 / $0.480 |
- Baidu100%Healthy24h 99.92%
- p50
- 1.02s
- p99
- 4.15s
- Throughput
- 45 tps
- Context
- 131K
- $/Mtok
- $0.280 / $0.420
baidu/fp8fp8 - DeepInfra100%Healthy24h 96.53%
- p50
- 1.16s
- p99
- 10.6s
- Throughput
- 9.0 tps
- Context
- 164K
- $/Mtok
- $0.260 / $0.380
deepinfra/fp4fp4 - DigitalOcean100%Healthy24h 95.54%
- p50
- 1.25s
- p99
- 14.6s
- Throughput
- 11 tps
- Context
- 164K
- $/Mtok
- $0.250 / $0.800
digitalocean - Friendli100%Healthy24h 95.82%
- p50
- 589ms
- p99
- 6.89s
- Throughput
- 42 tps
- Context
- 164K
- $/Mtok
- $0.500 / $1.50
friendli - Google100%Healthy24h 99.69%
- p50
- 1.39s
- p99
- 8.55s
- Throughput
- 11 tps
- Context
- 164K
- $/Mtok
- $0.560 / $1.68
google-vertex - Novita100%Healthy24h 99.99%
- p50
- 1.28s
- p99
- 5.98s
- Throughput
- 24 tps
- Context
- 164K
- $/Mtok
- $0.269 / $0.400
novita/fp8fp8 - Phala100%Healthy24h 99.53%
- p50
- 4.69s
- p99
- 13.1s
- Throughput
- 6.0 tps
- Context
- 164K
- $/Mtok
- $1.00 / $1.00
phala - StreamLake99.96%Healthy24h 99.87%
- p50
- 1.43s
- p99
- 8.92s
- Throughput
- 26 tps
- Context
- 128K
- $/Mtok
- $0.214 / $0.322
streamlake/fp8fp8 - AtlasCloud99.96%Healthy24h 99.92%
- p50
- 1.54s
- p99
- 8.72s
- Throughput
- 20 tps
- Context
- 164K
- $/Mtok
- $0.260 / $0.380
atlas-cloud/fp8fp8 - GMICloud99.94%Healthy24h 98.33%
- p50
- 2.27s
- p99
- 6.80s
- Throughput
- 33 tps
- Context
- 164K
- $/Mtok
- $0.209 / $0.310
gmicloud/fp8fp8 - SiliconFlow99.83%Healthy24h 99.78%
- p50
- 2.09s
- p99
- 8.43s
- Throughput
- 25 tps
- Context
- 164K
- $/Mtok
- $0.259 / $0.420
siliconflow/fp8fp8 - Alibaba99.42%Healthy24h 98.21%
- p50
- 745ms
- p99
- 12.2s
- Throughput
- 51 tps
- Context
- 131K
- $/Mtok
- $0.370 / $1.11
alibaba/fp8fp8 - SambaNova—No data24h 84.46%
- p50
- 3.99s
- p99
- 15.8s
- Throughput
- 30 tps
- Context
- 33K
- $/Mtok
- $3.00 / $4.50
sambanova - Venice—No data24h 92.66%
- p50
- 1.35s
- p99
- 20.3s
- Throughput
- 6.5 tps
- Context
- 160K
- $/Mtok
- $0.330 / $0.480
venice
Measured 39s 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 and p99 are OpenRouter's rolling 30-minute windows, averaged over the hour.
Throughput
Median tokens per second.