| Model | Endpoint | Context | Input /M | Output /M | Cached input /M | Cache write /M | Uptime 1d |
|---|---|---|---|---|---|---|---|
| nextbit/fp4 | 1M | $0.12 | $0.45 | $0.03 | — | 100.00% | |
| nextbit/int4 | 8K | $0.65 | $0.65 | — | — | 100.00% | |
| nextbit/int4 | 131K | $0.075 | $0.15 | $0.05 | — | 100.00% | |
| nextbit/fp8 | 131K | $0.08 | $0.35 | $0.04 | — | 99.79% | |
| nextbit/bf16 | 262K | $0.09 | $0.30 | $0.05 | — | 100.00% | |
| nextbit/fp4 | 262K | $0.15 | $0.40 | $0.06 | — | 99.86% | |
| nextbit/int4 | 41K | $0.10 | $0.22 | — | — | 100.00% |
