Inference provider
Catalogue
Available models
| Model | Endpoint | Context | Input /M | Output /M | Cached input /M | Cache write /M | Uptime 1d |
|---|---|---|---|---|---|---|---|
| gmicloud/fp8 | 128K | $0.29 | $1.14 | $0.11 | — | 99.79% | |
| gmicloud/fp8 | 164K | $0.21 | $0.31 | $0.02 | — | 100.00% | |
| gmicloud/fp8 | 1.0M | $0.09 | $0.18 | $0.02 | — | 100.00% | |
| gmicloud/fp8 | 1.0M | $0.29 | $0.86 | $0.0091 | — | 100.00% | |
| gmicloud/fp8 | 1.0M | $0.44 | $1.32 | $0.01 | — | 100.00% | |
| gmicloud/fp8 | 1.0M | $0.96 | $1.91 | $0.08 | — | 99.93% | |
| gmicloud/fp8 | 1.0M | $1.06 | $3.17 | $0.04 | — | 98.31% | |
| gmicloud/fp8 | 1.0M | $0.18 | $0.72 | $0.0036 | — | 99.44% | |
| gmicloud/fp8 | 203K | $0.60 | $1.92 | $0.12 | — | 99.72% | |
| gmicloud/fp8 | 203K | $1.40 | $4.40 | $0.26 | — | 100.00% | |
| gmicloud/fp8 | 1.0M | $1.40 | $4.40 | $0.26 | — | 100.00% | |
| gmicloud/fp8 | 1.0M | $0.98 | $3.08 | $0.18 | — | 100.00% | |
| gmicloud/fp8 | 1.0M | $0.09 | $0.30 | $0.02 | — | 93.68% | |
| gmicloud/bf16 | 262K | $0.14 | $0.58 | $0.04 | — | 100.00% | |
| gmicloud/bf16 | 262K | $0.18 | $0.60 | $0.06 | — | 100.00% | |
| gmicloud/fp8 | 262K | $0.86 | $3.60 | $0.14 | — | — | |
| gmicloud/fp8 | 262K | $0.95 | $4.00 | $0.19 | — | 86.67% | |
| gmicloud/fp8 | 1.1M | $0.12 | $0.24 | $0.00255 | — | 81.18% | |
| gmicloud/bf16 | 1.1M | $0.30 | $0.61 | $0.0028 | — | 99.14% | |
| gmicloud/bf16 | 1.1M | $0.14 | $0.28 | $0.003 | — | 45.80% | |
| gmicloud/bf16 | 1.1M | $0.44 | $0.87 | $0.004 | — | 92.29% | |
| gmicloud/fp8 | 197K | $0.30 | $1.20 | $0.03 | — | 100.00% | |
| gmicloud/fp8 | 197K | $0.21 | $0.84 | $0.04 | — | 99.71% | |
| gmicloud/fp8 | 1.0M | $0.24 | $0.96 | $0.05 | — | 99.72% | |
| gmicloud/fp8 | 262K | $0.09 | $0.35 | $0.02 | — | 0.00% | |
| gmicloud/fp8 | 262K | $0.60 | $3.60 | — | — | 99.48% |
