DeepInfra
76 endpoints · 12 unhealthy · worst uptime 65.73%
| State | ||||||||
|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 99.83% | 946ms | 4.49s | 8.0 tps | 164K | $0.250 / $0.950 | |
| Healthy | 100% | 99.98% | 668ms | 12.9s | 26 tps | 164K | $0.500 / $2.15 | |
| Healthy | 100% | 99.12% | 704ms | 6.69s | 16 tps | 131K | $0.080 / $0.160 | |
| Healthy | 100% | 99.98% | 611ms | 4.78s | 19 tps | 131K | $0.050 / $0.100 | |
| Healthy | 100% | 99.44% | 819ms | 2.69s | 42 tps | 131K | $0.060 / $0.180 | |
| Healthy | 100% | 97.94% | 324ms | 2.15s | 20 tps | 131K | $0.400 / $0.400 | |
| Healthy | 100% | 99.86% | 625ms | 3.59s | 16 tps | 131K | $0.020 / $0.040 | |
| Healthy | 100% | 99.84% | 372ms | 1.93s | 48 tps | 1.0M | $0.200 / $0.800 | |
| Healthy | 100% | 99.87% | 447ms | 3.76s | 25 tps | 328K | $0.100 / $0.300 | |
| Healthy | 100% | 99.64% | 366ms | 3.00s | 7.0 tps | 164K | $0.180 / $0.180 | |
| Healthy | 100% | 100% | 379ms | 4.45s | 70 tps | 16K | $0.070 / $0.140 | |
| Healthy | 100% | 99.90% | 517ms | 8.80s | 32 tps | 197K | $0.250 / $1.00 | |
| Healthy | 100% | 100% | 229ms | 1.25s | 62 tps | 33K | $0.050 / $0.080 | |
| Healthy | 100% | 99.92% | 757ms | 4.95s | 28 tps | 262K | $0.450 / $2.25 | |
| Healthy | 100% | 99.77% | 1.05s | 9.31s | 14 tps | 262K | $0.750 / $3.50 | |
| Healthy | 100% | 99.83% | 843ms | 11.9s | 29 tps | 262K | $0.680 / $3.40 | |
| Healthy | 100% | 99.99% | 327ms | 8.27s | 20 tps | 131K | $1.00 / $1.00 | |
| Healthy | 100% | 100% | 363ms | 2.46s | 34 tps | 131K | $0.700 / $0.700 | |
| Healthy | 100% | 99.88% | 433ms | 1.48s | 121 tps | 131K | $0.150 / $0.600 | |
| Healthy | 100% | 99.77% | 272ms | 5.66s | 31 tps | 33K | $0.360 / $0.400 | |
| Healthy | 100% | 99.72% | 225ms | 2.22s | 78 tps | 41K | $0.120 / $0.500 | |
| Healthy | 100% | 99.29% | 349ms | 1.81s | 43 tps | 262K | $0.090 / $1.10 | |
| Healthy | 100% | 99.82% | 477ms | 1.95s | 87 tps | 262K | $0.290 / $2.40 | |
| Healthy | 100% | 98.81% | 349ms | 1.85s | 54 tps | 262K | $0.260 / $2.60 | |
| Healthy | 100% | 99.44% | 290ms | 1.75s | 103 tps | 262K | $0.140 / $1.00 | |
| Healthy | 100% | 98.59% | 1.33s | 14.7s | 16 tps | 262K | $0.320 / $3.20 | |
| Healthy | 100% | 96.56% | 646ms | 24.2s | 36 tps | 262K | $0.100 / $0.950 | |
| Healthy | 100% | 99.95% | 153ms | 902ms | 76 tps | 8K | $0.040 / $0.050 | |
Step 3.7 Flashdeepinfra | Healthy | 100% | 99.93% | 163ms | 6.18s | 77 tps | 262K | $0.200 / $1.15 |
| Healthy | 100% | 99.67% | 439ms | 1.80s | 93 tps | 524K | $0.950 / $4.05 | |
| Healthy | 100% | 99.83% | 424ms | 2.88s | 147 tps | 524K | $0.450 / $1.20 | |
| Healthy | 100% | 95.89% | 555ms | 10.5s | 80 tps | 1.0M | $1.00 / $3.00 | |
| Healthy | 100% | 99.97% | 589ms | 10.7s | 25 tps | 203K | $0.500 / $2.00 | |
| Healthy | 100% | 99.56% | 1.54s | 18.0s | 14 tps | 203K | $0.400 / $1.75 | |
| Healthy | 100% | 99.85% | 714ms | 11.4s | 41 tps | 203K | $0.600 / $2.08 | |
| Degraded | 99.99% | 98.97% | 651ms | 13.9s | 30 tps | 131K | $0.037 / $0.170 | |
| Healthy | 99.98% | 99.96% | 372ms | 2.88s | 25 tps | 41K | $0.080 / $0.280 | |
| Healthy | 99.93% | 97.31% | 712ms | 10.3s | 25 tps | 262K | $0.130 / $0.380 | |
| Healthy | 99.93% | 100% | 305ms | 1.81s | 15 tps | 131K | $0.050 / $0.150 | |
| Healthy | 99.91% | 99.80% | 689ms | 4.30s | 26 tps | 262K | $0.090 / $0.340 | |
| Healthy | 99.87% | 99.94% | 699ms | 8.22s | 77 tps | 262K | $0.080 / $0.200 | |
| Healthy | 99.81% | 99.71% | 456ms | 3.82s | 20 tps | 262K | $0.070 / $0.340 | |
| Healthy | 99.77% | 99.64% | 1.49s | 22.5s | 32 tps | 1.0M | $0.750 / $2.40 | |
| Healthy | 99.69% | 95.68% | 451ms | 5.84s | 37 tps | 41K | $0.120 / $0.240 | |
| Healthy | 99.60% | 99.41% | 826ms | 11.5s | 21 tps | 1.0M | $1.30 / $2.60 | |
| Healthy | 99.37% | 96.82% | 3.31s | 19.3s | 48 tps | 262K | $0.085 / $0.400 | |
| Healthy | 99.36% | 99.59% | 757ms | 2.83s | 30 tps | 1.0M | $0.090 / $0.180 | |
| Degraded | 99.35% | 98.10% | 814ms | 10.2s | 8.0 tps | 262K | $0.090 / $0.550 | |
| Healthy | 99.25% | 98.79% | 332ms | 5.27s | 29 tps | 131K | $0.019 / $0.030 | |
| Healthy | 99.17% | 99.14% | 1.52s | 39.4s | 23 tps | 524K | $0.280 / $1.10 | |
| Healthy | 99.01% | 99.90% | 255ms | 7.01s | 99 tps | 131K | $0.030 / $0.140 | |
| Healthy | 98.98% | 99.90% | 342ms | 4.67s | 33 tps | 203K | $0.060 / $0.400 | |
| Healthy | 98.94% | 98.71% | 656ms | 12.5s | 38 tps | 1.0M | $0.080 / $0.180 | |
| Healthy | 97.51% | 96.90% | 701ms | 7.24s | 14 tps | 131K | $0.100 / $0.320 | |
| Healthy | 97.50% | 99.21% | 1.69s | 21.5s | 19 tps | 203K | $1.05 / $3.50 | |
| Healthy | 96.05% | 99.53% | 482ms | 5.17s | 13 tps | 262K | $0.150 / $0.600 | |
| Healthy | 95.54% | 99.33% | 331ms | 11.0s | 8.0 tps | 262K | $0.450 / $3.00 | |
| Degraded | 94.59% | 97.22% | 1.22s | 6.74s | 12 tps | 262K | $0.200 / $0.880 | |
| Degraded | 94.55% | 95.62% | 2.00s | 14.9s | 128 tps | 262K | $0.050 / $0.200 | |
| Down | 89.22% | 98.10% | 445ms | 37.6s | 60 tps | 262K | $0.140 / $0.580 | |
| Down | 86.58% | 86.29% | 3.95s | 18.7s | 77 tps | 262K | $0.500 / $2.20 | |
| Down | 69.72% | 97.48% | 350ms | 1.78s | 42 tps | 262K | $0.100 / $0.150 | |
| Down | 67.27% | 91.97% | 9.94s | 30.0s | 10 tps | 164K | $0.320 / $0.890 | |
| Down | 65.73% | 94.49% | 429ms | 13.9s | 72 tps | 262K | $0.400 / $2.00 | |
| Down | — | 81.89% | 4.05s | 41.1s | 21 tps | 164K | $0.240 / $0.900 | |
| No data | — | 95.30% | 2.60s | 32.2s | 8.0 tps | 164K | $0.260 / $0.380 | |
| No data | — | 37.77% | 2.27s | 8.03s | 26 tps | 131K | $0.270 / $0.760 | |
| No data | — | 99.92% | 272ms | 739ms | 46 tps | 4K | $0.400 / $0.400 | |
| No data | — | 99.77% | 263ms | 9.65s | 169 tps | 131K | $0.300 / $1.20 | |
| No data | — | 67.85% | 5.32s | 24.6s | 22 tps | 197K | $0.380 / $1.70 | |
| No data | — | 97.52% | 254ms | 3.76s | 11 tps | 128K | $0.075 / $0.200 | |
| Degraded | — | 89.58% | 1.74s | 40.2s | 19 tps | 1.0M | $2.85 / $14.25 | |
| No data | — | 100% | 678ms | 2.11s | 49 tps | 262K | $0.230 / $2.30 | |
| Down | — | 95.67% | 1.47s | 70.1s | 21 tps | 262K | $0.300 / $1.00 | |
| No data | — | 96.17% | 1.92s | 15.6s | 15 tps | 262K | $2.00 / $6.00 | |
| No data | — | 99.88% | 215ms | 1.60s | 46 tps | 131K | $0.850 / $0.850 |
- DeepSeek V3.1100%Healthy24h 99.83%
- p50
- 946ms
- p99
- 4.49s
- Throughput
- 8.0 tps
- Context
- 164K
- $/Mtok
- $0.250 / $0.950
deepinfra/fp4fp4 - R1 0528100%Healthy24h 99.98%
- p50
- 668ms
- p99
- 12.9s
- Throughput
- 26 tps
- Context
- 164K
- $/Mtok
- $0.500 / $2.15
deepinfra/fp4fp4 - Gemma 3 27B100%Healthy24h 99.12%
- p50
- 704ms
- p99
- 6.69s
- Throughput
- 16 tps
- Context
- 131K
- $/Mtok
- $0.080 / $0.160
deepinfra/fp8fp8 - Gemma 3 4B100%Healthy24h 99.98%
- p50
- 611ms
- p99
- 4.78s
- Throughput
- 19 tps
- Context
- 131K
- $/Mtok
- $0.050 / $0.100
deepinfra/bf16bf16 - Ling-3.0-flash100%Healthy24h 99.44%
- p50
- 819ms
- p99
- 2.69s
- Throughput
- 42 tps
- Context
- 131K
- $/Mtok
- $0.060 / $0.180
deepinfra/bf16bf16 - Healthy24h 97.94%
- p50
- 324ms
- p99
- 2.15s
- Throughput
- 20 tps
- Context
- 131K
- $/Mtok
- $0.400 / $0.400
deepinfra/turbofp8 - Healthy24h 99.86%
- p50
- 625ms
- p99
- 3.59s
- Throughput
- 16 tps
- Context
- 131K
- $/Mtok
- $0.020 / $0.040
deepinfra/fp8fp8 - Llama 4 Maverick100%Healthy24h 99.84%
- p50
- 372ms
- p99
- 1.93s
- Throughput
- 48 tps
- Context
- 1.0M
- $/Mtok
- $0.200 / $0.800
deepinfra/basefp8 - Llama 4 Scout100%Healthy24h 99.87%
- p50
- 447ms
- p99
- 3.76s
- Throughput
- 25 tps
- Context
- 328K
- $/Mtok
- $0.100 / $0.300
deepinfra/fp8fp8 - Healthy24h 99.64%
- p50
- 366ms
- p99
- 3.00s
- Throughput
- 7.0 tps
- Context
- 164K
- $/Mtok
- $0.180 / $0.180
deepinfra/bf16bf16 - Phi 4100%Healthy24h 100%
- p50
- 379ms
- p99
- 4.45s
- Throughput
- 70 tps
- Context
- 16K
- $/Mtok
- $0.070 / $0.140
deepinfra/bf16bf16 - MiniMax M2.7100%Healthy24h 99.90%
- p50
- 517ms
- p99
- 8.80s
- Throughput
- 32 tps
- Context
- 197K
- $/Mtok
- $0.250 / $1.00
deepinfra/fp8fp8 - Mistral Small 3100%Healthy24h 100%
- p50
- 229ms
- p99
- 1.25s
- Throughput
- 62 tps
- Context
- 33K
- $/Mtok
- $0.050 / $0.080
deepinfra/fp8fp8 - Kimi K2.5100%Healthy24h 99.92%
- p50
- 757ms
- p99
- 4.95s
- Throughput
- 28 tps
- Context
- 262K
- $/Mtok
- $0.450 / $2.25
deepinfra/fp4fp4 - Kimi K2.6100%Healthy24h 99.77%
- p50
- 1.05s
- p99
- 9.31s
- Throughput
- 14 tps
- Context
- 262K
- $/Mtok
- $0.750 / $3.50
deepinfra/fp4fp4 - Kimi K2.7 Code100%Healthy24h 99.83%
- p50
- 843ms
- p99
- 11.9s
- Throughput
- 29 tps
- Context
- 262K
- $/Mtok
- $0.680 / $3.40
deepinfra/fp4fp4 - Healthy24h 99.99%
- p50
- 327ms
- p99
- 8.27s
- Throughput
- 20 tps
- Context
- 131K
- $/Mtok
- $1.00 / $1.00
deepinfra/fp8fp8 - Healthy24h 100%
- p50
- 363ms
- p99
- 2.46s
- Throughput
- 34 tps
- Context
- 131K
- $/Mtok
- $0.700 / $0.700
deepinfra/fp8fp8 - gpt-oss-120b100%Healthy24h 99.88%
- p50
- 433ms
- p99
- 1.48s
- Throughput
- 121 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
deepinfra/turbobf16 - Healthy24h 99.77%
- p50
- 272ms
- p99
- 5.66s
- Throughput
- 31 tps
- Context
- 33K
- $/Mtok
- $0.360 / $0.400
deepinfra/fp8fp8 - Qwen3 30B A3B100%Healthy24h 99.72%
- p50
- 225ms
- p99
- 2.22s
- Throughput
- 78 tps
- Context
- 41K
- $/Mtok
- $0.120 / $0.500
deepinfra/fp8fp8 - Healthy24h 99.29%
- p50
- 349ms
- p99
- 1.81s
- Throughput
- 43 tps
- Context
- 262K
- $/Mtok
- $0.090 / $1.10
deepinfra/fp8fp8 - Healthy24h 99.82%
- p50
- 477ms
- p99
- 1.95s
- Throughput
- 87 tps
- Context
- 262K
- $/Mtok
- $0.290 / $2.40
deepinfra/fp4fp4 - Qwen3.5-27B100%Healthy24h 98.81%
- p50
- 349ms
- p99
- 1.85s
- Throughput
- 54 tps
- Context
- 262K
- $/Mtok
- $0.260 / $2.60
deepinfra/fp8fp8 - Qwen3.5-35B-A3B100%Healthy24h 99.44%
- p50
- 290ms
- p99
- 1.75s
- Throughput
- 103 tps
- Context
- 262K
- $/Mtok
- $0.140 / $1.00
deepinfra/fp8fp8 - Qwen3.6 27B100%Healthy24h 98.59%
- p50
- 1.33s
- p99
- 14.7s
- Throughput
- 16 tps
- Context
- 262K
- $/Mtok
- $0.320 / $3.20
deepinfra/fp8fp8 - Qwen3.6 35B A3B100%Healthy24h 96.56%
- p50
- 646ms
- p99
- 24.2s
- Throughput
- 36 tps
- Context
- 262K
- $/Mtok
- $0.100 / $0.950
deepinfra/fp8fp8 - Healthy24h 99.95%
- p50
- 153ms
- p99
- 902ms
- Throughput
- 76 tps
- Context
- 8K
- $/Mtok
- $0.040 / $0.050
deepinfra/turbofp8 - Step 3.7 Flash100%Healthy24h 99.93%
- p50
- 163ms
- p99
- 6.18s
- Throughput
- 77 tps
- Context
- 262K
- $/Mtok
- $0.200 / $1.15
deepinfra - Inkling100%Healthy24h 99.67%
- p50
- 439ms
- p99
- 1.80s
- Throughput
- 93 tps
- Context
- 524K
- $/Mtok
- $0.950 / $4.05
deepinfra/fp8fp8 - Inkling Small100%Healthy24h 99.83%
- p50
- 424ms
- p99
- 2.88s
- Throughput
- 147 tps
- Context
- 524K
- $/Mtok
- $0.450 / $1.20
deepinfra/fp8fp8 - MiMo-V2.5-Pro100%Healthy24h 95.89%
- p50
- 555ms
- p99
- 10.5s
- Throughput
- 80 tps
- Context
- 1.0M
- $/Mtok
- $1.00 / $3.00
deepinfra/fp8fp8 - GLM 4.6100%Healthy24h 99.97%
- p50
- 589ms
- p99
- 10.7s
- Throughput
- 25 tps
- Context
- 203K
- $/Mtok
- $0.500 / $2.00
deepinfra/fp4fp4 - GLM 4.7100%Healthy24h 99.56%
- p50
- 1.54s
- p99
- 18.0s
- Throughput
- 14 tps
- Context
- 203K
- $/Mtok
- $0.400 / $1.75
deepinfra/fp4fp4 - GLM 5100%Healthy24h 99.85%
- p50
- 714ms
- p99
- 11.4s
- Throughput
- 41 tps
- Context
- 203K
- $/Mtok
- $0.600 / $2.08
deepinfra/fp4fp4 - gpt-oss-120b99.99%Degraded24h 98.97%
- p50
- 651ms
- p99
- 13.9s
- Throughput
- 30 tps
- Context
- 131K
- $/Mtok
- $0.037 / $0.170
deepinfra/bf16bf16 - Qwen3 32B99.98%Healthy24h 99.96%
- p50
- 372ms
- p99
- 2.88s
- Throughput
- 25 tps
- Context
- 41K
- $/Mtok
- $0.080 / $0.280
deepinfra/fp8fp8 - Gemma 4 31B99.93%Healthy24h 97.31%
- p50
- 712ms
- p99
- 10.3s
- Throughput
- 25 tps
- Context
- 262K
- $/Mtok
- $0.130 / $0.380
deepinfra/fp8fp8 - Gemma 3 12B99.93%Healthy24h 100%
- p50
- 305ms
- p99
- 1.81s
- Throughput
- 15 tps
- Context
- 131K
- $/Mtok
- $0.050 / $0.150
deepinfra/bf16bf16 - Gemma 4 31B99.91%Healthy24h 99.80%
- p50
- 689ms
- p99
- 4.30s
- Throughput
- 26 tps
- Context
- 262K
- $/Mtok
- $0.090 / $0.340
deepinfra/turbofp4 - Nemotron 3.5 Lightning99.87%Healthy24h 99.94%
- p50
- 699ms
- p99
- 8.22s
- Throughput
- 77 tps
- Context
- 262K
- $/Mtok
- $0.080 / $0.200
deepinfra/bf16bf16 - Gemma 4 26B A4B 99.81%Healthy24h 99.71%
- p50
- 456ms
- p99
- 3.82s
- Throughput
- 20 tps
- Context
- 262K
- $/Mtok
- $0.070 / $0.340
deepinfra/fp8fp8 - GLM 5.299.77%Healthy24h 99.64%
- p50
- 1.49s
- p99
- 22.5s
- Throughput
- 32 tps
- Context
- 1.0M
- $/Mtok
- $0.750 / $2.40
deepinfra/fp4fp4 - Qwen3 14B99.69%Healthy24h 95.68%
- p50
- 451ms
- p99
- 5.84s
- Throughput
- 37 tps
- Context
- 41K
- $/Mtok
- $0.120 / $0.240
deepinfra/fp8fp8 - DeepSeek V4 Pro 042399.60%Healthy24h 99.41%
- p50
- 826ms
- p99
- 11.5s
- Throughput
- 21 tps
- Context
- 1.0M
- $/Mtok
- $1.30 / $2.60
deepinfra/fp8fp8 - Nemotron 3 Super99.37%Healthy24h 96.82%
- p50
- 3.31s
- p99
- 19.3s
- Throughput
- 48 tps
- Context
- 262K
- $/Mtok
- $0.085 / $0.400
deepinfra/bf16bf16 - DeepSeek V4 Flash 042399.36%Healthy24h 99.59%
- p50
- 757ms
- p99
- 2.83s
- Throughput
- 30 tps
- Context
- 1.0M
- $/Mtok
- $0.090 / $0.180
deepinfra/fp8fp8 - Degraded24h 98.10%
- p50
- 814ms
- p99
- 10.2s
- Throughput
- 8.0 tps
- Context
- 262K
- $/Mtok
- $0.090 / $0.550
deepinfra/fp8fp8 - Mistral Nemo99.25%Healthy24h 98.79%
- p50
- 332ms
- p99
- 5.27s
- Throughput
- 29 tps
- Context
- 131K
- $/Mtok
- $0.019 / $0.030
deepinfra/fp8fp8 - MiniMax M399.17%Healthy24h 99.14%
- p50
- 1.52s
- p99
- 39.4s
- Throughput
- 23 tps
- Context
- 524K
- $/Mtok
- $0.280 / $1.10
deepinfra/fp8fp8 - gpt-oss-20b99.01%Healthy24h 99.90%
- p50
- 255ms
- p99
- 7.01s
- Throughput
- 99 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.140
deepinfra/bf16bf16 - GLM 4.7 Flash98.98%Healthy24h 99.90%
- p50
- 342ms
- p99
- 4.67s
- Throughput
- 33 tps
- Context
- 203K
- $/Mtok
- $0.060 / $0.400
deepinfra/bf16bf16 - DeepSeek V4 Flash 073198.94%Healthy24h 98.71%
- p50
- 656ms
- p99
- 12.5s
- Throughput
- 38 tps
- Context
- 1.0M
- $/Mtok
- $0.080 / $0.180
deepinfra/fp8fp8 - Llama 3.3 70B Instruct97.51%Healthy24h 96.90%
- p50
- 701ms
- p99
- 7.24s
- Throughput
- 14 tps
- Context
- 131K
- $/Mtok
- $0.100 / $0.320
deepinfra/turbofp8 - GLM 5.197.50%Healthy24h 99.21%
- p50
- 1.69s
- p99
- 21.5s
- Throughput
- 19 tps
- Context
- 203K
- $/Mtok
- $1.05 / $3.50
deepinfra/fp4fp4 - Healthy24h 99.53%
- p50
- 482ms
- p99
- 5.17s
- Throughput
- 13 tps
- Context
- 262K
- $/Mtok
- $0.150 / $0.600
deepinfra/fp8fp8 - Qwen3.5 397B A17B95.54%Healthy24h 99.33%
- p50
- 331ms
- p99
- 11.0s
- Throughput
- 8.0 tps
- Context
- 262K
- $/Mtok
- $0.450 / $3.00
deepinfra/fp8fp8 - Degraded24h 97.22%
- p50
- 1.22s
- p99
- 6.74s
- Throughput
- 12 tps
- Context
- 262K
- $/Mtok
- $0.200 / $0.880
deepinfra/fp8fp8 - Nemotron 3 Nano 30B A3B94.55%Degraded24h 95.62%
- p50
- 2.00s
- p99
- 14.9s
- Throughput
- 128 tps
- Context
- 262K
- $/Mtok
- $0.050 / $0.200
deepinfra/fp4fp4 - Hy389.22%Down24h 98.10%
- p50
- 445ms
- p99
- 37.6s
- Throughput
- 60 tps
- Context
- 262K
- $/Mtok
- $0.140 / $0.580
deepinfra/fp8fp8 - Nemotron 3 Ultra86.58%Down24h 86.29%
- p50
- 3.95s
- p99
- 18.7s
- Throughput
- 77 tps
- Context
- 262K
- $/Mtok
- $0.500 / $2.20
deepinfra/fp4fp4 - Qwen3.5-9B69.72%Down24h 97.48%
- p50
- 350ms
- p99
- 1.78s
- Throughput
- 42 tps
- Context
- 262K
- $/Mtok
- $0.100 / $0.150
deepinfra/bf16bf16 - DeepSeek V367.27%Down24h 91.97%
- p50
- 9.94s
- p99
- 30.0s
- Throughput
- 10 tps
- Context
- 164K
- $/Mtok
- $0.320 / $0.890
deepinfra/fp4fp4 - MiMo-V2.565.73%Down24h 94.49%
- p50
- 429ms
- p99
- 13.9s
- Throughput
- 72 tps
- Context
- 262K
- $/Mtok
- $0.400 / $2.00
deepinfra/bf16bf16 - Down24h 81.89%
- p50
- 4.05s
- p99
- 41.1s
- Throughput
- 21 tps
- Context
- 164K
- $/Mtok
- $0.240 / $0.900
deepinfra/fp4fp4 - No data24h 95.30%
- p50
- 2.60s
- p99
- 32.2s
- Throughput
- 8.0 tps
- Context
- 164K
- $/Mtok
- $0.260 / $0.380
deepinfra/fp4fp4 - No data24h 37.77%
- p50
- 2.27s
- p99
- 8.03s
- Throughput
- 26 tps
- Context
- 131K
- $/Mtok
- $0.270 / $0.760
deepinfra/ultrafp8 - No data24h 99.92%
- p50
- 272ms
- p99
- 739ms
- Throughput
- 46 tps
- Context
- 4K
- $/Mtok
- $0.400 / $0.400
deepinfra/fp16fp16 - No data24h 99.77%
- p50
- 263ms
- p99
- 9.65s
- Throughput
- 169 tps
- Context
- 131K
- $/Mtok
- $0.300 / $1.20
deepinfra/bf16bf16 - No data24h 67.85%
- p50
- 5.32s
- p99
- 24.6s
- Throughput
- 22 tps
- Context
- 197K
- $/Mtok
- $0.380 / $1.70
deepinfra/turbofp8 - No data24h 97.52%
- p50
- 254ms
- p99
- 3.76s
- Throughput
- 11 tps
- Context
- 128K
- $/Mtok
- $0.075 / $0.200
deepinfra/fp8fp8 - Degraded24h 89.58%
- p50
- 1.74s
- p99
- 40.2s
- Throughput
- 19 tps
- Context
- 1.0M
- $/Mtok
- $2.85 / $14.25
deepinfra/bf16bf16 - No data24h 100%
- p50
- 678ms
- p99
- 2.11s
- Throughput
- 49 tps
- Context
- 262K
- $/Mtok
- $0.230 / $2.30
deepinfra/fp8fp8 - Down24h 95.67%
- p50
- 1.47s
- p99
- 70.1s
- Throughput
- 21 tps
- Context
- 262K
- $/Mtok
- $0.300 / $1.00
deepinfra/turbofp4 - No data24h 96.17%
- p50
- 1.92s
- p99
- 15.6s
- Throughput
- 15 tps
- Context
- 262K
- $/Mtok
- $2.00 / $6.00
deepinfra/fp4fp4 - No data24h 99.88%
- p50
- 215ms
- p99
- 1.60s
- Throughput
- 46 tps
- Context
- 131K
- $/Mtok
- $0.850 / $0.850
deepinfra/fp8fp8
Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.