| Model | Endpoint | Context | Input /M | Output /M | Cached input /M | Cache write /M | Uptime 1d |
|---|---|---|---|---|---|---|---|
 DeepSeek V4.1 Flash 1017 | dekallm | 1M | $0.18 | $0.68 | $0.006 | — | 98.75% |
 GLM 5.3 Flash | dekallm | 1M | $0.10 | $0.50 | $0.03 | — | 97.50% |
 Gemma 4 26B A4B | dekallm/bf16 | 262K | $0.06 | $0.33 | $0.04 | — | 100.00% |
| Gemma 4 31B | dekallm | 262K | $0.14 | $0.40 | $0.05 | — | 97.31% |
 Mistral Nemo | dekallm/fp8 | 131K | $0.018 | $0.03 | — | — | 100.00% |
 Nemotron 3 Super | dekallm/fp8 | 262K | $0.08 | $0.45 | — | — | 95.39% |
 Qwen3 30B A3B Instruct 2507 | dekallm | 262K | $0.09 | $0.30 | — | — | 98.91% |
| Qwen3.6 35B A3B | dekallm | 262K | $0.10 | $1.00 | $0.05 | — | 84.09% |
| Qwen3.8 27B | dekallm | 262K | $0.04 | $2.50 | $0.02 | — | 96.94% |
 gpt-oss-120b | dekallm/bf16 | 131K | $0.03 | $0.18 | $0.03 | — | 99.72% |
| gpt-oss-20b | dekallm/bf16 | 131K | $0.029 | $0.14 | $0.029 | — | 100.00% |