DeepInfra
80 endpoints · 3 unhealthy · worst uptime 81.53%
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 97.50% | 95.29% | 95.00% | 494ms | 2.69s | 29 tps | 164K | $0.320 / $0.890 | |
| Healthy | 100% | 99.91% | 99.84% | 99.91% | 3.27s | 7.87s | 6.0 tps | 164K | $0.250 / $0.950 | |
| Healthy | 100% | 99.94% | 99.94% | 99.94% | 816ms | 3.45s | 20 tps | 164K | $0.500 / $2.15 | |
| Healthy | 100% | 99.81% | 99.65% | 99.39% | 895ms | 5.21s | 63 tps | 1.0M | $1.30 / $2.60 | |
| Healthy | 100% | 99.04% | 99.57% | 99.26% | 1.35s | 17.5s | 51 tps | 1.0M | $1.30 / $2.60 | |
| Healthy | 100% | 99.38% | 99.39% | 99.46% | 1.62s | 9.47s | 21 tps | 131K | $0.080 / $0.160 | |
| Healthy | 100% | 100% | 100% | 100% | 686ms | 3.24s | 57 tps | 131K | $0.050 / $0.100 | |
| Healthy | 100% | 99.99% | 99.99% | 99.97% | 292ms | 1.42s | 45 tps | 4K | $0.400 / $0.400 | |
| Healthy | 100% | 100% | 99.97% | 99.98% | 726ms | 2.82s | 36 tps | 131K | $0.060 / $0.250 | |
| Healthy | 100% | 98.79% | 98.44% | 97.66% | 1.77s | 8.91s | 49 tps | 131K | $0.060 / $0.180 | |
| Healthy | 100% | 99.97% | 99.99% | 100% | 382ms | 1.83s | 183 tps | 262K | $0.060 / $0.180 | |
| Healthy | 100% | 99.95% | 99.81% | 99.82% | 1.23s | 11.1s | 45 tps | 131K | $0.060 / $0.180 | |
| Healthy | 100% | 99.55% | 97.01% | 94.90% | 341ms | 2.43s | 38 tps | 131K | $0.400 / $0.400 | |
| Healthy | 100% | 99.96% | 99.63% | 99.27% | 598ms | 3.15s | 31 tps | 131K | $0.020 / $0.040 | |
| Healthy | 100% | 99.94% | 99.92% | 99.91% | 704ms | 2.85s | 22 tps | 328K | $0.100 / $0.300 | |
| Healthy | 100% | 100% | 100% | 100% | — | — | — | 164K | $0.180 / $0.180 | |
| Healthy | 100% | 100% | 99.94% | 99.97% | 772ms | 3.13s | 147 tps | 131K | $0.300 / $1.20 | |
| Healthy | 100% | 100% | 100% | 99.98% | 2.62s | 4.35s | 44 tps | 16K | $0.070 / $0.140 | |
| Healthy | 100% | 99.99% | 99.99% | 99.99% | 318ms | 2.27s | 41 tps | 33K | $0.050 / $0.080 | |
| Healthy | 100% | 99.71% | 99.48% | 99.48% | 1.42s | 10.8s | 33 tps | 1.0M | $2.85 / $14.25 | |
| Healthy | 100% | 100% | 99.99% | 99.98% | 565ms | 5.30s | 20 tps | 131K | $1.00 / $1.00 | |
| Healthy | 100% | 99.99% | 99.99% | 100% | 551ms | 11.2s | 26 tps | 131K | $0.700 / $0.700 | |
| Healthy | 100% | 99.99% | 99.98% | 99.97% | 3.63s | 89.4s | 62 tps | 262K | $0.085 / $0.400 | |
| Healthy | 100% | 99.95% | 99.92% | 99.86% | 1.01s | 3.74s | 106 tps | 262K | $0.500 / $2.20 | |
| Healthy | 100% | 99.92% | 98.50% | 99.07% | 339ms | 2.65s | 60 tps | 131K | $0.037 / $0.170 | |
| Healthy | 100% | 99.94% | 99.98% | 99.97% | 466ms | 1.98s | 112 tps | 131K | $0.150 / $0.600 | |
| Healthy | 100% | 99.96% | 99.87% | 99.89% | 270ms | 2.38s | 86 tps | 131K | $0.030 / $0.140 | |
| Healthy | 100% | 99.88% | 97.68% | 99.00% | 565ms | 5.72s | 31 tps | 33K | $0.360 / $0.400 | |
| Healthy | 100% | 99.75% | 96.75% | 98.50% | 547ms | 8.87s | 22 tps | 41K | $0.120 / $0.240 | |
| Healthy | 100% | 99.99% | 99.98% | 99.84% | 493ms | 5.75s | 145 tps | 41K | $0.120 / $0.500 | |
| Healthy | 100% | 99.94% | 99.88% | 99.78% | 427ms | 37.3s | 25 tps | 41K | $0.080 / $0.280 | |
| Healthy | 100% | 98.49% | 96.01% | 96.19% | 818ms | 15.4s | 65 tps | 262K | $0.300 / $1.00 | |
| Healthy | 100% | 99.70% | 99.54% | 99.39% | 484ms | 2.76s | 125 tps | 262K | $0.090 / $1.10 | |
| Healthy | 100% | 99.97% | 99.98% | 98.79% | 592ms | 2.57s | 57 tps | 262K | $0.260 / $2.60 | |
| Healthy | 100% | 99.83% | 99.81% | 98.80% | 605ms | 2.91s | 45 tps | 262K | $0.140 / $1.00 | |
| Healthy | 100% | 99.47% | 98.86% | 97.33% | 1.05s | 23.4s | 39 tps | 262K | $0.450 / $3.00 | |
| Healthy | 100% | 99.80% | 97.50% | 95.76% | 901ms | 7.71s | 141 tps | 262K | $0.100 / $0.950 | |
| Healthy | 100% | 99.96% | 99.96% | 99.93% | 147ms | 1.50s | 83 tps | 8K | $0.040 / $0.050 | |
| Healthy | 100% | 99.84% | 99.83% | 99.55% | 882ms | 12.5s | 81 tps | 262K | $0.130 / $0.530 | |
| Healthy | 100% | 99.13% | 99.39% | 89.36% | 661ms | 3.59s | 79 tps | 524K | $0.950 / $4.05 | |
| Healthy | 100% | 98.35% | 96.41% | 94.23% | 1.08s | 8.09s | 44 tps | 1.0M | $0.140 / $0.280 | |
| Healthy | 100% | 99.89% | 99.81% | 98.27% | 1.82s | 22.9s | 32 tps | 1.0M | $0.430 / $0.870 | |
| Healthy | 100% | 98.09% | 93.18% | 95.60% | 1.51s | 8.27s | 14 tps | 203K | $0.400 / $1.75 | |
| Healthy | 100% | 98.24% | 99.51% | 98.83% | 1.17s | 11.7s | 42 tps | 1.0M | $0.075 / $0.250 | |
| Healthy | 100% | 99.95% | 99.94% | 99.92% | 993ms | 3.85s | 20 tps | 131K | $0.019 / $0.030 | |
| Healthy | 99.96% | 99.92% | 99.89% | 99.73% | 715ms | 7.09s | 42 tps | 1.0M | $0.060 / $0.180 | |
| Healthy | 99.95% | 99.95% | 99.92% | 99.93% | 1.63s | 4.95s | 19 tps | 131K | $0.050 / $0.150 | |
| Healthy | 99.92% | 99.58% | 99.09% | 99.05% | 1.46s | 8.21s | 17 tps | 164K | $0.260 / $0.380 | |
| Healthy | 99.88% | 99.86% | 98.78% | 96.58% | 1.39s | 16.0s | 26 tps | 262K | $0.150 / $1.88 | |
| Healthy | 99.87% | 99.96% | 99.94% | 98.66% | 929ms | 8.93s | 80 tps | 1.0M | $0.140 / $0.420 | |
| Healthy | 99.85% | 99.91% | 99.50% | 99.50% | 1.07s | 6.93s | 30 tps | 1.0M | $0.090 / $0.180 | |
| Healthy | 99.82% | 99.83% | 99.88% | 99.82% | 873ms | 6.03s | 32 tps | 128K | $0.075 / $0.200 | |
| Healthy | 99.75% | 99.74% | 99.68% | 95.96% | 1.47s | 10.5s | 79 tps | 1.0M | $0.216 / $0.647 | |
| Healthy | 99.59% | 99.66% | 99.62% | 97.99% | 1.54s | 7.59s | 9.0 tps | 262K | $0.100 / $0.150 | |
| Healthy | 99.48% | 99.88% | 99.77% | 91.35% | 910ms | 6.53s | 23 tps | 262K | $0.150 / $0.600 | |
| Healthy | 99.26% | 99.02% | 99.23% | 97.11% | 1.40s | 24.7s | 77 tps | 1.0M | $0.563 / $2.50 | |
| Healthy | 99.07% | 98.58% | 97.93% | 97.11% | 2.02s | 11.0s | 15 tps | 262K | $0.200 / $0.400 | |
| Healthy | 98.92% | 99.81% | 99.62% | 99.41% | 705ms | 10.5s | 32 tps | 262K | $0.070 / $0.340 | |
| Healthy | 98.68% | 96.74% | 96.66% | 95.87% | 1.86s | 7.22s | 16 tps | 262K | $0.200 / $0.880 | |
| Healthy | 98.50% | 98.45% | 97.23% | 98.01% | 561ms | 11.7s | 17 tps | 131K | $0.100 / $0.320 | |
| Degraded | 97.22% | 93.69% | 96.48% | 98.32% | 2.57s | 15.9s | 12 tps | 262K | $0.750 / $3.50 | |
| Healthy | 96.97% | 99.56% | 99.38% | 99.17% | 1.69s | 24.8s | 51 tps | 1.0M | $0.563 / $1.80 | |
| Down | 95.12% | 90.24% | 84.27% | 90.57% | 4.66s | 10.9s | 6.0 tps | 262K | $0.090 / $0.550 | |
| Down | 81.53% | 97.19% | 98.73% | 99.00% | 605ms | 5.57s | 34 tps | 262K | $0.090 / $0.340 | |
| No data | — | — | — | — | — | — | — | 1.0M | $0.112 / $0.336 | |
| No data | — | 99.78% | 99.58% | 98.86% | 1.32s | 74.6s | 7.0 tps | 524K | $0.280 / $1.10 | |
| No data | — | — | — | — | — | — | — | 1.0M | $2.28 / $11.40 | |
| No data | — | 86.79% | 95.22% | 98.49% | 5.43s | 69.0s | 49 tps | 262K | $0.050 / $0.200 | |
| No data | — | 100% | 100% | 100% | 397ms | 1.05s | 227 tps | 131K | $0.200 / $0.200 | |
| No data | — | 99.98% | 99.95% | 99.83% | 693ms | 2.65s | 217 tps | 262K | $0.060 / $0.160 | |
| No data | — | — | — | — | — | — | — | 131K | $0.030 / $0.136 | |
| No data | — | — | — | — | — | — | — | 131K | $0.024 / $0.112 | |
| No data | — | 99.57% | 99.63% | 97.67% | 424ms | 3.35s | 68 tps | 262K | $0.320 / $3.20 | |
| No data | — | 99.62% | 99.75% | 99.46% | 1.75s | 13.9s | 71 tps | 262K | $2.00 / $6.00 | |
| No data | — | 99.77% | 99.72% | 99.31% | 287ms | 3.05s | 37 tps | 131K | $0.850 / $0.850 | |
| No data | — | 98.04% | 99.75% | 99.75% | 2.46s | 4.71s | 15 tps | 1.0M | $0.834 / $2.50 | |
| No data | — | 99.98% | 100% | 96.45% | 898ms | 4.55s | 127 tps | 524K | $0.450 / $1.20 | |
| No data | — | 99.81% | 99.78% | 99.78% | 1.06s | 3.21s | 18 tps | 203K | $0.500 / $2.00 | |
| No data | — | — | — | — | — | — | — | 1.0M | $0.060 / $0.200 | |
| No data | — | — | — | — | — | — | — | 1.0M | $0.450 / $2.00 |
- DeepSeek V3100%Healthy24h 97.50%
- 7d
- 95.29%
- 30d
- 95.00%
- p50
- 494ms
- p99
- 2.69s
- Throughput
- 29 tps
- Context
- 164K
- $/Mtok
- $0.320 / $0.890
deepinfra/fp4fp4 - DeepSeek V3.1100%Healthy24h 99.91%
- 7d
- 99.84%
- 30d
- 99.91%
- p50
- 3.27s
- p99
- 7.87s
- Throughput
- 6.0 tps
- Context
- 164K
- $/Mtok
- $0.250 / $0.950
deepinfra/fp4fp4 - R1 0528100%Healthy24h 99.94%
- 7d
- 99.94%
- 30d
- 99.94%
- p50
- 816ms
- p99
- 3.45s
- Throughput
- 20 tps
- Context
- 164K
- $/Mtok
- $0.500 / $2.15
deepinfra/fp4fp4 - Healthy24h 99.81%
- 7d
- 99.65%
- 30d
- 99.39%
- p50
- 895ms
- p99
- 5.21s
- Throughput
- 63 tps
- Context
- 1.0M
- $/Mtok
- $1.30 / $2.60
deepinfra/fp8fp8 - Healthy24h 99.04%
- 7d
- 99.57%
- 30d
- 99.26%
- p50
- 1.35s
- p99
- 17.5s
- Throughput
- 51 tps
- Context
- 1.0M
- $/Mtok
- $1.30 / $2.60
deepinfra/fp8fp8 - Gemma 3 27B100%Healthy24h 99.38%
- 7d
- 99.39%
- 30d
- 99.46%
- p50
- 1.62s
- p99
- 9.47s
- Throughput
- 21 tps
- Context
- 131K
- $/Mtok
- $0.080 / $0.160
deepinfra/fp8fp8 - Gemma 3 4B100%Healthy24h 100%
- 7d
- 100%
- 30d
- 100%
- p50
- 686ms
- p99
- 3.24s
- Throughput
- 57 tps
- Context
- 131K
- $/Mtok
- $0.050 / $0.100
deepinfra/bf16bf16 - MythoMax 13B100%Healthy24h 99.99%
- 7d
- 99.99%
- 30d
- 99.97%
- p50
- 292ms
- p99
- 1.42s
- Throughput
- 45 tps
- Context
- 4K
- $/Mtok
- $0.400 / $0.400
deepinfra/fp16fp16 - Granite 4.2 8B100%Healthy24h 100%
- 7d
- 99.97%
- 30d
- 99.98%
- p50
- 726ms
- p99
- 2.82s
- Throughput
- 36 tps
- Context
- 131K
- $/Mtok
- $0.060 / $0.250
deepinfra/bf16bf16 - Ling 3.0 Flash100%Healthy24h 98.79%
- 7d
- 98.44%
- 30d
- 97.66%
- p50
- 1.77s
- p99
- 8.91s
- Throughput
- 49 tps
- Context
- 131K
- $/Mtok
- $0.060 / $0.180
deepinfra/bf16bf16 - Healthy24h 99.97%
- 7d
- 99.99%
- 30d
- 100%
- p50
- 382ms
- p99
- 1.83s
- Throughput
- 183 tps
- Context
- 262K
- $/Mtok
- $0.060 / $0.180
deepinfra/fp4fp4 - Healthy24h 99.95%
- 7d
- 99.81%
- 30d
- 99.82%
- p50
- 1.23s
- p99
- 11.1s
- Throughput
- 45 tps
- Context
- 131K
- $/Mtok
- $0.060 / $0.180
deepinfra/fp16fp16 - Healthy24h 99.55%
- 7d
- 97.01%
- 30d
- 94.90%
- p50
- 341ms
- p99
- 2.43s
- Throughput
- 38 tps
- Context
- 131K
- $/Mtok
- $0.400 / $0.400
deepinfra/turbofp8 - Healthy24h 99.96%
- 7d
- 99.63%
- 30d
- 99.27%
- p50
- 598ms
- p99
- 3.15s
- Throughput
- 31 tps
- Context
- 131K
- $/Mtok
- $0.020 / $0.040
deepinfra/fp8fp8 - Llama 4 Scout100%Healthy24h 99.94%
- 7d
- 99.92%
- 30d
- 99.91%
- p50
- 704ms
- p99
- 2.85s
- Throughput
- 22 tps
- Context
- 328K
- $/Mtok
- $0.100 / $0.300
deepinfra/fp8fp8 - Healthy24h 100%
- 7d
- 100%
- 30d
- 100%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 164K
- $/Mtok
- $0.180 / $0.180
deepinfra/bf16bf16 - Muse Glimmer 30B100%Healthy24h 100%
- 7d
- 99.94%
- 30d
- 99.97%
- p50
- 772ms
- p99
- 3.13s
- Throughput
- 147 tps
- Context
- 131K
- $/Mtok
- $0.300 / $1.20
deepinfra/bf16bf16 - Phi 4100%Healthy24h 100%
- 7d
- 100%
- 30d
- 99.98%
- p50
- 2.62s
- p99
- 4.35s
- Throughput
- 44 tps
- Context
- 16K
- $/Mtok
- $0.070 / $0.140
deepinfra/bf16bf16 - Mistral Small 3100%Healthy24h 99.99%
- 7d
- 99.99%
- 30d
- 99.99%
- p50
- 318ms
- p99
- 2.27s
- Throughput
- 41 tps
- Context
- 33K
- $/Mtok
- $0.050 / $0.080
deepinfra/fp8fp8 - Kimi K3100%Healthy24h 99.71%
- 7d
- 99.48%
- 30d
- 99.48%
- p50
- 1.42s
- p99
- 10.8s
- Throughput
- 33 tps
- Context
- 1.0M
- $/Mtok
- $2.85 / $14.25
deepinfra/mxfp4mxfp4 - Healthy24h 100%
- 7d
- 99.99%
- 30d
- 99.98%
- p50
- 565ms
- p99
- 5.30s
- Throughput
- 20 tps
- Context
- 131K
- $/Mtok
- $1.00 / $1.00
deepinfra/fp8fp8 - Healthy24h 99.99%
- 7d
- 99.99%
- 30d
- 100%
- p50
- 551ms
- p99
- 11.2s
- Throughput
- 26 tps
- Context
- 131K
- $/Mtok
- $0.700 / $0.700
deepinfra/fp8fp8 - Nemotron 3 Super100%Healthy24h 99.99%
- 7d
- 99.98%
- 30d
- 99.97%
- p50
- 3.63s
- p99
- 89.4s
- Throughput
- 62 tps
- Context
- 262K
- $/Mtok
- $0.085 / $0.400
deepinfra/bf16bf16 - Nemotron 3 Ultra100%Healthy24h 99.95%
- 7d
- 99.92%
- 30d
- 99.86%
- p50
- 1.01s
- p99
- 3.74s
- Throughput
- 106 tps
- Context
- 262K
- $/Mtok
- $0.500 / $2.20
deepinfra/fp4fp4 - gpt-oss-120b100%Healthy24h 99.92%
- 7d
- 98.50%
- 30d
- 99.07%
- p50
- 339ms
- p99
- 2.65s
- Throughput
- 60 tps
- Context
- 131K
- $/Mtok
- $0.037 / $0.170
deepinfra/bf16bf16 - gpt-oss-120b100%Healthy24h 99.94%
- 7d
- 99.98%
- 30d
- 99.97%
- p50
- 466ms
- p99
- 1.98s
- Throughput
- 112 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
deepinfra/turbobf16 - gpt-oss-20b100%Healthy24h 99.96%
- 7d
- 99.87%
- 30d
- 99.89%
- p50
- 270ms
- p99
- 2.38s
- Throughput
- 86 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.140
deepinfra/bf16bf16 - Healthy24h 99.88%
- 7d
- 97.68%
- 30d
- 99.00%
- p50
- 565ms
- p99
- 5.72s
- Throughput
- 31 tps
- Context
- 33K
- $/Mtok
- $0.360 / $0.400
deepinfra/fp8fp8 - Qwen3 14B100%Healthy24h 99.75%
- 7d
- 96.75%
- 30d
- 98.50%
- p50
- 547ms
- p99
- 8.87s
- Throughput
- 22 tps
- Context
- 41K
- $/Mtok
- $0.120 / $0.240
deepinfra/fp8fp8 - Qwen3 30B A3B100%Healthy24h 99.99%
- 7d
- 99.98%
- 30d
- 99.84%
- p50
- 493ms
- p99
- 5.75s
- Throughput
- 145 tps
- Context
- 41K
- $/Mtok
- $0.120 / $0.500
deepinfra/fp8fp8 - Qwen3 32B100%Healthy24h 99.94%
- 7d
- 99.88%
- 30d
- 99.78%
- p50
- 427ms
- p99
- 37.3s
- Throughput
- 25 tps
- Context
- 41K
- $/Mtok
- $0.080 / $0.280
deepinfra/fp8fp8 - Healthy24h 98.49%
- 7d
- 96.01%
- 30d
- 96.19%
- p50
- 818ms
- p99
- 15.4s
- Throughput
- 65 tps
- Context
- 262K
- $/Mtok
- $0.300 / $1.00
deepinfra/turbofp4 - Healthy24h 99.70%
- 7d
- 99.54%
- 30d
- 99.39%
- p50
- 484ms
- p99
- 2.76s
- Throughput
- 125 tps
- Context
- 262K
- $/Mtok
- $0.090 / $1.10
deepinfra/fp8fp8 - Qwen3.5-27B100%Healthy24h 99.97%
- 7d
- 99.98%
- 30d
- 98.79%
- p50
- 592ms
- p99
- 2.57s
- Throughput
- 57 tps
- Context
- 262K
- $/Mtok
- $0.260 / $2.60
deepinfra/fp8fp8 - Qwen3.5-35B-A3B100%Healthy24h 99.83%
- 7d
- 99.81%
- 30d
- 98.80%
- p50
- 605ms
- p99
- 2.91s
- Throughput
- 45 tps
- Context
- 262K
- $/Mtok
- $0.140 / $1.00
deepinfra/fp8fp8 - Healthy24h 99.47%
- 7d
- 98.86%
- 30d
- 97.33%
- p50
- 1.05s
- p99
- 23.4s
- Throughput
- 39 tps
- Context
- 262K
- $/Mtok
- $0.450 / $3.00
deepinfra/fp8fp8 - Qwen3.6 35B A3B100%Healthy24h 99.80%
- 7d
- 97.50%
- 30d
- 95.76%
- p50
- 901ms
- p99
- 7.71s
- Throughput
- 141 tps
- Context
- 262K
- $/Mtok
- $0.100 / $0.950
deepinfra/fp8fp8 - Healthy24h 99.96%
- 7d
- 99.96%
- 30d
- 99.93%
- p50
- 147ms
- p99
- 1.50s
- Throughput
- 83 tps
- Context
- 8K
- $/Mtok
- $0.040 / $0.050
deepinfra/turbofp8 - Hy3100%Healthy24h 99.84%
- 7d
- 99.83%
- 30d
- 99.55%
- p50
- 882ms
- p99
- 12.5s
- Throughput
- 81 tps
- Context
- 262K
- $/Mtok
- $0.130 / $0.530
deepinfra/fp4fp4 - Inkling100%Healthy24h 99.13%
- 7d
- 99.39%
- 30d
- 89.36%
- p50
- 661ms
- p99
- 3.59s
- Throughput
- 79 tps
- Context
- 524K
- $/Mtok
- $0.950 / $4.05
deepinfra/fp8fp8 - MiMo-V2.6-Flash100%Healthy24h 98.35%
- 7d
- 96.41%
- 30d
- 94.23%
- p50
- 1.08s
- p99
- 8.09s
- Throughput
- 44 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
deepinfra/fp8fp8 - MiMo-V2.6-Pro100%Healthy24h 99.89%
- 7d
- 99.81%
- 30d
- 98.27%
- p50
- 1.82s
- p99
- 22.9s
- Throughput
- 32 tps
- Context
- 1.0M
- $/Mtok
- $0.430 / $0.870
deepinfra/fp8fp8 - GLM 4.7100%Healthy24h 98.09%
- 7d
- 93.18%
- 30d
- 95.60%
- p50
- 1.51s
- p99
- 8.27s
- Throughput
- 14 tps
- Context
- 203K
- $/Mtok
- $0.400 / $1.75
deepinfra/fp4fp4 - GLM 5.3 Flash100%Healthy24h 98.24%
- 7d
- 99.51%
- 30d
- 98.83%
- p50
- 1.17s
- p99
- 11.7s
- Throughput
- 42 tps
- Context
- 1.0M
- $/Mtok
- $0.075 / $0.250
deepinfra/fp4fp4 - Mistral Nemo100%Healthy24h 99.95%
- 7d
- 99.94%
- 30d
- 99.92%
- p50
- 993ms
- p99
- 3.85s
- Throughput
- 20 tps
- Context
- 131K
- $/Mtok
- $0.019 / $0.030
deepinfra/fp8fp8 - DeepSeek V4 Flash 073199.96%Healthy24h 99.92%
- 7d
- 99.89%
- 30d
- 99.73%
- p50
- 715ms
- p99
- 7.09s
- Throughput
- 42 tps
- Context
- 1.0M
- $/Mtok
- $0.060 / $0.180
deepinfra/fp8fp8 - Gemma 3 12B99.95%Healthy24h 99.95%
- 7d
- 99.92%
- 30d
- 99.93%
- p50
- 1.63s
- p99
- 4.95s
- Throughput
- 19 tps
- Context
- 131K
- $/Mtok
- $0.050 / $0.150
deepinfra/bf16bf16 - DeepSeek V3.299.92%Healthy24h 99.58%
- 7d
- 99.09%
- 30d
- 99.05%
- p50
- 1.46s
- p99
- 8.21s
- Throughput
- 17 tps
- Context
- 164K
- $/Mtok
- $0.260 / $0.380
deepinfra/fp4fp4 - Qwen3.8 27B99.88%Healthy24h 99.86%
- 7d
- 98.78%
- 30d
- 96.58%
- p50
- 1.39s
- p99
- 16.0s
- Throughput
- 26 tps
- Context
- 262K
- $/Mtok
- $0.150 / $1.88
deepinfra/bf16bf16 - DeepSeek V4.1 Flash99.87%Healthy24h 99.96%
- 7d
- 99.94%
- 30d
- 98.66%
- p50
- 929ms
- p99
- 8.93s
- Throughput
- 80 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.420
deepinfra/fp8fp8 - DeepSeek V4 Flash 042399.85%Healthy24h 99.91%
- 7d
- 99.50%
- 30d
- 99.50%
- p50
- 1.07s
- p99
- 6.93s
- Throughput
- 30 tps
- Context
- 1.0M
- $/Mtok
- $0.090 / $0.180
deepinfra/fp8fp8 - Mistral Small 3.2 24B99.82%Healthy24h 99.83%
- 7d
- 99.88%
- 30d
- 99.82%
- p50
- 873ms
- p99
- 6.03s
- Throughput
- 32 tps
- Context
- 128K
- $/Mtok
- $0.075 / $0.200
deepinfra/fp8fp8 - Healthy24h 99.74%
- 7d
- 99.68%
- 30d
- 95.96%
- p50
- 1.47s
- p99
- 10.5s
- Throughput
- 79 tps
- Context
- 1.0M
- $/Mtok
- $0.216 / $0.647
deepinfra/fp8fp8 - Qwen3.5-9B99.59%Healthy24h 99.66%
- 7d
- 99.62%
- 30d
- 97.99%
- p50
- 1.54s
- p99
- 7.59s
- Throughput
- 9.0 tps
- Context
- 262K
- $/Mtok
- $0.100 / $0.150
deepinfra/bf16bf16 - Healthy24h 99.88%
- 7d
- 99.77%
- 30d
- 91.35%
- p50
- 910ms
- p99
- 6.53s
- Throughput
- 23 tps
- Context
- 262K
- $/Mtok
- $0.150 / $0.600
deepinfra/fp8fp8 - GLM 5.399.26%Healthy24h 99.02%
- 7d
- 99.23%
- 30d
- 97.11%
- p50
- 1.40s
- p99
- 24.7s
- Throughput
- 77 tps
- Context
- 1.0M
- $/Mtok
- $0.563 / $2.50
deepinfra/fp4fp4 - Gemma 4 31B99.07%Healthy24h 98.58%
- 7d
- 97.93%
- 30d
- 97.11%
- p50
- 2.02s
- p99
- 11.0s
- Throughput
- 15 tps
- Context
- 262K
- $/Mtok
- $0.200 / $0.400
deepinfra/fp8fp8 - Gemma 4 26B A4B 98.92%Healthy24h 99.81%
- 7d
- 99.62%
- 30d
- 99.41%
- p50
- 705ms
- p99
- 10.5s
- Throughput
- 32 tps
- Context
- 262K
- $/Mtok
- $0.070 / $0.340
deepinfra/fp8fp8 - Healthy24h 96.74%
- 7d
- 96.66%
- 30d
- 95.87%
- p50
- 1.86s
- p99
- 7.22s
- Throughput
- 16 tps
- Context
- 262K
- $/Mtok
- $0.200 / $0.880
deepinfra/fp8fp8 - Llama 3.3 70B Instruct98.50%Healthy24h 98.45%
- 7d
- 97.23%
- 30d
- 98.01%
- p50
- 561ms
- p99
- 11.7s
- Throughput
- 17 tps
- Context
- 131K
- $/Mtok
- $0.100 / $0.320
deepinfra/turbofp8 - Kimi K2.697.22%Degraded24h 93.69%
- 7d
- 96.48%
- 30d
- 98.32%
- p50
- 2.57s
- p99
- 15.9s
- Throughput
- 12 tps
- Context
- 262K
- $/Mtok
- $0.750 / $3.50
deepinfra/fp4fp4 - GLM 5.296.97%Healthy24h 99.56%
- 7d
- 99.38%
- 30d
- 99.17%
- p50
- 1.69s
- p99
- 24.8s
- Throughput
- 51 tps
- Context
- 1.0M
- $/Mtok
- $0.563 / $1.80
deepinfra/fp4fp4 - Down24h 90.24%
- 7d
- 84.27%
- 30d
- 90.57%
- p50
- 4.66s
- p99
- 10.9s
- Throughput
- 6.0 tps
- Context
- 262K
- $/Mtok
- $0.090 / $0.550
deepinfra/fp8fp8 - Gemma 4 31B81.53%Down24h 97.19%
- 7d
- 98.73%
- 30d
- 99.00%
- p50
- 605ms
- p99
- 5.57s
- Throughput
- 34 tps
- Context
- 262K
- $/Mtok
- $0.090 / $0.340
deepinfra/turbofp4 - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.112 / $0.336
deepinfra/fp8fp8 - No data24h 99.78%
- 7d
- 99.58%
- 30d
- 98.86%
- p50
- 1.32s
- p99
- 74.6s
- Throughput
- 7.0 tps
- Context
- 524K
- $/Mtok
- $0.280 / $1.10
deepinfra/fp8fp8 - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $2.28 / $11.40
deepinfra/bf16bf16 - No data24h 86.79%
- 7d
- 95.22%
- 30d
- 98.49%
- p50
- 5.43s
- p99
- 69.0s
- Throughput
- 49 tps
- Context
- 262K
- $/Mtok
- $0.050 / $0.200
deepinfra/fp4fp4 - No data24h 100%
- 7d
- 100%
- 30d
- 100%
- p50
- 397ms
- p99
- 1.05s
- Throughput
- 227 tps
- Context
- 131K
- $/Mtok
- $0.200 / $0.200
deepinfra/bf16bf16 - No data24h 99.98%
- 7d
- 99.95%
- 30d
- 99.83%
- p50
- 693ms
- p99
- 2.65s
- Throughput
- 217 tps
- Context
- 262K
- $/Mtok
- $0.060 / $0.160
deepinfra/bf16bf16 - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.030 / $0.136
deepinfra/bf16bf16 - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.024 / $0.112
deepinfra/bf16bf16 - No data24h 99.57%
- 7d
- 99.63%
- 30d
- 97.67%
- p50
- 424ms
- p99
- 3.35s
- Throughput
- 68 tps
- Context
- 262K
- $/Mtok
- $0.320 / $3.20
deepinfra/fp8fp8 - No data24h 99.62%
- 7d
- 99.75%
- 30d
- 99.46%
- p50
- 1.75s
- p99
- 13.9s
- Throughput
- 71 tps
- Context
- 262K
- $/Mtok
- $2.00 / $6.00
deepinfra/fp4fp4 - No data24h 99.77%
- 7d
- 99.72%
- 30d
- 99.31%
- p50
- 287ms
- p99
- 3.05s
- Throughput
- 37 tps
- Context
- 131K
- $/Mtok
- $0.850 / $0.850
deepinfra/fp8fp8 - No data24h 98.04%
- 7d
- 99.75%
- 30d
- 99.75%
- p50
- 2.46s
- p99
- 4.71s
- Throughput
- 15 tps
- Context
- 1.0M
- $/Mtok
- $0.834 / $2.50
deepinfra/fp8fp8 - No data24h 99.98%
- 7d
- 100%
- 30d
- 96.45%
- p50
- 898ms
- p99
- 4.55s
- Throughput
- 127 tps
- Context
- 524K
- $/Mtok
- $0.450 / $1.20
deepinfra/fp8fp8 - No data24h 99.81%
- 7d
- 99.78%
- 30d
- 99.78%
- p50
- 1.06s
- p99
- 3.21s
- Throughput
- 18 tps
- Context
- 203K
- $/Mtok
- $0.500 / $2.00
deepinfra/fp4fp4 - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.060 / $0.200
deepinfra/fp4fp4 - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.450 / $2.00
deepinfra/fp4fp4
Measured 1m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
Qwen3 235B A22B Instruct 2507 deepinfra/fp8
GLM 4.7 deepinfra/fp4
Kimi K2.6 deepinfra/fp4
Nemotron 3 Nano 30B A3B deepinfra/fp4
Qwen3 VL 235B A22B Instruct deepinfra/fp8
Qwen3 Coder 480B A35B deepinfra/turbo
MiMo-V2.6-Flash deepinfra/fp8
Gemma 4 31B deepinfra/fp8
Gemma 4 31B deepinfra/turbo
Qwen3 14B deepinfra/fp8
Llama 3.3 70B Instruct deepinfra/turbo
DeepSeek V3 deepinfra/fp4
Qwen3.6 27B deepinfra/fp8
Gemma 3 27B deepinfra/fp8
DeepSeek V4 Pro 0813 deepinfra/fp8
GLM 5.3 Flash deepinfra/fp4
Ling 3.0 Flash deepinfra/bf16
Llama 3.1 70B Instruct deepinfra/turbo
GLM 5.3 deepinfra/fp4
Kimi K3 deepinfra/mxfp4
Inkling deepinfra/fp8
DeepSeek V3.2 deepinfra/fp4
Qwen3.5-9B deepinfra/bf16
MiniMax M3 deepinfra/fp8
Qwen3.5-35B-A3B deepinfra/fp8
Qwen3.6 35B A3B deepinfra/fp8
Qwen3.5 397B A17B deepinfra/fp8
Qwen3 32B deepinfra/fp8
Qwen3 Next 80B A3B Instruct deepinfra/fp8
Qwen3.8 27B deepinfra/bf16
GLM 4.6 deepinfra/fp4
GLM 5.2 deepinfra/fp4
DeepSeek V4 Flash Vision Exp deepinfra/fp8
Llama 4 Scout deepinfra/fp8
Qwen2.5 72B Instruct deepinfra/fp8
DeepSeek V4 Flash 0423 deepinfra/fp8
DeepSeek V4 Pro 0423 deepinfra/fp8
Llama 3.1 Euryale 70B v2.2 deepinfra/fp8
Hy3 deepinfra/fp4
Mistral Small 3.2 24B deepinfra/fp8
Mistral Nemo deepinfra/fp8
Mistral Small 3 deepinfra/fp8
Qwen3 VL 30B A3B Instruct deepinfra/fp8
Gemma 4 26B A4B deepinfra/fp8
gpt-oss-20b deepinfra/bf16
R1 0528 deepinfra/fp4
Granite 4.2 8B deepinfra/bf16
gpt-oss-120b deepinfra/bf16
Nemotron 3 Ultra deepinfra/fp4
DeepSeek V3.1 deepinfra/fp4
Ling 3.0 Flash VL deepinfra/fp16
Hy4 preview deepinfra/fp8
MiMo-V2.6-Pro deepinfra/fp8
MythoMax 13B deepinfra/fp16
Llama 3 8B Lunaris deepinfra/turbo
Muse Glimmer 30B deepinfra/bf16
gpt-oss-120b deepinfra/turbo
Gemma 3 12B deepinfra/bf16
Qwen3.5-27B deepinfra/fp8
Qwen3 30B A3B deepinfra/fp8
DeepSeek V4 Flash 0731 deepinfra/fp8
Llama 3.1 8B Instruct deepinfra/fp8
DeepSeek V4.1 Flash deepinfra/fp8
Nemotron 3 Super deepinfra/bf16
Hermes 3 70B Instruct deepinfra/fp8
Inkling Small deepinfra/fp8
Nemotron 3.5 Lightning deepinfra/bf16
Gemma 3 4B deepinfra/bf16
Llama Guard 4 12B deepinfra/bf16
Phi 4 deepinfra/bf16
Hermes 3 405B Instruct deepinfra/fp8
Qwen3.8 2.4T A95B deepinfra/fp4
Ling 3.0 Flash Fin deepinfra/fp4
Nemotron 3.5 Content Safety deepinfra/bf16
GLM 5.3 Flash (batch) deepinfra/fp4
GLM 5.3 (batch) deepinfra/fp4
DeepSeek V4.1 Flash (batch) deepinfra/fp8
Kimi K3 (batch) deepinfra/bf16
gpt-oss-20b (batch) deepinfra/bf16
gpt-oss-120b (batch) deepinfra/bf16
Colour by hourly mean uptime:≥ 95%90–95%< 90%no data
Through the live last bucket (raw rounds, updated every collection round) · 80 endpoints with data, sorted worst-first.