Inference provider
Catalogue
Available models
| Model | Endpoint | Context | Input /M | Output /M | Cached input /M | Cache write /M | Uptime 1d |
|---|---|---|---|---|---|---|---|
| inference-net/fp8 | 1.0M | $0.10 | $0.66 | $0.01 | — | 100.00% | |
| inference-net/fp4 | 1.0M | $0.08 | $4.80 | $0.06 | — | 100.00% | |
| inference-net/fp4 | 1.0M | $0.08 | $0.15 | $0.03 | — | 100.00% | |
 Kimi K3 | inference-net/fast | 1.0M | $2.49 | $15.00 | $0.35 | — | 100.00% |
| Kimi K3 | inference-net/fp4 | 1.0M | $0.45 | $15.00 | $0.28 | — | 100.00% |
| inference-net/bf16 | 128K | $0.05 | $0.23 | $0.05 | — | 100.00% | |
| inference-net/bf16 | 128K | $0.03 | $0.15 | $0.03 | — | 100.00% |