Inference provider
DekaLLM: every model it hosts
4 endpoints tracked. Hosts may use different quantizations, context limits, and serving defaults, so compare price together with reliability and configuration. On this host family, the same model costs up to 11× more depending on which endpoint serves it.
Verified 2026-10-21 · source: OpenRouter public API
| Model | Input /1M | Output /1M | Cache read | Context | Uptime 1d | Throughput |
|---|---|---|---|---|---|---|
| NVIDIA: Nemotron 3 Superfp8 | $0.080 | $0.450 | — | 262K | 100.0% | — |
| Qwen: Qwen3.6 35B A3Bunknown | $0.100 | $1.00 | $0.050 | 262K | 99.9% | — |
| Z.ai: GLM 5.3unknown | $0.180 | $2.95 | $0.150 | 1049K | 89.4% | — |
| DeepSeek: DeepSeek V4 Pro 0423unknown | $0.880 | $3.80 | $0.150 | 1049K | 99.8% | — |
Prices are list prices at build time; providers run promotions. Uptime/throughput are OpenRouter's rolling measurements. Compare hosts on the providers index.