Inference provider
Catalogue
Available models
| Model | Endpoint | Context | Input /M | Output /M | Cached input /M | Cache write /M | Uptime 1d |
|---|---|---|---|---|---|---|---|
| baidu/fp8 | 131K | $0.28 | $0.42 | $0.03 | — | 99.93% | |
| baidu/fp8 | 1.0M | $0.14 | $0.28 | $0.03 | — | 99.86% | |
| baidu/fp8 | 1.0M | $0.44 | $1.32 | $0.01 | — | 100.00% | |
| baidu/fp8 | 1.0M | $0.44 | $0.88 | $0.04 | — | 99.79% | |
| baidu/fp8 | 1.0M | $1.32 | $3.96 | $0.04 | — | 100.00% | |
| baidu/fp8 | 1.0M | $0.30 | $1.20 | $0.006 | — | 100.00% | |
| baidu/fp8 | 203K | $0.70 | $2.24 | $0.14 | — | 100.00% | |
| baidu/fp8 | 203K | $1.40 | $4.40 | $0.26 | — | 100.00% | |
| baidu/fast | 1.0M | $2.25 | $7.88 | $0.56 | — | 100.00% | |
| baidu/fp8 | 1.0M | $0.62 | $1.94 | $0.11 | — | 99.86% | |
| baidu/fp8 | 1.0M | $1.40 | $4.40 | $0.26 | — | 100.00% | |
 Kimi K2.6 | baidu/fp4 | 262K | $0.44 | $1.84 | $0.07 | — | 100.00% |