Venice
37 endpoints · 6 unhealthy · worst uptime 71.30%
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 99.97% | 99.99% | 99.99% | 523ms | 2.47s | 66 tps | 128K | $0.200 / $0.900 | |
DeepSeek V3.2venice | Healthy | 100% | 99.61% | 98.82% | 98.83% | 1.43s | 11.6s | 17 tps | 160K | $0.268 / $0.390 |
DeepSeek V4 Pro 0423venice | Healthy | 100% | 99.71% | 96.03% | 96.17% | 1.27s | 5.92s | 44 tps | 1.0M | $1.65 / $3.30 |
| Healthy | 100% | 99.29% | 99.66% | 99.26% | 1.27s | 23.2s | 148 tps | 1.0M | $0.300 / $1.20 | |
MiniMax M2.5venice | Healthy | 100% | 91.75% | 92.54% | 90.54% | 1.37s | 5.80s | 32 tps | 198K | $0.270 / $0.950 |
| Healthy | 100% | 95.93% | 96.56% | 95.23% | 1.01s | 3.83s | 74 tps | 524K | $0.300 / $1.20 | |
Kimi K2.5venice | Degraded | 100% | 96.18% | 97.79% | 98.98% | 1.23s | 13.6s | 16 tps | 256K | $0.532 / $3.32 |
| Healthy | 100% | 96.61% | 89.99% | 90.09% | 558ms | 16.7s | 88 tps | 256K | $0.350 / $1.50 | |
Qwen3.5-35B-A3Bvenice | Healthy | 100% | 99.98% | 99.92% | 99.93% | 1.16s | 7.67s | 131 tps | 256K | $0.313 / $1.25 |
| Healthy | 100% | 99.84% | 99.81% | 99.51% | 785ms | 2.72s | 79 tps | 256K | $0.100 / $0.150 | |
| Healthy | 100% | 98.86% | 98.10% | 97.98% | 612ms | 15.7s | 46 tps | 256K | $0.325 / $3.25 | |
| Healthy | 100% | 99.91% | 99.77% | 99.85% | 641ms | 4.07s | 140 tps | 256K | $0.100 / $1.00 | |
| Healthy | 100% | 98.16% | 94.58% | 94.58% | 1.21s | 6.01s | 23 tps | 1.0M | $0.175 / $0.350 | |
| Healthy | 100% | 99.93% | 99.68% | 99.81% | 862ms | 4.33s | 53 tps | 198K | $0.430 / $1.75 | |
| Healthy | 100% | 93.81% | 85.70% | 91.10% | 1.85s | 25.0s | 14 tps | 198K | $0.400 / $1.93 | |
| Degraded | 100% | 99.29% | 98.41% | 98.00% | 1.84s | 33.2s | 27 tps | 128K | $0.060 / $0.400 | |
GLM 5.3 Flashvenice | Degraded | 99.93% | 97.65% | 98.19% | 97.07% | 3.27s | 26.0s | 26 tps | 1.0M | $0.150 / $0.500 |
| Healthy | 99.84% | 99.82% | 99.58% | 99.20% | 714ms | 4.54s | 39 tps | 256K | $0.094 / $0.250 | |
DeepSeek V4 Flash 0423venice | Healthy | 99.78% | 99.22% | 98.88% | 98.44% | 1.09s | 10.3s | 38 tps | 1.0M | $0.097 / $0.193 |
| Healthy | 99.63% | 99.37% | 96.57% | 96.36% | 1.00s | 7.70s | 46 tps | 128K | $0.210 / $1.90 | |
| Healthy | 99.62% | 99.58% | 99.51% | 98.93% | 1.10s | 6.70s | 33 tps | 256K | $0.130 / $0.400 | |
| Healthy | 99.42% | 99.38% | 93.52% | 93.53% | 1.18s | 6.75s | 28 tps | 1.0M | $0.400 / $2.00 | |
DeepSeek V4 Flash 0731venice | Healthy | 98.90% | 99.74% | 99.65% | 99.20% | 1.20s | 23.3s | 37 tps | 1.0M | $0.175 / $0.350 |
| Degraded | 91.41% | 95.22% | 98.50% | 98.55% | 519ms | 4.58s | 39 tps | 256K | $0.120 / $0.360 | |
| Down | 71.30% | 89.15% | 90.18% | 94.00% | 767ms | 79.6s | 37 tps | 128K | $0.150 / $0.750 | |
DeepSeek V4 Pro 0813venice | Degraded | — | 94.73% | 96.23% | 97.89% | 1.34s | 24.6s | 38 tps | 1.0M | $1.65 / $4.95 |
| No data | — | 89.72% | 86.07% | 91.22% | 3.54s | 38.5s | 9.0 tps | 256K | $0.750 / $3.50 | |
| No data | — | 99.63% | 99.69% | 97.04% | 1.22s | 9.29s | 29 tps | 256K | $0.750 / $3.50 | |
| No data | — | 99.93% | 97.97% | 97.89% | 1.36s | 13.1s | 32 tps | 256K | $0.625 / $3.13 | |
| No data | — | 100% | 95.76% | 96.04% | 3.01s | 16.7s | 125 tps | 128K | $0.450 / $3.50 | |
Qwen3.5 397B A17Bvenice | No data | — | 87.10% | 95.39% | 93.59% | 1.14s | 5.63s | 62 tps | 128K | $0.750 / $4.50 |
Qwen3.8 2.4T A95Bvenice | No data | — | 97.54% | 98.32% | 99.36% | 848ms | 10.5s | 75 tps | 262K | $2.00 / $6.00 |
| No data | — | 99.46% | 99.55% | 98.69% | 647ms | 7.36s | 102 tps | 262K | $0.450 / $3.20 | |
| No data | — | 99.15% | 99.05% | 98.65% | 1.05s | 3.98s | 59 tps | 198K | $1.00 / $3.20 | |
| No data | — | 96.60% | 97.81% | 89.68% | 1.41s | 12.5s | 48 tps | 200K | $1.40 / $4.40 | |
| No data | — | 99.76% | 99.57% | 99.57% | 1.15s | 51.2s | 75 tps | 1.0M | $1.40 / $4.40 | |
GLM 5.3venice | No data | — | 98.56% | 99.50% | 97.55% | 1.53s | 18.6s | 43 tps | 1.0M | $1.40 / $4.40 |
- Uncensored100%Healthy24h 99.97%
- 7d
- 99.99%
- 30d
- 99.99%
- p50
- 523ms
- p99
- 2.47s
- Throughput
- 66 tps
- Context
- 128K
- $/Mtok
- $0.200 / $0.900
venice/fp16fp16 - DeepSeek V3.2100%Healthy24h 99.61%
- 7d
- 98.82%
- 30d
- 98.83%
- p50
- 1.43s
- p99
- 11.6s
- Throughput
- 17 tps
- Context
- 160K
- $/Mtok
- $0.268 / $0.390
venice - Healthy24h 99.71%
- 7d
- 96.03%
- 30d
- 96.17%
- p50
- 1.27s
- p99
- 5.92s
- Throughput
- 44 tps
- Context
- 1.0M
- $/Mtok
- $1.65 / $3.30
venice - Healthy24h 99.29%
- 7d
- 99.66%
- 30d
- 99.26%
- p50
- 1.27s
- p99
- 23.2s
- Throughput
- 148 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
venice/fp8fp8 - MiniMax M2.5100%Healthy24h 91.75%
- 7d
- 92.54%
- 30d
- 90.54%
- p50
- 1.37s
- p99
- 5.80s
- Throughput
- 32 tps
- Context
- 198K
- $/Mtok
- $0.270 / $0.950
venice - MiniMax M3100%Healthy24h 95.93%
- 7d
- 96.56%
- 30d
- 95.23%
- p50
- 1.01s
- p99
- 3.83s
- Throughput
- 74 tps
- Context
- 524K
- $/Mtok
- $0.300 / $1.20
venice/fp8fp8 - Kimi K2.5100%Degraded24h 96.18%
- 7d
- 97.79%
- 30d
- 98.98%
- p50
- 1.23s
- p99
- 13.6s
- Throughput
- 16 tps
- Context
- 256K
- $/Mtok
- $0.532 / $3.32
venice - Healthy24h 96.61%
- 7d
- 89.99%
- 30d
- 90.09%
- p50
- 558ms
- p99
- 16.7s
- Throughput
- 88 tps
- Context
- 256K
- $/Mtok
- $0.350 / $1.50
venice/fp8fp8 - Qwen3.5-35B-A3B100%Healthy24h 99.98%
- 7d
- 99.92%
- 30d
- 99.93%
- p50
- 1.16s
- p99
- 7.67s
- Throughput
- 131 tps
- Context
- 256K
- $/Mtok
- $0.313 / $1.25
venice - Qwen3.5-9B100%Healthy24h 99.84%
- 7d
- 99.81%
- 30d
- 99.51%
- p50
- 785ms
- p99
- 2.72s
- Throughput
- 79 tps
- Context
- 256K
- $/Mtok
- $0.100 / $0.150
venice/fp8fp8 - Qwen3.6 27B100%Healthy24h 98.86%
- 7d
- 98.10%
- 30d
- 97.98%
- p50
- 612ms
- p99
- 15.7s
- Throughput
- 46 tps
- Context
- 256K
- $/Mtok
- $0.325 / $3.25
venice/fp8fp8 - Qwen3.6 35B A3B100%Healthy24h 99.91%
- 7d
- 99.77%
- 30d
- 99.85%
- p50
- 641ms
- p99
- 4.07s
- Throughput
- 140 tps
- Context
- 256K
- $/Mtok
- $0.100 / $1.00
venice/fp8fp8 - MiMo-V2.6-Flash100%Healthy24h 98.16%
- 7d
- 94.58%
- 30d
- 94.58%
- p50
- 1.21s
- p99
- 6.01s
- Throughput
- 23 tps
- Context
- 1.0M
- $/Mtok
- $0.175 / $0.350
venice/fp8fp8 - GLM 4.6100%Healthy24h 99.93%
- 7d
- 99.68%
- 30d
- 99.81%
- p50
- 862ms
- p99
- 4.33s
- Throughput
- 53 tps
- Context
- 198K
- $/Mtok
- $0.430 / $1.75
venice/fp4fp4 - GLM 4.7100%Healthy24h 93.81%
- 7d
- 85.70%
- 30d
- 91.10%
- p50
- 1.85s
- p99
- 25.0s
- Throughput
- 14 tps
- Context
- 198K
- $/Mtok
- $0.400 / $1.93
venice/fp4fp4 - GLM 4.7 Flash100%Degraded24h 99.29%
- 7d
- 98.41%
- 30d
- 98.00%
- p50
- 1.84s
- p99
- 33.2s
- Throughput
- 27 tps
- Context
- 128K
- $/Mtok
- $0.060 / $0.400
venice/fp8fp8 - GLM 5.3 Flash99.93%Degraded24h 97.65%
- 7d
- 98.19%
- 30d
- 97.07%
- p50
- 3.27s
- p99
- 26.0s
- Throughput
- 26 tps
- Context
- 1.0M
- $/Mtok
- $0.150 / $0.500
venice - Mistral Small 3.2 24B99.84%Healthy24h 99.82%
- 7d
- 99.58%
- 30d
- 99.20%
- p50
- 714ms
- p99
- 4.54s
- Throughput
- 39 tps
- Context
- 256K
- $/Mtok
- $0.094 / $0.250
venice/fp8fp8 - DeepSeek V4 Flash 042399.78%Healthy24h 99.22%
- 7d
- 98.88%
- 30d
- 98.44%
- p50
- 1.09s
- p99
- 10.3s
- Throughput
- 38 tps
- Context
- 1.0M
- $/Mtok
- $0.097 / $0.193
venice - Healthy24h 99.37%
- 7d
- 96.57%
- 30d
- 96.36%
- p50
- 1.00s
- p99
- 7.70s
- Throughput
- 46 tps
- Context
- 128K
- $/Mtok
- $0.210 / $1.90
venice/fp8fp8 - Gemma 4 26B A4B 99.62%Healthy24h 99.58%
- 7d
- 99.51%
- 30d
- 98.93%
- p50
- 1.10s
- p99
- 6.70s
- Throughput
- 33 tps
- Context
- 256K
- $/Mtok
- $0.130 / $0.400
venice/bf16bf16 - MiMo-V2.599.42%Healthy24h 99.38%
- 7d
- 93.52%
- 30d
- 93.53%
- p50
- 1.18s
- p99
- 6.75s
- Throughput
- 28 tps
- Context
- 1.0M
- $/Mtok
- $0.400 / $2.00
venice/fp8fp8 - DeepSeek V4 Flash 073198.90%Healthy24h 99.74%
- 7d
- 99.65%
- 30d
- 99.20%
- p50
- 1.20s
- p99
- 23.3s
- Throughput
- 37 tps
- Context
- 1.0M
- $/Mtok
- $0.175 / $0.350
venice - Gemma 4 31B91.41%Degraded24h 95.22%
- 7d
- 98.50%
- 30d
- 98.55%
- p50
- 519ms
- p99
- 4.58s
- Throughput
- 39 tps
- Context
- 256K
- $/Mtok
- $0.120 / $0.360
venice/fp4fp4 - Down24h 89.15%
- 7d
- 90.18%
- 30d
- 94.00%
- p50
- 767ms
- p99
- 79.6s
- Throughput
- 37 tps
- Context
- 128K
- $/Mtok
- $0.150 / $0.750
venice/fp8fp8 - Degraded24h 94.73%
- 7d
- 96.23%
- 30d
- 97.89%
- p50
- 1.34s
- p99
- 24.6s
- Throughput
- 38 tps
- Context
- 1.0M
- $/Mtok
- $1.65 / $4.95
venice - No data24h 89.72%
- 7d
- 86.07%
- 30d
- 91.22%
- p50
- 3.54s
- p99
- 38.5s
- Throughput
- 9.0 tps
- Context
- 256K
- $/Mtok
- $0.750 / $3.50
venice/int4int4 - No data24h 99.63%
- 7d
- 99.69%
- 30d
- 97.04%
- p50
- 1.22s
- p99
- 9.29s
- Throughput
- 29 tps
- Context
- 256K
- $/Mtok
- $0.750 / $3.50
venice/int4int4 - No data24h 99.93%
- 7d
- 97.97%
- 30d
- 97.89%
- p50
- 1.36s
- p99
- 13.1s
- Throughput
- 32 tps
- Context
- 256K
- $/Mtok
- $0.625 / $3.13
venice/fp8fp8 - No data24h 100%
- 7d
- 95.76%
- 30d
- 96.04%
- p50
- 3.01s
- p99
- 16.7s
- Throughput
- 125 tps
- Context
- 128K
- $/Mtok
- $0.450 / $3.50
venice/fp8fp8 - No data24h 87.10%
- 7d
- 95.39%
- 30d
- 93.59%
- p50
- 1.14s
- p99
- 5.63s
- Throughput
- 62 tps
- Context
- 128K
- $/Mtok
- $0.750 / $4.50
venice - No data24h 97.54%
- 7d
- 98.32%
- 30d
- 99.36%
- p50
- 848ms
- p99
- 10.5s
- Throughput
- 75 tps
- Context
- 262K
- $/Mtok
- $2.00 / $6.00
venice - No data24h 99.46%
- 7d
- 99.55%
- 30d
- 98.69%
- p50
- 647ms
- p99
- 7.36s
- Throughput
- 102 tps
- Context
- 262K
- $/Mtok
- $0.450 / $3.20
venice/fp8fp8 - No data24h 99.15%
- 7d
- 99.05%
- 30d
- 98.65%
- p50
- 1.05s
- p99
- 3.98s
- Throughput
- 59 tps
- Context
- 198K
- $/Mtok
- $1.00 / $3.20
venice/fp8fp8 - No data24h 96.60%
- 7d
- 97.81%
- 30d
- 89.68%
- p50
- 1.41s
- p99
- 12.5s
- Throughput
- 48 tps
- Context
- 200K
- $/Mtok
- $1.40 / $4.40
venice/fp8fp8 - No data24h 99.76%
- 7d
- 99.57%
- 30d
- 99.57%
- p50
- 1.15s
- p99
- 51.2s
- Throughput
- 75 tps
- Context
- 1.0M
- $/Mtok
- $1.40 / $4.40
venice/fp8fp8 - No data24h 98.56%
- 7d
- 99.50%
- 30d
- 97.55%
- p50
- 1.53s
- p99
- 18.6s
- Throughput
- 43 tps
- Context
- 1.0M
- $/Mtok
- $1.40 / $4.40
venice
Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
Kimi K2.6 venice/int4
GLM 4.7 venice/fp4
Qwen3 Coder 480B A35B venice/fp8
Nemotron 3 Ultra venice/fp8
DeepSeek V4 Pro 0423 venice
MiniMax M2.5 venice
DeepSeek V4 Pro 0813 venice
GLM 5.1 venice/fp8
MiMo-V2.6-Flash venice/fp8
MiMo-V2.5 venice/fp8
Qwen3 235B A22B Instruct 2507 venice/fp8
Qwen3.5 397B A17B venice
MiniMax M3 venice/fp8
Qwen3 VL 235B A22B Instruct venice/fp8
Qwen3.6 27B venice/fp8
Qwen3 235B A22B Thinking 2507 venice/fp8
Qwen3.8 2.4T A95B venice
GLM 4.6 venice/fp4
Kimi K2.5 venice
DeepSeek V4 Flash 0423 venice
GLM 5.3 Flash venice
GLM 4.7 Flash venice/fp8
Gemma 4 31B venice/fp4
DeepSeek V3.2 venice
GLM 5 venice/fp8
DeepSeek V4.1 Flash venice/fp8
GLM 5.2 venice/fp8
Qwen3.8 27B venice/fp8
Qwen3.6 35B A3B venice/fp8
GLM 5.3 venice
Mistral Small 3.2 24B venice/fp8
Kimi K2.7 Code venice/int4
Gemma 4 26B A4B venice/bf16
DeepSeek V4 Flash 0731 venice
Qwen3.5-35B-A3B venice
Qwen3.5-9B venice/fp8
Uncensored venice/fp16
Colour by 6-hourly mean uptime:≥ 95%90–95%< 90%no data
Through the live last bucket (raw rounds, updated every collection round) · 37 endpoints with data, sorted worst-first.