| Model | Endpoint | Context | Input /M | Output /M | Cached input /M | Cache write /M | Uptime 1d |
|---|---|---|---|---|---|---|---|
| chutes/fp8 | 1M | $0.44 | $1.32 | $0.044 | — | 100.00% | |
| chutes/fp8 | 203K | $0.90 | $2.90 | $0.09 | — | 100.00% | |
| chutes/fp4 | 131K | $0.12 | $0.37 | $0.012 | — | 96.93% | |
| chutes/int4 | 262K | $0.39 | $1.80 | $0.039 | — | 100.00% | |
| chutes/mxfp4 | 1M | $1.85 | $9.50 | $0.185 | — | 100.00% | |
| chutes/fp8 | 262K | $0.20 | $1.75 | $0.02 | — | 88.98% | |
| chutes/fp8 | 262K | $0.25 | $2.00 | $0.025 | — | 98.04% | |
| chutes/fp8 | 262K | $0.039 | $1.25 | $0.0039 | — | 99.86% |
