DekaLLM
9 models served.
| Model | Agent Index | Input | Output | Agent $/M | Uptime 24h | Context | Quant |
|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | 57.6 | $0.10 | $0.60 | $0.050 | 100.0% | 1M | — |
| GLM-5.3-Flash | 48.3 | $0.10 | $0.50 | $0.060 | 99.6% | 1M | — |
| GPT OSS 120B | 22.1 | $0.030 | $0.18 | $0.040 | 99.2% | 131K | bf16 |
| Gemma 4 26B A4B IT | — | $0.060 | $0.33 | $0.060 | 98.8% | 262K | bf16 |
| GPT OSS 20B | — | $0.029 | $0.14 | $0.030 | 95.5% | 131K | bf16 |
| Mistral Nemo | — | $0.018 | $0.030 | $0.020 | 90.6% | 131K | fp8 |
| Nemotron 3 Super 120B A12B | — | $0.080 | $0.45 | $0.10 | 44.3% | 262K | fp8 |
| Qwen3 30B A3B Instruct 2507 | — | $0.090 | $0.30 | $0.10 | 99.0% | 262K | — |
| Qwen3.8 27B | — | $0.040 | $2.50 | $0.14 | 99.9% | 262K | — |