# NVIDIA: Nemotron 3 Ultra — price and measured latency by host

Updated July 25, 2026. Served by 4 providers; 3 of them measured here.

Latency and uptime are measured by llmlatency.dev probes. Prices are published by the providers and read via OpenRouter on 2026-07-25 — not measured.

| Host | Input $/M | Output $/M | Context | Fastest p50 | From | Uptime |
| --- | --- | --- | --- | --- | --- | --- |
| deepinfra | $0.500 | $2.200 | 262,144 | 226 ms | us-central | 99.9% |
| baseten | $0.600 | $2.400 | 202,800 | 54 ms | us-central | 100% |
| together | $0.600 | $3.600 | 512,288 | 111 ms | us-central | 100% |

Source: https://llmlatency.dev/model/nvidia-nemotron-3-ultra-550b-a55b · CC BY 4.0