Inference provider
Catalogue
Available models
| Model | Endpoint | Context | Input /M | Output /M | Cached input /M | Cache write /M | Uptime 1d |
|---|---|---|---|---|---|---|---|
| chutes/fp8 | 203K | $0.98 | $3.08 | $0.10 | — | 41.82% | |
| chutes/fp4 | 131K | $0.12 | $0.37 | $0.01 | — | 98.96% | |
| chutes/int4 | 262K | $0.45 | $1.95 | $0.05 | — | 99.66% | |
| chutes/mxfp4 | 1.0M | $1.85 | $9.50 | $0.19 | — | 95.97% | |
| chutes/fp8 | 262K | $0.25 | $2.00 | $0.02 | — | 96.36% | |
| chutes/fp8 | 262K | $0.04 | $1.25 | $0.0039 | — | 99.93% |
