nvidia · Text chat

NVIDIA-Nemotron-3-Ultra-550B-A55B API

NVIDIA-Nemotron-3-Ultra-550B-A55B by nvidia is listed in ServerNet for Text chat. Review current availability and pricing before connecting.

Preparing
AI dashboardIntegration guide

Toman per million tokens

Input115,936
Output510,118
Context window
262,144
Gateway output cap
4,096

Model features

Reasoning ✓

Tool calling ✓

Streaming ✓

10% tax is added to usage charges. Prices are frozen at request admission and settlement uses reported consumption. Only available models are exposed by the API. Availability requires a configured provider, valid prices and a supported execution path.

This chat endpoint accepts text only. A model’s vision capability does not mean image inputs are enabled in the gateway.