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

Updated July 29, 2026. Served by 9 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 2026-07-29 — not measured.

| Host | Input $/M | Output $/M | Context | Fastest p50 | From | Uptime |
| --- | --- | --- | --- | --- | --- | --- |
| baseten | $3.000 | $15.000 | 1,048,576 | 53 ms | us-central | 100% |
| nebius | $3.000 | $15.000 | 8,000 | 100 ms | eu-hetzner | 99.9% |
| fireworks | $3.000 | $15.000 | 1,048,576 | 18 ms | ap-tokyo | 100% |
| together | $3.000 | $15.000 | 1,000,000 | 114 ms | us-central | 100% |

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