Inference provider
Makora: every model it hosts
5 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 |
|---|---|---|---|---|---|---|
| Xiaomi: MiMo-V2.6-Flashfp8 | $0.130 | $0.280 | $0.0020 | 1049K | 90.9% | — |
| Z.ai: GLM 5.3 Flashunknown | $0.140 | $0.470 | $0.024 | 1049K | 66.8% | — |
| Z.ai: GLM 5.3fp4 | $0.140 | $4.40 | $0.100 | 1049K | 71.9% | — |
| DeepSeek: DeepSeek V4.1 Flashfp8 | $0.260 | $1.17 | $0.0058 | 1049K | 96.9% | — |
| MoonshotAI: Kimi K3fp4 | $0.650 | $15.00 | $0.230 | 1049K | 98.8% | — |
Prices are list prices at build time; providers run promotions. Uptime/throughput are OpenRouter's rolling measurements. Compare hosts on the providers index.