InferenceNet
22 models served.
| Model | Agent Index | Input | Output | Agent $/M | Uptime 24h | Context | Quant |
|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | 57.6 | $0.080 | $0.67 | $0.050 | 100.0% | 1M | fp8 |
| DeepSeek V4.1 Flash 1017 | 57.6 | $0.080 | $0.67 | $0.050 | 100.0% | 1M | fp8 |
| GLM-5.3 | 55.2 | $0.084 | $3.60 | $0.25 | 100.0% | 1M | fp4 |
| GLM-5.3 | 55.2 | $0.084 | $3.60 | $0.25 | 100.0% | 1M | fp4 |
| Kimi K3 | 54.9 | $0.24 | $15.00 | $0.92 | 100.0% | 1M | fp4 |
| Kimi K3 | 54.9 | $0.24 | $15.00 | $0.92 | 100.0% | 1M | fp4 |
| Kimi K3 | 54.9 | $0.45 | $18.00 | $1.20 | 100.0% | 1M | fp4 |
| Kimi K3 | 54.9 | $0.45 | $18.00 | $1.20 | 100.0% | 1M | fp4 |
| DeepSeek V4.1 Flash | 51.2 | $0.10 | $0.60 | $0.050 | 100.0% | 1M | fp8 |
| DeepSeek V4.1 Flash | 51.2 | $0.10 | $0.60 | $0.050 | 100.0% | 1M | fp8 |
| GLM-5.3-Flash | 48.3 | $0.11 | $0.35 | $0.060 | 100.0% | 1M | fp4 |
| GLM-5.3-Flash | 48.3 | $0.11 | $0.35 | $0.060 | 100.0% | 1M | fp4 |
| Kimi K3.1 Pro | — | $1.80 | $9.00 | $0.85 | 100.0% | 1M | mxfp4 |
| Kimi K3.1 Pro | — | $1.80 | $9.00 | $0.85 | 100.0% | 1M | mxfp4 |
| Kimi K3.1 Pro | — | $2.70 | $13.50 | $1.25 | 100.0% | 1M | mxfp4 |
| Kimi K3.1 Pro | — | $2.70 | $13.50 | $1.25 | 100.0% | 1M | mxfp4 |
| MiniMax-M3.1-Flash | — | $0.15 | $0.60 | $0.060 | 99.0% | 1M | fp4 |
| MiniMax-M3.1-Flash | — | $0.15 | $0.60 | $0.060 | 99.5% | 1M | fp4 |
| Schematron V2 Small | — | $0.050 | $0.23 | $0.060 | 100.0% | 128K | bf16 |
| Schematron V2 Small | — | $0.050 | $0.23 | $0.060 | 100.0% | 128K | bf16 |
| Schematron V2 Turbo | — | $0.030 | $0.15 | $0.040 | 100.0% | 128K | bf16 |
| Schematron V2 Turbo | — | $0.030 | $0.15 | $0.040 | 100.0% | 128K | bf16 |