NVIDIA Models: Pricing per 1M Tokens and Context (2026)

NVIDIA’s model catalogue brings together entries to filter and sort, with ordering based on creation date, newest first. It includes Switchyard and several Nemotron variants, including Nemotron 3.5 Lightning, Nemotron 3.5 Content Safety, and Nemotron 3 Ultra, with free variants shown for some models. Use the catalogue to narrow the available NVIDIA models to the entries relevant to your work, then compare their listed pricing per million tokens and context details before deciding which to evaluate.

11 on record. Sorted by created; every figure comes from the OpenRouter model catalogue, with the page it was read from on each entry.

11listed

Context bars share one log scale, 1K to 2M tokens. Prices are what each provider publishes per million tokens; 'varies' is a router that bills the model it picks.

More in By lab

All by lab lists