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% | 1.06s | 4.71s | 41 tps | 131K | $0.280 / $0.420 |
Googlegoogle-vertex | Healthy | 100% | 99.69% | 1.08s | 7.11s | 10 tps | 164K | $0.560 / $1.68 |
Phalaphala | Healthy | 100% | 99.46% | 4.18s | 12.1s | 7.0 tps | 164K | $1.00 / $1.00 |
Novitanovita/fp8fp8 | Healthy | 99.93% | 99.99% | 1.41s | 5.88s | 22 tps | 164K | $0.269 / $0.400 |
StreamLakestreamlake/fp8fp8 | Healthy | 99.90% | 99.87% | 1.35s | 10.7s | 24 tps | 128K | $0.214 / $0.322 |
AtlasCloudatlas-cloud/fp8fp8 | Healthy | 99.88% | 99.92% | 1.41s | 9.49s | 18 tps | 164K | $0.260 / $0.380 |
SiliconFlowsiliconflow/fp8fp8 | Healthy | 99.71% | 99.78% | 1.83s | 10.8s | 21 tps | 164K | $0.259 / $0.420 |
DigitalOceandigitalocean | Healthy | 99.33% | 95.93% | 864ms | 7.61s | 44 tps | 164K | $0.250 / $0.800 |
Alibabaalibaba/fp8fp8 | Healthy | 97.45% | 98.25% | 869ms | 10.9s | 52 tps | 131K | $0.370 / $1.11 |
GMICloudgmicloud/fp8fp8 | Down | 89.15% | 98.50% | 2.15s | 11.1s | 19 tps | 164K | $0.209 / $0.310 |
Friendlifriendli | Down | 0.00% | 96.42% | — | — | — | 164K | $0.500 / $1.50 |
DeepInfradeepinfra/fp4fp4 | Degraded | — | 95.99% | 8.64s | 30.4s | 7.0 tps | 164K | $0.260 / $0.380 |
SambaNovasambanova | No data | — | 86.63% | 5.48s | 16.1s | 10 tps | 33K | $3.00 / $4.50 |
Venicevenice | No data | — | 92.31% | 6.31s | 11.8s | 4.0 tps | 160K | $0.330 / $0.480 |
- Baidu100%Healthy24h 99.92%
- p50
- 1.06s
- p99
- 4.71s
- Throughput
- 41 tps
- Context
- 131K
- $/Mtok
- $0.280 / $0.420
baidu/fp8fp8 - Google100%Healthy24h 99.69%
- p50
- 1.08s
- p99
- 7.11s
- Throughput
- 10 tps
- Context
- 164K
- $/Mtok
- $0.560 / $1.68
google-vertex - Phala100%Healthy24h 99.46%
- p50
- 4.18s
- p99
- 12.1s
- Throughput
- 7.0 tps
- Context
- 164K
- $/Mtok
- $1.00 / $1.00
phala - Novita99.93%Healthy24h 99.99%
- p50
- 1.41s
- p99
- 5.88s
- Throughput
- 22 tps
- Context
- 164K
- $/Mtok
- $0.269 / $0.400
novita/fp8fp8 - StreamLake99.90%Healthy24h 99.87%
- p50
- 1.35s
- p99
- 10.7s
- Throughput
- 24 tps
- Context
- 128K
- $/Mtok
- $0.214 / $0.322
streamlake/fp8fp8 - AtlasCloud99.88%Healthy24h 99.92%
- p50
- 1.41s
- p99
- 9.49s
- Throughput
- 18 tps
- Context
- 164K
- $/Mtok
- $0.260 / $0.380
atlas-cloud/fp8fp8 - SiliconFlow99.71%Healthy24h 99.78%
- p50
- 1.83s
- p99
- 10.8s
- Throughput
- 21 tps
- Context
- 164K
- $/Mtok
- $0.259 / $0.420
siliconflow/fp8fp8 - DigitalOcean99.33%Healthy24h 95.93%
- p50
- 864ms
- p99
- 7.61s
- Throughput
- 44 tps
- Context
- 164K
- $/Mtok
- $0.250 / $0.800
digitalocean - Alibaba97.45%Healthy24h 98.25%
- p50
- 869ms
- p99
- 10.9s
- Throughput
- 52 tps
- Context
- 131K
- $/Mtok
- $0.370 / $1.11
alibaba/fp8fp8 - GMICloud89.15%Down24h 98.50%
- p50
- 2.15s
- p99
- 11.1s
- Throughput
- 19 tps
- Context
- 164K
- $/Mtok
- $0.209 / $0.310
gmicloud/fp8fp8 - Friendli0.00%Down24h 96.42%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 164K
- $/Mtok
- $0.500 / $1.50
friendli - DeepInfra—Degraded24h 95.99%
- p50
- 8.64s
- p99
- 30.4s
- Throughput
- 7.0 tps
- Context
- 164K
- $/Mtok
- $0.260 / $0.380
deepinfra/fp4fp4 - SambaNova—No data24h 86.63%
- p50
- 5.48s
- p99
- 16.1s
- Throughput
- 10 tps
- Context
- 33K
- $/Mtok
- $3.00 / $4.50
sambanova - Venice—No data24h 92.31%
- p50
- 6.31s
- p99
- 11.8s
- Throughput
- 4.0 tps
- Context
- 160K
- $/Mtok
- $0.330 / $0.480
venice
Measured 3m 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.
Throughput
Median tokens per second.