Inference provider
Nebius: every model it hosts
3 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 5× 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 |
|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V4.1 Flashfp8 | $0.300 | $1.20 | $0.010 | 1048K | 99.8% | — |
| Z.ai: GLM 5.3fp4 | $1.40 | $4.40 | $0.260 | 1024K | 93.2% | — |
| Z.ai: GLM 5.2fp4 | $1.40 | $4.40 | $0.140 | 1049K | 94.4% | — |
Prices are list prices at build time; providers run promotions. Uptime/throughput are OpenRouter's rolling measurements. Compare hosts on the providers index.