OpenAI compatible API · Attested · Public status
NVIDIA: Nemotron 3 Ultra Pricing
Compare prompt and completion token prices for every NVIDIA: Nemotron 3 Ultra route on TrustedRouter, including provider-specific cached-input rates.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
nvidia/nemotron-3-ultra-550b-a55b
open weights
Pricing
Credits prices are shown as USD per million tokens and billed internally as integer microdollars, not floats. Cached input appears when the provider publishes a distinct cache-read rate.
| Provider | Input | Cached input | Output | Schedule |
|---|---|---|---|---|
| DeepInfra | $0.5275/1M | $0.1055/1M | $2.321/1M | Flat |
| Baseten | $0.633/1M | $0.1266/1M | $2.532/1M | Flat |
| Fireworks AI | $0.633/1M | $0.1266/1M | $2.532/1M | Flat |
| Weights & Biases | $0.79125/1M | $0.15825/1M | $2.90125/1M | Flat |
| NVIDIA NIM | $2.11/1M | Not published | $10.55/1M | Flat |
