| Model | Endpoint | Context | Input /M | Output /M | Cached input /M | Cache write /M | Uptime 1d |
|---|---|---|---|---|---|---|---|
| wafer/mxfp4 | 1M | $0.12 | $0.17 | $0.024 | — | 100.00% | |
| wafer/fast | 1M | $0.14 | $0.23 | $0.135 | — | 100.00% | |
| wafer/us | 1M | $0.0434 | $0.30 | $0.035 | — | 100.00% | |
| wafer/mxfp4 | 1M | $0.285 | $4.30 | $0.284 | — | 100.00% | |
| wafer/us | 1M | $0.111 | $4.44 | $0.097 | — | 100.00% | |
| wafer/mxfp4 | 1M | $0.19 | $0.65 | $0.012 | — | 100.00% | |
| wafer/us | 1M | $0.051 | $0.567 | $0.018 | — | 100.00% | |
| wafer/mxfp4 | 1M | $0.079 | $0.50 | $0.0079 | — | 100.00% | |
| wafer/us | 1M | $0.038 | $0.50 | $0.01 | — | 100.00% | |
| wafer | 1M | $0.19 | $8.00 | $0.18 | — | 100.00% | |
| wafer/us | 1M | $0.007 | $6.80 | $0.006 | — | 100.00% | |
| wafer/fp4 | 1M | $0.179 | $1.40 | $0.178 | — | 100.00% | |
| wafer/us | 1M | $0.0699 | $1.40 | $0.0689 | — | 100.00% | |
| wafer/nvfp4 | 1M | $0.065 | $0.24 | $0.064 | — | 100.00% | |
| wafer/us | 1M | $0.042 | $0.184 | $0.041 | — | 100.00% | |
| wafer | 1M | $0.192 | $16.00 | $0.182 | — | 100.00% | |
| wafer/fast | 1M | $0.153 | $16.00 | $0.152 | — | 100.00% | |
| wafer/us | 1M | $0.276 | $9.60 | $0.13 | — | 100.00% | |
| wafer/mxfp4 | 1M | $1.80 | $9.00 | $0.18 | — | 100.00% | |
| wafer/us | 1M | $0.25 | $10.00 | $0.18 | — | 100.00% | |
| wafer/fp8 | 262K | $0.06 | $2.20 | $0.059 | — | 100.00% |
