DeepSeek V3.2
deepseek/deepseek-v3.2
Compare with DeepSeek V4 Flash 0731, DeepSeek V4 Flash 0423, DeepSeek V4 Pro 0423
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Baidubaidu/fp8fp8 | Healthy | 100% | 99.92% | 1000ms | 4.50s | 45 tps | 131K | $0.280 / $0.420 |
DigitalOceandigitalocean | Healthy | 100% | 96.16% | 1.36s | 13.6s | 20 tps | 164K | $0.250 / $0.800 |
Googlegoogle-vertex | Healthy | 100% | 99.69% | 1.46s | 9.15s | 9.0 tps | 164K | $0.560 / $1.68 |
Phalaphala | Healthy | 100% | 99.47% | 4.38s | 13.0s | 7.0 tps | 164K | $1.00 / $1.00 |
StreamLakestreamlake/fp8fp8 | Healthy | 100% | 99.87% | 1.39s | 10.1s | 24 tps | 128K | $0.214 / $0.322 |
Novitanovita/fp8fp8 | Healthy | 99.98% | 99.99% | 1.36s | 5.61s | 23 tps | 164K | $0.269 / $0.400 |
AtlasCloudatlas-cloud/fp8fp8 | Healthy | 99.95% | 99.92% | 1.40s | 9.74s | 20 tps | 164K | $0.260 / $0.380 |
SiliconFlowsiliconflow/fp8fp8 | Healthy | 99.89% | 99.78% | 1.94s | 15.1s | 23 tps | 164K | $0.259 / $0.420 |
GMICloudgmicloud/fp8fp8 | Degraded | 95.89% | 98.53% | 2.25s | 15.6s | 23 tps | 164K | $0.209 / $0.310 |
Alibabaalibaba/fp8fp8 | Healthy | 95.59% | 98.25% | 1000ms | 11.9s | 48 tps | 131K | $0.370 / $1.11 |
Friendlifriendli | Down | 0.00% | 97.30% | — | — | — | 164K | $0.500 / $1.50 |
DeepInfradeepinfra/fp4fp4 | No data | — | 95.92% | 9.30s | 41.7s | 8.0 tps | 164K | $0.260 / $0.380 |
SambaNovasambanova | No data | — | 86.52% | 12.1s | 17.1s | 24 tps | 33K | $3.00 / $4.50 |
Venicevenice | No data | — | 92.21% | 9.64s | 17.6s | 6.0 tps | 160K | $0.330 / $0.480 |
- Baidu100%Healthy24h 99.92%
- p50
- 1000ms
- p99
- 4.50s
- Throughput
- 45 tps
- Context
- 131K
- $/Mtok
- $0.280 / $0.420
baidu/fp8fp8 - DigitalOcean100%Healthy24h 96.16%
- p50
- 1.36s
- p99
- 13.6s
- Throughput
- 20 tps
- Context
- 164K
- $/Mtok
- $0.250 / $0.800
digitalocean - Google100%Healthy24h 99.69%
- p50
- 1.46s
- p99
- 9.15s
- Throughput
- 9.0 tps
- Context
- 164K
- $/Mtok
- $0.560 / $1.68
google-vertex - Phala100%Healthy24h 99.47%
- p50
- 4.38s
- p99
- 13.0s
- Throughput
- 7.0 tps
- Context
- 164K
- $/Mtok
- $1.00 / $1.00
phala - StreamLake100%Healthy24h 99.87%
- p50
- 1.39s
- p99
- 10.1s
- Throughput
- 24 tps
- Context
- 128K
- $/Mtok
- $0.214 / $0.322
streamlake/fp8fp8 - Novita99.98%Healthy24h 99.99%
- p50
- 1.36s
- p99
- 5.61s
- Throughput
- 23 tps
- Context
- 164K
- $/Mtok
- $0.269 / $0.400
novita/fp8fp8 - AtlasCloud99.95%Healthy24h 99.92%
- p50
- 1.40s
- p99
- 9.74s
- Throughput
- 20 tps
- Context
- 164K
- $/Mtok
- $0.260 / $0.380
atlas-cloud/fp8fp8 - SiliconFlow99.89%Healthy24h 99.78%
- p50
- 1.94s
- p99
- 15.1s
- Throughput
- 23 tps
- Context
- 164K
- $/Mtok
- $0.259 / $0.420
siliconflow/fp8fp8 - GMICloud95.89%Degraded24h 98.53%
- p50
- 2.25s
- p99
- 15.6s
- Throughput
- 23 tps
- Context
- 164K
- $/Mtok
- $0.209 / $0.310
gmicloud/fp8fp8 - Alibaba95.59%Healthy24h 98.25%
- p50
- 1000ms
- p99
- 11.9s
- Throughput
- 48 tps
- Context
- 131K
- $/Mtok
- $0.370 / $1.11
alibaba/fp8fp8 - Friendli0.00%Down24h 97.30%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 164K
- $/Mtok
- $0.500 / $1.50
friendli - DeepInfra—No data24h 95.92%
- p50
- 9.30s
- p99
- 41.7s
- Throughput
- 8.0 tps
- Context
- 164K
- $/Mtok
- $0.260 / $0.380
deepinfra/fp4fp4 - SambaNova—No data24h 86.52%
- p50
- 12.1s
- p99
- 17.1s
- Throughput
- 24 tps
- Context
- 33K
- $/Mtok
- $3.00 / $4.50
sambanova - Venice—No data24h 92.21%
- p50
- 9.64s
- p99
- 17.6s
- Throughput
- 6.0 tps
- Context
- 160K
- $/Mtok
- $0.330 / $0.480
venice
Measured 1m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
3 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.