DeepSeek V3.2
deepseek/deepseek-v3.2
Compare with DeepSeek V3, DeepSeek V3.2 Exp, DeepSeek V3.1
CompareDeepSeek V3.2
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 99.90% | 99.94% | 99.94% | 1.64s | 14.1s | 28 tps | 131K | $0.280 / $0.420 | |
Friendlifriendli | Healthy | 100% | 99.89% | 91.20% | 91.20% | 413ms | 7.15s | 44 tps | 164K | $0.500 / $1.50 |
Googlegoogle-vertex | Healthy | 100% | 99.45% | 99.67% | 99.67% | 1.23s | 12.5s | 26 tps | 164K | $0.560 / $1.68 |
| Healthy | 100% | 99.98% | 99.99% | 99.99% | 1.30s | 5.89s | 25 tps | 164K | $0.269 / $0.400 | |
| Healthy | 99.99% | 99.95% | 99.96% | 99.96% | 1.60s | 8.58s | 22 tps | 164K | $0.260 / $0.380 | |
| Healthy | 99.31% | 98.01% | 98.43% | 98.43% | 1.03s | 12.3s | 52 tps | 131K | $0.370 / $1.11 | |
| Healthy | 99.16% | 99.49% | 99.54% | 99.54% | 2.06s | 24.7s | 27 tps | 164K | $0.209 / $0.310 | |
| Degraded | 90.85% | 99.26% | 99.76% | 99.76% | 1.52s | 16.5s | 27 tps | 128K | $0.214 / $0.322 | |
| Down | 86.47% | 98.94% | 99.62% | 99.62% | 2.09s | 18.3s | 25 tps | 164K | $0.259 / $0.420 | |
DigitalOceandigitalocean | Down | 86.34% | 96.98% | 97.21% | 97.21% | 1.12s | 10.1s | 33 tps | 164K | $0.250 / $0.800 |
| No data | — | 97.69% | 94.36% | 94.36% | 1.59s | 61.4s | 13 tps | 164K | $0.260 / $0.380 | |
Phalaphala | No data | — | 98.58% | 99.06% | 99.06% | 2.80s | 427s | 6.0 tps | 164K | $1.00 / $1.00 |
SambaNovasambanova | No data | — | 94.35% | 96.81% | 96.81% | 7.52s | 7.86s | 111 tps | 33K | $3.00 / $4.50 |
Venicevenice | Down | — | 82.03% | 75.96% | 75.96% | 1.07s | 70.5s | 16 tps | 160K | $0.330 / $0.480 |
- Baidu100%Healthy24h 99.90%
- 7d
- 99.94%
- 30d
- 99.94%
- p50
- 1.64s
- p99
- 14.1s
- Throughput
- 28 tps
- Context
- 131K
- $/Mtok
- $0.280 / $0.420
baidu/fp8fp8 - Friendli100%Healthy24h 99.89%
- 7d
- 91.20%
- 30d
- 91.20%
- p50
- 413ms
- p99
- 7.15s
- Throughput
- 44 tps
- Context
- 164K
- $/Mtok
- $0.500 / $1.50
friendli - Google100%Healthy24h 99.45%
- 7d
- 99.67%
- 30d
- 99.67%
- p50
- 1.23s
- p99
- 12.5s
- Throughput
- 26 tps
- Context
- 164K
- $/Mtok
- $0.560 / $1.68
google-vertex - Novita100%Healthy24h 99.98%
- 7d
- 99.99%
- 30d
- 99.99%
- p50
- 1.30s
- p99
- 5.89s
- Throughput
- 25 tps
- Context
- 164K
- $/Mtok
- $0.269 / $0.400
novita/fp8fp8 - AtlasCloud99.99%Healthy24h 99.95%
- 7d
- 99.96%
- 30d
- 99.96%
- p50
- 1.60s
- p99
- 8.58s
- Throughput
- 22 tps
- Context
- 164K
- $/Mtok
- $0.260 / $0.380
atlas-cloud/fp8fp8 - Alibaba99.31%Healthy24h 98.01%
- 7d
- 98.43%
- 30d
- 98.43%
- p50
- 1.03s
- p99
- 12.3s
- Throughput
- 52 tps
- Context
- 131K
- $/Mtok
- $0.370 / $1.11
alibaba/fp8fp8 - GMICloud99.16%Healthy24h 99.49%
- 7d
- 99.54%
- 30d
- 99.54%
- p50
- 2.06s
- p99
- 24.7s
- Throughput
- 27 tps
- Context
- 164K
- $/Mtok
- $0.209 / $0.310
gmicloud/fp8fp8 - StreamLake90.85%Degraded24h 99.26%
- 7d
- 99.76%
- 30d
- 99.76%
- p50
- 1.52s
- p99
- 16.5s
- Throughput
- 27 tps
- Context
- 128K
- $/Mtok
- $0.214 / $0.322
streamlake/fp8fp8 - SiliconFlow86.47%Down24h 98.94%
- 7d
- 99.62%
- 30d
- 99.62%
- p50
- 2.09s
- p99
- 18.3s
- Throughput
- 25 tps
- Context
- 164K
- $/Mtok
- $0.259 / $0.420
siliconflow/fp8fp8 - DigitalOcean86.34%Down24h 96.98%
- 7d
- 97.21%
- 30d
- 97.21%
- p50
- 1.12s
- p99
- 10.1s
- Throughput
- 33 tps
- Context
- 164K
- $/Mtok
- $0.250 / $0.800
digitalocean - No data24h 97.69%
- 7d
- 94.36%
- 30d
- 94.36%
- p50
- 1.59s
- p99
- 61.4s
- Throughput
- 13 tps
- Context
- 164K
- $/Mtok
- $0.260 / $0.380
deepinfra/fp4fp4 - No data24h 98.58%
- 7d
- 99.06%
- 30d
- 99.06%
- p50
- 2.80s
- p99
- 427s
- Throughput
- 6.0 tps
- Context
- 164K
- $/Mtok
- $1.00 / $1.00
phala - No data24h 94.35%
- 7d
- 96.81%
- 30d
- 96.81%
- p50
- 7.52s
- p99
- 7.86s
- Throughput
- 111 tps
- Context
- 33K
- $/Mtok
- $3.00 / $4.50
sambanova - Down24h 82.03%
- 7d
- 75.96%
- 30d
- 75.96%
- p50
- 1.07s
- p99
- 70.5s
- Throughput
- 16 tps
- Context
- 160K
- $/Mtok
- $0.330 / $0.480
venice
Measured 2m 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 is OpenRouter's rolling 30-minute window.
Throughput
Median tokens per second.