# MoonshotAI: Kimi K3.1 Pro — price and measured latency by host

Updated November 05, 2026. Served by 18 providers; 4 of them measured here.

Latency and uptime are measured by llmlatency.dev probes. Prices are published by the providers and read via OpenRouter on 2026-11-05 — not measured.

| Host | Input $/M | Output $/M | Context | Fastest p50 | From | Uptime |
| --- | --- | --- | --- | --- | --- | --- |
| inference-net | $1.800 | $9.000 | 1,048,576 | 117 ms | eu-hetzner | 100% |
| deepinfra | $1.900 | $9.500 | 1,048,576 | 161 ms | us-central | 99.9% |
| nebius | $2.000 | $10.000 | 1,048,576 | 37 ms | eu-hetzner | 100% |
| together | $2.000 | $10.000 | 1,048,576 | 132 ms | us-central | 100% |

Source: https://llmlatency.dev/model/moonshotai-kimi-k3.1-pro · CC BY 4.0