| Model | Endpoint | Context | Input /M | Output /M | Cached input /M | Cache write /M | Uptime 1d |
|---|---|---|---|---|---|---|---|
 GLM 5.3 Flash | darkbloom/fp4 | 262K | $0.065 | $0.18 | $0.012 | — | 97.33% |
 Gemma 4 26B A4B | darkbloom | 131K | $0.04 | $0.15 | $0.01 | — | 100.00% |
 MiMo-V2.6-Flash | darkbloom/fp4 | 1M | $0.10 | $0.28 | $0.0028 | — | 99.85% |
 Nemotron 3.5 Lightning | darkbloom/int4 | 262K | $0.025 | $0.12 | $0.0125 | — | 98.81% |
| Nemotron 3.5 Super VL | darkbloom/nvfp4 | 262K | $0.06 | $0.35 | $0.01 | — | 99.26% |
 Qwen3.5-35B-A3B | darkbloom/fp4 | 262K | $0.065 | $0.75 | $0.0325 | — | 99.80% |
| Qwen3.5-9B | darkbloom/fp4 | 262K | $0.08 | $0.13 | $0.04 | — | 98.75% |
| Qwen3.6 35B A3B | darkbloom/fp4 | 262K | $0.05 | $0.70 | $0.025 | — | 99.81% |
| Qwen3.8 27B | darkbloom/fp4 | 262K | $0.035 | $1.50 | $0.0175 | — | 98.48% |
 Ternary Bonsai 2 27B | darkbloom/int4 | 262K | $0.075 | $0.50 | $0.0375 | — | 100.00% |
| Ternary Bonsai 2 9B | darkbloom/int4 | 262K | $0.08 | $0.13 | $0.04 | — | 99.81% |
 gpt-oss-20b | darkbloom/fp8 | 131K | $0.018 | $0.09 | $0.009 | — | 98.54% |