Venice
37 endpoints · 6 unhealthy · worst uptime 78.33%
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 99.97% | 99.99% | 99.99% | 504ms | 1.98s | 68 tps | 128K | $0.200 / $0.900 | |
DeepSeek V3.2venice | Healthy | 100% | 99.54% | 98.82% | 98.83% | 1.73s | 23.8s | 18 tps | 160K | $0.268 / $0.390 |
DeepSeek V4 Flash 0731venice | Healthy | 100% | 99.77% | 99.64% | 99.19% | 1.14s | 9.16s | 45 tps | 1.0M | $0.175 / $0.350 |
DeepSeek V4 Pro 0813venice | Healthy | 100% | 94.62% | 96.25% | 97.88% | 1.18s | 12.6s | 38 tps | 1.0M | $1.65 / $4.95 |
| Healthy | 100% | 99.28% | 99.66% | 99.26% | 1.11s | 16.5s | 191 tps | 1.0M | $0.300 / $1.20 | |
| Healthy | 100% | 99.58% | 99.50% | 98.93% | 1.05s | 9.97s | 44 tps | 256K | $0.130 / $0.400 | |
| Healthy | 100% | 96.12% | 96.57% | 95.24% | 1.13s | 11.7s | 88 tps | 524K | $0.300 / $1.20 | |
| Healthy | 100% | 99.88% | 97.96% | 97.89% | 1.40s | 9.84s | 70 tps | 256K | $0.625 / $3.13 | |
Qwen3.5-35B-A3Bvenice | Healthy | 100% | 99.98% | 99.92% | 99.93% | 1.04s | 21.8s | 154 tps | 256K | $0.313 / $1.25 |
Qwen3.5 397B A17Bvenice | Healthy | 100% | 87.07% | 95.36% | 93.58% | 2.28s | 8.58s | 40 tps | 128K | $0.750 / $4.50 |
| Healthy | 100% | 99.84% | 99.81% | 99.51% | 842ms | 4.54s | 72 tps | 256K | $0.100 / $0.150 | |
| Healthy | 100% | 99.91% | 99.77% | 99.85% | 678ms | 4.30s | 132 tps | 256K | $0.100 / $1.00 | |
| Healthy | 100% | 99.43% | 93.47% | 93.52% | 1.19s | 7.04s | 30 tps | 1.0M | $0.400 / $2.00 | |
| Healthy | 100% | 98.17% | 94.55% | 94.55% | 1.20s | 5.84s | 26 tps | 1.0M | $0.175 / $0.350 | |
| Healthy | 100% | 99.93% | 99.68% | 99.81% | 858ms | 4.58s | 30 tps | 198K | $0.430 / $1.75 | |
| Degraded | 100% | 92.53% | 85.69% | 91.09% | 1.86s | 18.5s | 15 tps | 198K | $0.400 / $1.93 | |
| Healthy | 100% | 99.35% | 98.41% | 98.00% | 1.72s | 13.6s | 32 tps | 128K | $0.060 / $0.400 | |
GLM 5.3 Flashvenice | Healthy | 100% | 98.09% | 98.18% | 97.06% | 2.95s | 12.6s | 36 tps | 1.0M | $0.150 / $0.500 |
DeepSeek V4 Flash 0423venice | Healthy | 99.76% | 99.23% | 98.86% | 98.44% | 1.47s | 6.88s | 21 tps | 1.0M | $0.097 / $0.193 |
| Healthy | 99.69% | 99.82% | 99.58% | 99.20% | 741ms | 3.43s | 41 tps | 256K | $0.094 / $0.250 | |
Kimi K2.5venice | Healthy | 96.00% | 96.26% | 97.80% | 98.99% | 1.15s | 12.6s | 18 tps | 256K | $0.532 / $3.32 |
| Degraded | 93.33% | 99.36% | 96.56% | 96.36% | 1.89s | 7.08s | 43 tps | 128K | $0.210 / $1.90 | |
DeepSeek V4 Pro 0423venice | Down | 88.89% | 99.73% | 96.03% | 96.17% | 1.33s | 26.8s | 52 tps | 1.0M | $1.65 / $3.30 |
| Down | 88.86% | 95.54% | 98.54% | 98.57% | 527ms | 4.05s | 39 tps | 256K | $0.120 / $0.360 | |
| Down | 78.33% | 88.33% | 90.19% | 93.98% | 687ms | 85.5s | 43 tps | 128K | $0.150 / $0.750 | |
MiniMax M2.5venice | No data | — | 91.61% | 92.60% | 90.57% | 1.21s | 4.79s | 19 tps | 198K | $0.270 / $0.950 |
| No data | — | 90.03% | 86.16% | 91.23% | 1.75s | 15.7s | 13 tps | 256K | $0.750 / $3.50 | |
| No data | — | 99.63% | 99.70% | 97.04% | 1.70s | 6.80s | 19 tps | 256K | $0.750 / $3.50 | |
| No data | — | 100% | 95.76% | 96.04% | 738ms | 3.75s | 122 tps | 128K | $0.450 / $3.50 | |
| Down | — | 96.62% | 90.01% | 90.08% | 888ms | 10.5s | 37 tps | 256K | $0.350 / $1.50 | |
| No data | — | 99.01% | 98.11% | 97.99% | 583ms | 6.57s | 63 tps | 256K | $0.325 / $3.25 | |
Qwen3.8 2.4T A95Bvenice | No data | — | 97.53% | 98.35% | 99.36% | 1.01s | 8.31s | 55 tps | 262K | $2.00 / $6.00 |
| No data | — | 99.47% | 99.55% | 98.69% | 781ms | 2.45s | 107 tps | 262K | $0.450 / $3.20 | |
| No data | — | 99.21% | 99.06% | 98.65% | 1.48s | 6.59s | 65 tps | 198K | $1.00 / $3.20 | |
| No data | — | 96.60% | 97.81% | 89.65% | 855ms | 7.84s | 76 tps | 200K | $1.40 / $4.40 | |
| No data | — | 99.76% | 99.57% | 99.57% | 1.04s | 9.98s | 95 tps | 1.0M | $1.40 / $4.40 | |
GLM 5.3venice | No data | — | 98.60% | 99.50% | 97.55% | 3.17s | 23.7s | 63 tps | 1.0M | $1.40 / $4.40 |
- Uncensored100%Healthy24h 99.97%
- 7d
- 99.99%
- 30d
- 99.99%
- p50
- 504ms
- p99
- 1.98s
- Throughput
- 68 tps
- Context
- 128K
- $/Mtok
- $0.200 / $0.900
venice/fp16fp16 - DeepSeek V3.2100%Healthy24h 99.54%
- 7d
- 98.82%
- 30d
- 98.83%
- p50
- 1.73s
- p99
- 23.8s
- Throughput
- 18 tps
- Context
- 160K
- $/Mtok
- $0.268 / $0.390
venice - Healthy24h 99.77%
- 7d
- 99.64%
- 30d
- 99.19%
- p50
- 1.14s
- p99
- 9.16s
- Throughput
- 45 tps
- Context
- 1.0M
- $/Mtok
- $0.175 / $0.350
venice - Healthy24h 94.62%
- 7d
- 96.25%
- 30d
- 97.88%
- p50
- 1.18s
- p99
- 12.6s
- Throughput
- 38 tps
- Context
- 1.0M
- $/Mtok
- $1.65 / $4.95
venice - Healthy24h 99.28%
- 7d
- 99.66%
- 30d
- 99.26%
- p50
- 1.11s
- p99
- 16.5s
- Throughput
- 191 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
venice/fp8fp8 - Gemma 4 26B A4B 100%Healthy24h 99.58%
- 7d
- 99.50%
- 30d
- 98.93%
- p50
- 1.05s
- p99
- 9.97s
- Throughput
- 44 tps
- Context
- 256K
- $/Mtok
- $0.130 / $0.400
venice/bf16bf16 - MiniMax M3100%Healthy24h 96.12%
- 7d
- 96.57%
- 30d
- 95.24%
- p50
- 1.13s
- p99
- 11.7s
- Throughput
- 88 tps
- Context
- 524K
- $/Mtok
- $0.300 / $1.20
venice/fp8fp8 - Nemotron 3 Ultra100%Healthy24h 99.88%
- 7d
- 97.96%
- 30d
- 97.89%
- p50
- 1.40s
- p99
- 9.84s
- Throughput
- 70 tps
- Context
- 256K
- $/Mtok
- $0.625 / $3.13
venice/fp8fp8 - Qwen3.5-35B-A3B100%Healthy24h 99.98%
- 7d
- 99.92%
- 30d
- 99.93%
- p50
- 1.04s
- p99
- 21.8s
- Throughput
- 154 tps
- Context
- 256K
- $/Mtok
- $0.313 / $1.25
venice - Healthy24h 87.07%
- 7d
- 95.36%
- 30d
- 93.58%
- p50
- 2.28s
- p99
- 8.58s
- Throughput
- 40 tps
- Context
- 128K
- $/Mtok
- $0.750 / $4.50
venice - Qwen3.5-9B100%Healthy24h 99.84%
- 7d
- 99.81%
- 30d
- 99.51%
- p50
- 842ms
- p99
- 4.54s
- Throughput
- 72 tps
- Context
- 256K
- $/Mtok
- $0.100 / $0.150
venice/fp8fp8 - Qwen3.6 35B A3B100%Healthy24h 99.91%
- 7d
- 99.77%
- 30d
- 99.85%
- p50
- 678ms
- p99
- 4.30s
- Throughput
- 132 tps
- Context
- 256K
- $/Mtok
- $0.100 / $1.00
venice/fp8fp8 - MiMo-V2.5100%Healthy24h 99.43%
- 7d
- 93.47%
- 30d
- 93.52%
- p50
- 1.19s
- p99
- 7.04s
- Throughput
- 30 tps
- Context
- 1.0M
- $/Mtok
- $0.400 / $2.00
venice/fp8fp8 - MiMo-V2.6-Flash100%Healthy24h 98.17%
- 7d
- 94.55%
- 30d
- 94.55%
- p50
- 1.20s
- p99
- 5.84s
- Throughput
- 26 tps
- Context
- 1.0M
- $/Mtok
- $0.175 / $0.350
venice/fp8fp8 - GLM 4.6100%Healthy24h 99.93%
- 7d
- 99.68%
- 30d
- 99.81%
- p50
- 858ms
- p99
- 4.58s
- Throughput
- 30 tps
- Context
- 198K
- $/Mtok
- $0.430 / $1.75
venice/fp4fp4 - GLM 4.7100%Degraded24h 92.53%
- 7d
- 85.69%
- 30d
- 91.09%
- p50
- 1.86s
- p99
- 18.5s
- Throughput
- 15 tps
- Context
- 198K
- $/Mtok
- $0.400 / $1.93
venice/fp4fp4 - GLM 4.7 Flash100%Healthy24h 99.35%
- 7d
- 98.41%
- 30d
- 98.00%
- p50
- 1.72s
- p99
- 13.6s
- Throughput
- 32 tps
- Context
- 128K
- $/Mtok
- $0.060 / $0.400
venice/fp8fp8 - GLM 5.3 Flash100%Healthy24h 98.09%
- 7d
- 98.18%
- 30d
- 97.06%
- p50
- 2.95s
- p99
- 12.6s
- Throughput
- 36 tps
- Context
- 1.0M
- $/Mtok
- $0.150 / $0.500
venice - DeepSeek V4 Flash 042399.76%Healthy24h 99.23%
- 7d
- 98.86%
- 30d
- 98.44%
- p50
- 1.47s
- p99
- 6.88s
- Throughput
- 21 tps
- Context
- 1.0M
- $/Mtok
- $0.097 / $0.193
venice - Mistral Small 3.2 24B99.69%Healthy24h 99.82%
- 7d
- 99.58%
- 30d
- 99.20%
- p50
- 741ms
- p99
- 3.43s
- Throughput
- 41 tps
- Context
- 256K
- $/Mtok
- $0.094 / $0.250
venice/fp8fp8 - Kimi K2.596.00%Healthy24h 96.26%
- 7d
- 97.80%
- 30d
- 98.99%
- p50
- 1.15s
- p99
- 12.6s
- Throughput
- 18 tps
- Context
- 256K
- $/Mtok
- $0.532 / $3.32
venice - Degraded24h 99.36%
- 7d
- 96.56%
- 30d
- 96.36%
- p50
- 1.89s
- p99
- 7.08s
- Throughput
- 43 tps
- Context
- 128K
- $/Mtok
- $0.210 / $1.90
venice/fp8fp8 - DeepSeek V4 Pro 042388.89%Down24h 99.73%
- 7d
- 96.03%
- 30d
- 96.17%
- p50
- 1.33s
- p99
- 26.8s
- Throughput
- 52 tps
- Context
- 1.0M
- $/Mtok
- $1.65 / $3.30
venice - Gemma 4 31B88.86%Down24h 95.54%
- 7d
- 98.54%
- 30d
- 98.57%
- p50
- 527ms
- p99
- 4.05s
- Throughput
- 39 tps
- Context
- 256K
- $/Mtok
- $0.120 / $0.360
venice/fp4fp4 - Down24h 88.33%
- 7d
- 90.19%
- 30d
- 93.98%
- p50
- 687ms
- p99
- 85.5s
- Throughput
- 43 tps
- Context
- 128K
- $/Mtok
- $0.150 / $0.750
venice/fp8fp8 - No data24h 91.61%
- 7d
- 92.60%
- 30d
- 90.57%
- p50
- 1.21s
- p99
- 4.79s
- Throughput
- 19 tps
- Context
- 198K
- $/Mtok
- $0.270 / $0.950
venice - No data24h 90.03%
- 7d
- 86.16%
- 30d
- 91.23%
- p50
- 1.75s
- p99
- 15.7s
- Throughput
- 13 tps
- Context
- 256K
- $/Mtok
- $0.750 / $3.50
venice/int4int4 - No data24h 99.63%
- 7d
- 99.70%
- 30d
- 97.04%
- p50
- 1.70s
- p99
- 6.80s
- Throughput
- 19 tps
- Context
- 256K
- $/Mtok
- $0.750 / $3.50
venice/int4int4 - No data24h 100%
- 7d
- 95.76%
- 30d
- 96.04%
- p50
- 738ms
- p99
- 3.75s
- Throughput
- 122 tps
- Context
- 128K
- $/Mtok
- $0.450 / $3.50
venice/fp8fp8 - Down24h 96.62%
- 7d
- 90.01%
- 30d
- 90.08%
- p50
- 888ms
- p99
- 10.5s
- Throughput
- 37 tps
- Context
- 256K
- $/Mtok
- $0.350 / $1.50
venice/fp8fp8 - No data24h 99.01%
- 7d
- 98.11%
- 30d
- 97.99%
- p50
- 583ms
- p99
- 6.57s
- Throughput
- 63 tps
- Context
- 256K
- $/Mtok
- $0.325 / $3.25
venice/fp8fp8 - No data24h 97.53%
- 7d
- 98.35%
- 30d
- 99.36%
- p50
- 1.01s
- p99
- 8.31s
- Throughput
- 55 tps
- Context
- 262K
- $/Mtok
- $2.00 / $6.00
venice - No data24h 99.47%
- 7d
- 99.55%
- 30d
- 98.69%
- p50
- 781ms
- p99
- 2.45s
- Throughput
- 107 tps
- Context
- 262K
- $/Mtok
- $0.450 / $3.20
venice/fp8fp8 - No data24h 99.21%
- 7d
- 99.06%
- 30d
- 98.65%
- p50
- 1.48s
- p99
- 6.59s
- Throughput
- 65 tps
- Context
- 198K
- $/Mtok
- $1.00 / $3.20
venice/fp8fp8 - No data24h 96.60%
- 7d
- 97.81%
- 30d
- 89.65%
- p50
- 855ms
- p99
- 7.84s
- Throughput
- 76 tps
- Context
- 200K
- $/Mtok
- $1.40 / $4.40
venice/fp8fp8 - No data24h 99.76%
- 7d
- 99.57%
- 30d
- 99.57%
- p50
- 1.04s
- p99
- 9.98s
- Throughput
- 95 tps
- Context
- 1.0M
- $/Mtok
- $1.40 / $4.40
venice/fp8fp8 - No data24h 98.60%
- 7d
- 99.50%
- 30d
- 97.55%
- p50
- 3.17s
- p99
- 23.7s
- Throughput
- 63 tps
- Context
- 1.0M
- $/Mtok
- $1.40 / $4.40
venice
Measured 3m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
MiniMax M2.5 venice
GLM 4.7 venice/fp4
MiMo-V2.5 venice/fp8
Qwen3.6 27B venice/fp8
Qwen3.5 397B A17B venice
Qwen3 235B A22B Instruct 2507 venice/fp8
Qwen3 Coder 480B A35B venice/fp8
DeepSeek V4 Pro 0813 venice
Gemma 4 31B venice/fp4
MiMo-V2.6-Flash venice/fp8
Kimi K2.6 venice/int4
Kimi K2.5 venice
Qwen3 VL 235B A22B Instruct venice/fp8
MiniMax M3 venice/fp8
Qwen3.8 27B venice/fp8
GLM 4.7 Flash venice/fp8
GLM 5.3 Flash venice
DeepSeek V4 Flash 0423 venice
GLM 5.3 venice
GLM 5 venice/fp8
DeepSeek V3.2 venice
Qwen3.8 2.4T A95B venice
DeepSeek V4.1 Flash venice/fp8
Nemotron 3 Ultra venice/fp8
DeepSeek V4 Pro 0423 venice
Gemma 4 26B A4B venice/bf16
Qwen3.6 35B A3B venice/fp8
GLM 4.6 venice/fp4
DeepSeek V4 Flash 0731 venice
GLM 5.2 venice/fp8
Mistral Small 3.2 24B venice/fp8
Qwen3.5-9B venice/fp8
Uncensored venice/fp16
Kimi K2.7 Code venice/int4
Qwen3.5-35B-A3B venice
Qwen3 235B A22B Thinking 2507 venice/fp8
GLM 5.1 venice/fp8
Colour by 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.