InferenceNet
18 endpoints · all healthy · worst uptime 100%
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 100% | 100% | 99.97% | 241ms | 1.83s | 121 tps | 1.0M | $0.103 / $0.600 | |
| Healthy | 100% | 100% | 100% | 99.97% | 238ms | 1.07s | 83 tps | 1.0M | $0.103 / $0.600 | |
| Healthy | 100% | 100% | 100% | 99.96% | 325ms | 2.13s | 113 tps | 1.0M | $0.080 / $0.550 | |
| Healthy | 100% | 100% | 100% | 99.97% | 273ms | 1.99s | 127 tps | 1.0M | $0.080 / $0.550 | |
| Healthy | 100% | 100% | 92.32% | 98.51% | 318ms | 1.45s | 139 tps | 128K | $0.030 / $0.150 | |
| Healthy | 100% | 100% | 96.28% | 97.79% | 401ms | 966ms | 157 tps | 128K | $0.030 / $0.150 | |
| Healthy | 100% | 97.22% | 98.28% | 98.73% | 943ms | 11.0s | 75 tps | 1.0M | $0.150 / $0.600 | |
| Healthy | 100% | 100% | 100% | 99.86% | 825ms | 3.56s | 56 tps | 1.0M | $0.500 / $22.00 | |
| Healthy | 100% | 100% | 100% | 99.91% | 1.14s | 4.94s | 31 tps | 1.0M | $0.234 / $15.00 | |
| Healthy | 100% | 100% | 100% | 99.95% | 1.04s | 4.27s | 33 tps | 1.0M | $0.234 / $15.00 | |
| Healthy | 100% | 100% | 100% | 99.94% | 842ms | 4.64s | 54 tps | 1.0M | $0.500 / $22.00 | |
| Healthy | 100% | 100% | 100% | 99.96% | 439ms | 6.26s | 109 tps | 1.0M | $0.080 / $3.60 | |
| Healthy | 100% | 100% | 100% | 99.96% | 603ms | 6.08s | 99 tps | 1.0M | $0.080 / $3.60 | |
| Healthy | 100% | 100% | 100% | 99.74% | 465ms | 6.88s | 89 tps | 1.0M | $0.108 / $0.350 | |
| Healthy | 100% | 100% | 100% | 99.70% | 343ms | 3.22s | 96 tps | 1.0M | $0.108 / $0.350 | |
| No data | — | 100% | 97.04% | 99.47% | — | — | — | 128K | $0.050 / $0.230 | |
| No data | — | 100% | 100% | 100% | — | — | — | 128K | $0.050 / $0.230 | |
| No data | — | 99.76% | 97.44% | 96.95% | 607ms | 9.95s | 59 tps | 1.0M | $0.150 / $0.600 |
- Healthy24h 100%
- 7d
- 100%
- 30d
- 99.97%
- p50
- 241ms
- p99
- 1.83s
- Throughput
- 121 tps
- Context
- 1.0M
- $/Mtok
- $0.103 / $0.600
inference-net/fp8fp8 - Healthy24h 100%
- 7d
- 100%
- 30d
- 99.97%
- p50
- 238ms
- p99
- 1.07s
- Throughput
- 83 tps
- Context
- 1.0M
- $/Mtok
- $0.103 / $0.600
inference-net/usfp8 - Healthy24h 100%
- 7d
- 100%
- 30d
- 99.96%
- p50
- 325ms
- p99
- 2.13s
- Throughput
- 113 tps
- Context
- 1.0M
- $/Mtok
- $0.080 / $0.550
inference-net/fp8fp8 - Healthy24h 100%
- 7d
- 100%
- 30d
- 99.97%
- p50
- 273ms
- p99
- 1.99s
- Throughput
- 127 tps
- Context
- 1.0M
- $/Mtok
- $0.080 / $0.550
inference-net/usfp8 - Healthy24h 100%
- 7d
- 92.32%
- 30d
- 98.51%
- p50
- 318ms
- p99
- 1.45s
- Throughput
- 139 tps
- Context
- 128K
- $/Mtok
- $0.030 / $0.150
inference-net/bf16bf16 - Healthy24h 100%
- 7d
- 96.28%
- 30d
- 97.79%
- p50
- 401ms
- p99
- 966ms
- Throughput
- 157 tps
- Context
- 128K
- $/Mtok
- $0.030 / $0.150
inference-net/usbf16 - Healthy24h 97.22%
- 7d
- 98.28%
- 30d
- 98.73%
- p50
- 943ms
- p99
- 11.0s
- Throughput
- 75 tps
- Context
- 1.0M
- $/Mtok
- $0.150 / $0.600
inference-net/fp4fp4 - Kimi K3100%Healthy24h 100%
- 7d
- 100%
- 30d
- 99.86%
- p50
- 825ms
- p99
- 3.56s
- Throughput
- 56 tps
- Context
- 1.0M
- $/Mtok
- $0.500 / $22.00
inference-net/fastfp4 - Kimi K3100%Healthy24h 100%
- 7d
- 100%
- 30d
- 99.91%
- p50
- 1.14s
- p99
- 4.94s
- Throughput
- 31 tps
- Context
- 1.0M
- $/Mtok
- $0.234 / $15.00
inference-net/fp4fp4 - Kimi K3100%Healthy24h 100%
- 7d
- 100%
- 30d
- 99.95%
- p50
- 1.04s
- p99
- 4.27s
- Throughput
- 33 tps
- Context
- 1.0M
- $/Mtok
- $0.234 / $15.00
inference-net/usfp4 - Kimi K3100%Healthy24h 100%
- 7d
- 100%
- 30d
- 99.94%
- p50
- 842ms
- p99
- 4.64s
- Throughput
- 54 tps
- Context
- 1.0M
- $/Mtok
- $0.500 / $22.00
inference-net/us/fastfp4 - GLM 5.3100%Healthy24h 100%
- 7d
- 100%
- 30d
- 99.96%
- p50
- 439ms
- p99
- 6.26s
- Throughput
- 109 tps
- Context
- 1.0M
- $/Mtok
- $0.080 / $3.60
inference-net/fp4fp4 - GLM 5.3100%Healthy24h 100%
- 7d
- 100%
- 30d
- 99.96%
- p50
- 603ms
- p99
- 6.08s
- Throughput
- 99 tps
- Context
- 1.0M
- $/Mtok
- $0.080 / $3.60
inference-net/usfp4 - GLM 5.3 Flash100%Healthy24h 100%
- 7d
- 100%
- 30d
- 99.74%
- p50
- 465ms
- p99
- 6.88s
- Throughput
- 89 tps
- Context
- 1.0M
- $/Mtok
- $0.108 / $0.350
inference-net/fp4fp4 - GLM 5.3 Flash100%Healthy24h 100%
- 7d
- 100%
- 30d
- 99.70%
- p50
- 343ms
- p99
- 3.22s
- Throughput
- 96 tps
- Context
- 1.0M
- $/Mtok
- $0.108 / $0.350
inference-net/usfp4 - No data24h 100%
- 7d
- 97.04%
- 30d
- 99.47%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 128K
- $/Mtok
- $0.050 / $0.230
inference-net/bf16bf16 - No data24h 100%
- 7d
- 100%
- 30d
- 100%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 128K
- $/Mtok
- $0.050 / $0.230
inference-net/usbf16 - No data24h 99.76%
- 7d
- 97.44%
- 30d
- 96.95%
- p50
- 607ms
- p99
- 9.95s
- Throughput
- 59 tps
- Context
- 1.0M
- $/Mtok
- $0.150 / $0.600
inference-net/fp4/usfp4
Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
Schematron V2 Small inference-net/bf16
Schematron V2 Turbo inference-net/bf16
Schematron V2 Turbo inference-net/us
GLM 5.3 inference-net/fp4
MiniMax M3.1 Flash inference-net/fp4/us
Kimi K3 inference-net/fp4
MiniMax M3.1 Flash inference-net/fp4
GLM 5.3 Flash inference-net/fp4
GLM 5.3 Flash inference-net/us
Kimi K3 inference-net/fast
DeepSeek V4.1 Flash 1017 inference-net/fp8
DeepSeek V4.1 Flash inference-net/fp8
Kimi K3 inference-net/us
GLM 5.3 inference-net/us
DeepSeek V4.1 Flash 1017 inference-net/us
Kimi K3 inference-net/us/fast
DeepSeek V4.1 Flash inference-net/us
Schematron V2 Small inference-net/us
Colour by daily mean uptime:≥ 95%90–95%< 90%no data
Through the live last bucket (raw rounds, updated every collection round) · 18 endpoints with data, sorted worst-first.