DeepSeek V3.2
deepseek/deepseek-v3.2
Compare with DeepSeek V3, DeepSeek V3.2 Exp, DeepSeek V3.1
CompareDeepSeek V3.2
| State | ||||||||
|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 97.55% | 692ms | 11.6s | 51 tps | 131K | $0.370 / $1.11 | |
| Healthy | 100% | 99.90% | 860ms | 2.50s | 48 tps | 131K | $0.280 / $0.420 | |
Friendlifriendli | Healthy | 100% | 99.88% | 303ms | 6.42s | 48 tps | 164K | $0.500 / $1.50 |
| Healthy | 100% | 99.44% | 2.11s | 8.68s | 25 tps | 164K | $0.209 / $0.310 | |
| Healthy | 100% | 99.98% | 1.21s | 5.44s | 28 tps | 164K | $0.269 / $0.400 | |
| Healthy | 100% | 99.72% | 2.10s | 8.95s | 26 tps | 164K | $0.259 / $0.420 | |
| Healthy | 100% | 99.87% | 1.45s | 7.61s | 27 tps | 128K | $0.214 / $0.322 | |
| Healthy | 99.99% | 99.95% | 1.52s | 9.34s | 24 tps | 164K | $0.260 / $0.380 | |
Googlegoogle-vertex | Healthy | 98.61% | 99.62% | 2.35s | 9.77s | 9.0 tps | 164K | $0.560 / $1.68 |
Phalaphala | Healthy | 96.88% | 99.12% | 2.95s | 218s | 7.0 tps | 164K | $1.00 / $1.00 |
DigitalOceandigitalocean | Down | 88.68% | 96.08% | 1.21s | 15.6s | 15 tps | 164K | $0.250 / $0.800 |
| No data | — | 95.22% | 3.07s | 37.9s | 8.0 tps | 164K | $0.260 / $0.380 | |
SambaNovasambanova | No data | — | 91.10% | — | — | — | 33K | $3.00 / $4.50 |
Venicevenice | Down | — | 77.18% | 2.24s | 188s | 7.0 tps | 160K | $0.330 / $0.480 |
- Alibaba100%Healthy24h 97.55%
- p50
- 692ms
- p99
- 11.6s
- Throughput
- 51 tps
- Context
- 131K
- $/Mtok
- $0.370 / $1.11
alibaba/fp8fp8 - Baidu100%Healthy24h 99.90%
- p50
- 860ms
- p99
- 2.50s
- Throughput
- 48 tps
- Context
- 131K
- $/Mtok
- $0.280 / $0.420
baidu/fp8fp8 - Friendli100%Healthy24h 99.88%
- p50
- 303ms
- p99
- 6.42s
- Throughput
- 48 tps
- Context
- 164K
- $/Mtok
- $0.500 / $1.50
friendli - GMICloud100%Healthy24h 99.44%
- p50
- 2.11s
- p99
- 8.68s
- Throughput
- 25 tps
- Context
- 164K
- $/Mtok
- $0.209 / $0.310
gmicloud/fp8fp8 - Novita100%Healthy24h 99.98%
- p50
- 1.21s
- p99
- 5.44s
- Throughput
- 28 tps
- Context
- 164K
- $/Mtok
- $0.269 / $0.400
novita/fp8fp8 - SiliconFlow100%Healthy24h 99.72%
- p50
- 2.10s
- p99
- 8.95s
- Throughput
- 26 tps
- Context
- 164K
- $/Mtok
- $0.259 / $0.420
siliconflow/fp8fp8 - StreamLake100%Healthy24h 99.87%
- p50
- 1.45s
- p99
- 7.61s
- Throughput
- 27 tps
- Context
- 128K
- $/Mtok
- $0.214 / $0.322
streamlake/fp8fp8 - AtlasCloud99.99%Healthy24h 99.95%
- p50
- 1.52s
- p99
- 9.34s
- Throughput
- 24 tps
- Context
- 164K
- $/Mtok
- $0.260 / $0.380
atlas-cloud/fp8fp8 - Google98.61%Healthy24h 99.62%
- p50
- 2.35s
- p99
- 9.77s
- Throughput
- 9.0 tps
- Context
- 164K
- $/Mtok
- $0.560 / $1.68
google-vertex - Phala96.88%Healthy24h 99.12%
- p50
- 2.95s
- p99
- 218s
- Throughput
- 7.0 tps
- Context
- 164K
- $/Mtok
- $1.00 / $1.00
phala - DigitalOcean88.68%Down24h 96.08%
- p50
- 1.21s
- p99
- 15.6s
- Throughput
- 15 tps
- Context
- 164K
- $/Mtok
- $0.250 / $0.800
digitalocean - No data24h 95.22%
- p50
- 3.07s
- p99
- 37.9s
- Throughput
- 8.0 tps
- Context
- 164K
- $/Mtok
- $0.260 / $0.380
deepinfra/fp4fp4 - No data24h 91.10%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 33K
- $/Mtok
- $3.00 / $4.50
sambanova - Down24h 77.18%
- p50
- 2.24s
- p99
- 188s
- Throughput
- 7.0 tps
- Context
- 160K
- $/Mtok
- $0.330 / $0.480
venice
Measured 1m 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.