Inference provider
Catalogue
Available models
| Model | Endpoint | Context | Input /M | Output /M | Cached input /M | Cache write /M | Uptime 1d |
|---|---|---|---|---|---|---|---|
| phala | 164K | $1.00 | $1.00 | $0.50 | — | 99.73% | |
| phala | 1.0M | $0.31 | $0.92 | $0.02 | — | 100.00% | |
| phala | 1.0M | $0.96 | $2.88 | $0.10 | — | 99.90% | |
| phala | 1.0M | $0.21 | $0.84 | $0.0042 | — | 99.86% | |
| phala | 203K | $1.21 | $4.20 | $0.60 | — | 43.75% | |
| phala/fp8 | 1.0M | $1.26 | $3.00 | $0.22 | — | 0.00% | |
| phala | 1.0M | $0.84 | $2.64 | $0.16 | — | 99.76% | |
| phala/nvfp4 | 1.0M | $0.11 | $0.38 | $0.02 | — | 100.00% | |
| phala | 262K | $0.15 | $0.64 | $0.04 | — | 99.78% | |
| Kev 4B | phala | 8K | $0.04 | $0.00 | — | — | 99.87% |
 Kimi K2.6 | phala | 262K | $1.09 | $4.60 | $0.37 | — | 95.91% |
| Kimi K2.7 Code | phala | 262K | $0.95 | $4.00 | $0.19 | — | 98.69% |
| Kimi K3 | phala | 1.0M | $2.55 | $12.75 | $0.26 | — | 99.79% |
| phala | 33K | $0.10 | $0.20 | — | — | 100.00% | |
| phala | 262K | $0.55 | $3.50 | $0.22 | — | 98.36% | |
| phala | 262K | $0.30 | $2.40 | $0.03 | — | 97.71% | |
| phala | 262K | $0.32 | $3.25 | $0.03 | — | 92.26% | |
| phala | 262K | $0.20 | $1.27 | $0.06 | — | 96.83% | |
| phala | 1M | $0.20 | $2.50 | $0.05 | — | 97.92% | |
| phala | 131K | $0.15 | $0.60 | — | — | 99.73% |