| Model | Endpoint | Context | Input /M | Output /M | Cached input /M | Cache write /M | Uptime 1d |
|---|---|---|---|---|---|---|---|
 DeepSeek V4.1 Flash | modal | 1M | $0.30 | $1.20 | $0.03 | — | 100.00% |
| DeepSeek V4.1 Flash 1017 | modal | 1M | $0.25 | $1.00 | $0.005 | — | 100.00% |
 GLM 5.3 | modal | 1M | $1.40 | $4.40 | $0.26 | — | 100.00% |
| GLM 5.3 Flash | modal/fp4 | 1M | $0.15 | $0.50 | $0.03 | — | 100.00% |
 Gemma 4 31B | modal | 131K | $0.34 | $0.10 | $0.10 | — | 98.64% |
 Kimi K3 | modal/mxfp4 | 1M | $3.00 | $15.00 | $0.30 | — | 100.00% |
| Kimi K3.1 Pro | modal/mxfp4 | 1M | $2.00 | $10.00 | $0.20 | — | 100.00% |
 Muse Spark Open | modal | 1M | $1.25 | $4.25 | $0.15 | — | 99.92% |
 Qwen3.8 27B | modal | 262K | $0.04 | $2.30 | $0.02 | — | 100.00% |