| Model | Endpoint | Context | Input /M | Output /M | Cached input /M | Cache write /M | Uptime 1d |
|---|---|---|---|---|---|---|---|
| inceptron/fp4 | 1M | $0.13 | $0.495 | $0.027 | — | 99.65% | |
| inceptron/fp4 | 1M | $1.40 | $4.40 | $0.26 | — | 100.00% | |
| inceptron/fp4 | 1M | $1.00 | $4.396 | $0.14 | — | 100.00% | |
| inceptron/fp8 | 1M | $0.175 | $0.50 | $0.03 | — | 100.00% | |
| inceptron/int4 | 262K | $0.7995 | $3.75 | $0.156 | — | 99.86% | |
| inceptron/int4 | 262K | $0.60 | $3.50 | $0.16 | — | 99.92% |
