Venice
32 endpoints · 6 unhealthy · worst uptime 52.99%
| State | ||||||||
|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 99.99% | 715ms | 6.22s | 29 tps | 128K | $0.200 / $0.900 | |
| Healthy | 100% | 99.82% | 1.43s | 12.3s | 98 tps | 524K | $0.300 / $1.20 | |
| Healthy | 100% | 99.96% | 621ms | 7.41s | 71 tps | 256K | $0.188 / $0.750 | |
Kimi K2.5venice | Healthy | 100% | 97.37% | 2.71s | 14.9s | 35 tps | 256K | $0.532 / $3.32 |
| Healthy | 100% | 97.72% | 2.20s | 7.19s | 13 tps | 256K | $0.750 / $3.50 | |
Qwen3.5-35B-A3Bvenice | Healthy | 100% | 99.94% | 703ms | 6.17s | 125 tps | 256K | $0.313 / $1.25 |
| Healthy | 100% | 99.97% | 1.05s | 13.3s | 73 tps | 256K | $0.100 / $0.150 | |
| Healthy | 100% | 94.24% | 712ms | 16.9s | 33 tps | 256K | $0.325 / $3.25 | |
| Healthy | 100% | 99.71% | 631ms | 1.61s | 147 tps | 256K | $0.098 / $0.950 | |
| Healthy | 100% | 99.27% | 1.36s | 6.18s | 109 tps | 262K | $0.450 / $3.20 | |
| Healthy | 100% | 99.36% | 1.27s | 7.10s | 15 tps | 198K | $0.430 / $1.75 | |
| Healthy | 100% | 99.64% | 614ms | 3.81s | 37 tps | 128K | $0.060 / $0.400 | |
| Healthy | 100% | 92.28% | 1.30s | 12.5s | 45 tps | 198K | $1.00 / $3.20 | |
| Healthy | 100% | 97.82% | 1.34s | 7.61s | 22 tps | 200K | $1.54 / $4.84 | |
| Healthy | 100% | 98.53% | 2.37s | 22.8s | 38 tps | 1.0M | $1.40 / $4.40 | |
DeepSeek V4 Flash 0423venice | Healthy | 99.90% | 99.77% | 1.61s | 4.60s | 35 tps | 1.0M | $0.138 / $0.275 |
| Healthy | 99.77% | 99.47% | 932ms | 6.92s | 20 tps | 256K | $0.130 / $0.400 | |
| Healthy | 99.65% | 99.82% | 1.14s | 15.1s | 31 tps | 256K | $0.120 / $0.360 | |
DeepSeek V4 Pro 0423venice | Healthy | 99.18% | 88.39% | 1.18s | 10.0s | 47 tps | 1.0M | $1.65 / $3.30 |
| Degraded | 98.54% | 97.83% | 1.06s | 12.0s | 8.0 tps | 128K | $0.150 / $0.750 | |
| Healthy | 98.52% | 96.07% | 1.54s | 6.40s | 20 tps | 128K | $0.210 / $1.90 | |
DeepSeek V4 Flash 0731venice | Healthy | 97.97% | 97.85% | 1.14s | 12.0s | 45 tps | 1.0M | $0.175 / $0.350 |
| Degraded | 94.64% | 98.54% | 649ms | 15.2s | 11 tps | 256K | $0.094 / $0.250 | |
Qwen3.5 397B A17Bvenice | Degraded | 93.90% | 95.95% | 954ms | 9.40s | 2.0 tps | 128K | $0.750 / $4.50 |
| Down | 52.99% | 98.42% | 3.24s | 44.9s | 12 tps | 198K | $0.550 / $2.65 | |
DeepSeek V3.2venice | Down | — | 77.71% | 2.05s | 51.4s | 7.0 tps | 160K | $0.330 / $0.480 |
MiniMax M2.5venice | No data | — | 99.73% | 788ms | 2.92s | 34 tps | 198K | $0.270 / $0.950 |
| No data | — | 98.75% | 1.33s | 9.13s | 16 tps | 256K | $0.750 / $3.50 | |
| Down | — | 73.07% | 2.43s | 22.2s | 78 tps | 256K | $0.625 / $3.13 | |
| No data | — | 99.82% | 789ms | 1.33s | 49 tps | 128K | $0.450 / $3.50 | |
| No data | — | 90.04% | 1.11s | 13.4s | 25 tps | 256K | $0.350 / $1.50 | |
Qwen3.8 2.4T A95Bvenice | No data | — | 97.03% | 1.25s | 58.2s | 96 tps | 262K | $2.50 / $7.50 |
- Uncensored100%Healthy24h 99.99%
- p50
- 715ms
- p99
- 6.22s
- Throughput
- 29 tps
- Context
- 128K
- $/Mtok
- $0.200 / $0.900
venice/fp16fp16 - MiniMax M3100%Healthy24h 99.82%
- p50
- 1.43s
- p99
- 12.3s
- Throughput
- 98 tps
- Context
- 524K
- $/Mtok
- $0.300 / $1.20
venice/fp8fp8 - Mistral Small 4100%Healthy24h 99.96%
- p50
- 621ms
- p99
- 7.41s
- Throughput
- 71 tps
- Context
- 256K
- $/Mtok
- $0.188 / $0.750
venice/fp8fp8 - Kimi K2.5100%Healthy24h 97.37%
- p50
- 2.71s
- p99
- 14.9s
- Throughput
- 35 tps
- Context
- 256K
- $/Mtok
- $0.532 / $3.32
venice - Kimi K2.7 Code100%Healthy24h 97.72%
- p50
- 2.20s
- p99
- 7.19s
- Throughput
- 13 tps
- Context
- 256K
- $/Mtok
- $0.750 / $3.50
venice/int4int4 - Qwen3.5-35B-A3B100%Healthy24h 99.94%
- p50
- 703ms
- p99
- 6.17s
- Throughput
- 125 tps
- Context
- 256K
- $/Mtok
- $0.313 / $1.25
venice - Qwen3.5-9B100%Healthy24h 99.97%
- p50
- 1.05s
- p99
- 13.3s
- Throughput
- 73 tps
- Context
- 256K
- $/Mtok
- $0.100 / $0.150
venice/fp8fp8 - Qwen3.6 27B100%Healthy24h 94.24%
- p50
- 712ms
- p99
- 16.9s
- Throughput
- 33 tps
- Context
- 256K
- $/Mtok
- $0.325 / $3.25
venice/fp8fp8 - Qwen3.6 35B A3B100%Healthy24h 99.71%
- p50
- 631ms
- p99
- 1.61s
- Throughput
- 147 tps
- Context
- 256K
- $/Mtok
- $0.098 / $0.950
venice/fp8fp8 - Qwen3.8 27B100%Healthy24h 99.27%
- p50
- 1.36s
- p99
- 6.18s
- Throughput
- 109 tps
- Context
- 262K
- $/Mtok
- $0.450 / $3.20
venice/fp8fp8 - GLM 4.6100%Healthy24h 99.36%
- p50
- 1.27s
- p99
- 7.10s
- Throughput
- 15 tps
- Context
- 198K
- $/Mtok
- $0.430 / $1.75
venice/fp4fp4 - GLM 4.7 Flash100%Healthy24h 99.64%
- p50
- 614ms
- p99
- 3.81s
- Throughput
- 37 tps
- Context
- 128K
- $/Mtok
- $0.060 / $0.400
venice/fp8fp8 - GLM 5100%Healthy24h 92.28%
- p50
- 1.30s
- p99
- 12.5s
- Throughput
- 45 tps
- Context
- 198K
- $/Mtok
- $1.00 / $3.20
venice/fp8fp8 - GLM 5.1100%Healthy24h 97.82%
- p50
- 1.34s
- p99
- 7.61s
- Throughput
- 22 tps
- Context
- 200K
- $/Mtok
- $1.54 / $4.84
venice/fp8fp8 - GLM 5.2100%Healthy24h 98.53%
- p50
- 2.37s
- p99
- 22.8s
- Throughput
- 38 tps
- Context
- 1.0M
- $/Mtok
- $1.40 / $4.40
venice/fp8fp8 - DeepSeek V4 Flash 042399.90%Healthy24h 99.77%
- p50
- 1.61s
- p99
- 4.60s
- Throughput
- 35 tps
- Context
- 1.0M
- $/Mtok
- $0.138 / $0.275
venice - Gemma 4 26B A4B 99.77%Healthy24h 99.47%
- p50
- 932ms
- p99
- 6.92s
- Throughput
- 20 tps
- Context
- 256K
- $/Mtok
- $0.130 / $0.400
venice/bf16bf16 - Gemma 4 31B99.65%Healthy24h 99.82%
- p50
- 1.14s
- p99
- 15.1s
- Throughput
- 31 tps
- Context
- 256K
- $/Mtok
- $0.120 / $0.360
venice/bf16bf16 - DeepSeek V4 Pro 042399.18%Healthy24h 88.39%
- p50
- 1.18s
- p99
- 10.0s
- Throughput
- 47 tps
- Context
- 1.0M
- $/Mtok
- $1.65 / $3.30
venice - Degraded24h 97.83%
- p50
- 1.06s
- p99
- 12.0s
- Throughput
- 8.0 tps
- Context
- 128K
- $/Mtok
- $0.150 / $0.750
venice/fp8fp8 - Healthy24h 96.07%
- p50
- 1.54s
- p99
- 6.40s
- Throughput
- 20 tps
- Context
- 128K
- $/Mtok
- $0.210 / $1.90
venice/fp8fp8 - DeepSeek V4 Flash 073197.97%Healthy24h 97.85%
- p50
- 1.14s
- p99
- 12.0s
- Throughput
- 45 tps
- Context
- 1.0M
- $/Mtok
- $0.175 / $0.350
venice - Mistral Small 3.2 24B94.64%Degraded24h 98.54%
- p50
- 649ms
- p99
- 15.2s
- Throughput
- 11 tps
- Context
- 256K
- $/Mtok
- $0.094 / $0.250
venice/fp8fp8 - Qwen3.5 397B A17B93.90%Degraded24h 95.95%
- p50
- 954ms
- p99
- 9.40s
- Throughput
- 2.0 tps
- Context
- 128K
- $/Mtok
- $0.750 / $4.50
venice - GLM 4.752.99%Down24h 98.42%
- p50
- 3.24s
- p99
- 44.9s
- Throughput
- 12 tps
- Context
- 198K
- $/Mtok
- $0.550 / $2.65
venice/fp4fp4 - Down24h 77.71%
- p50
- 2.05s
- p99
- 51.4s
- Throughput
- 7.0 tps
- Context
- 160K
- $/Mtok
- $0.330 / $0.480
venice - No data24h 99.73%
- p50
- 788ms
- p99
- 2.92s
- Throughput
- 34 tps
- Context
- 198K
- $/Mtok
- $0.270 / $0.950
venice - No data24h 98.75%
- p50
- 1.33s
- p99
- 9.13s
- Throughput
- 16 tps
- Context
- 256K
- $/Mtok
- $0.750 / $3.50
venice/int4int4 - Down24h 73.07%
- p50
- 2.43s
- p99
- 22.2s
- Throughput
- 78 tps
- Context
- 256K
- $/Mtok
- $0.625 / $3.13
venice/fp8fp8 - No data24h 99.82%
- p50
- 789ms
- p99
- 1.33s
- Throughput
- 49 tps
- Context
- 128K
- $/Mtok
- $0.450 / $3.50
venice/fp8fp8 - No data24h 90.04%
- p50
- 1.11s
- p99
- 13.4s
- Throughput
- 25 tps
- Context
- 256K
- $/Mtok
- $0.350 / $1.50
venice/fp8fp8 - No data24h 97.03%
- p50
- 1.25s
- p99
- 58.2s
- Throughput
- 96 tps
- Context
- 262K
- $/Mtok
- $2.50 / $7.50
venice
Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.