| Model | Endpoint | Context | Input /M | Output /M | Cached input /M | Cache write /M | Uptime 1d |
|---|---|---|---|---|---|---|---|
 DeepSeek V4 Flash 0731 | sail-research/fp4 | 1M | $0.15 | $0.30 | $0.042 | — | 99.66% |
| DeepSeek V4 Flash 0731 | sail-research/us | 1M | $0.15 | $0.30 | $0.042 | — | 99.44% |
| DeepSeek V4 Pro 0813 | sail-research/fp4 | 1M | $1.35 | $2.40 | $0.195 | — | 100.00% |
| DeepSeek V4 Pro 0813 | sail-research/us | 1M | $1.35 | $2.40 | $0.195 | — | 100.00% |
| DeepSeek V4.1 Flash 1017 | sail-research/fp4 | 1M | $0.1818 | $0.27 | $0.007 | — | 100.00% |
| DeepSeek V4.1 Flash 1017 | sail-research/fp4/us | 1M | $0.1818 | $0.27 | $0.007 | — | 99.72% |
 GLM 5.3 | sail-research/fp8 | 1M | $1.05 | $4.20 | $0.168 | — | 100.00% |
| GLM 5.3 | sail-research/us | 1M | $0.75 | $3.00 | $0.12 | — | 100.00% |
| GLM 5.3 Flash | sail-research/fp4 | 1M | $0.175 | $0.625 | $0.0225 | — | 100.00% |
| GLM 5.3 Flash | sail-research/us | 1M | $0.175 | $0.625 | $0.0225 | — | 100.00% |
 Kimi K3 | sail-research/fp4 | 1M | $0.345 | $16.58 | $0.1725 | — | 100.00% |
| Kimi K3 | sail-research/fp4/us | 1M | $0.345 | $16.58 | $0.1725 | — | 99.89% |
| Kimi K3.1 Pro | sail-research/fp4 | 1M | $1.4025 | $9.35 | $0.187 | — | 100.00% |
| Kimi K3.1 Pro | sail-research/fp4/us | 1M | $1.0425 | $9.35 | $0.187 | — | 100.00% |
 gpt-oss-120b | sail-research/fp4 | 131K | $0.06 | $0.40 | $0.03 | — | 100.00% |