OptimToken Models by maker

OptimToken › Models by maker › Nvidia

Nvidia (Nemotron) API pricing

As of 2026-11-21, the OptimToken catalogue holds 6 Nvidia models. By price tier, 1 is Mid-range and 5 Budget. The cheapest is Nemotron 3.5 Lightning at $0.07 per 1M input tokens and $0.20 per 1M output tokens. The most expensive is Nemotron 3 Ultra at $0.50 input and $2.20 output, 10x the cheapest on blended price (30% input, 70% output). These are the prices we quote: a model sold by several hosts has other rates, listed on its own page.

Nvidia models and prices

Nvidia models, cheapest first on blended price (30% input, 70% output). USD per 1M tokens, data snapshot 2026-11-21.
ModelInputOutputBatch (in / out)Cache readContextLicence
Nemotron 3.5 Lightning$0.07$0.20not published$0.041MOpen weights (OpenMDW 1.1)
Nemotron 3 Nano 30B A3B$0.06$0.24not published$0.012262KOpen weights (NVIDIA Open Model License)
Nemotron 3.5 Content Safety$0.20$0.20not publishednot published131KOpen weights (OpenMDW 1.1)
Nemotron 3 Super$0.075$0.40not publishednot published262KOpen weights (NVIDIA Open Model License)
Nemotron 3.5 Super VL$0.15$0.47not published$0.021MUnknown
Nemotron 3 Ultra$0.50$2.20not published$0.10262KOpen weights (OpenMDW 1.1)

Published discounts: a prompt-cache read rate for 4 of the 6 and a batch rate for none. The most recent by release date is Nemotron 3.5 Super VL (2026-10). Arena ELO scores (as of 2026-11-11) exist for 5 of the 6; the highest is Nemotron 3 Ultra at 1445.

Licences

Of the 6, 5 are open weights, which is not the same as open source: the weights are published, but under the NVIDIA Open Model License and OpenMDW 1.1 licences, which restrict some uses. Read them before self-hosting commercially. No licence is recorded for the other 1, so this page does not say whether it can be self-hosted. Licences are as recorded in this catalogue: check the maker's own terms before relying on one.

Price changes since tracking began

Our daily price archive began on 2026-08-15 and holds a record for all 6 models. The price we quote has changed for 5 of them, 37 times in all, 29 of those changes flagged as a change of quoted host rather than a repricing. The most recent was to Nemotron 3.5 Super VL on 2026-11-21: -5.3% on the blended price (30% input, 70% output) (quoted host changed, not a repricing). Since tracking began, 2 of them joined the catalogue, most recently Nemotron 3.5 Super VL on 2026-10-17. Last checked against the 2026-11-21 snapshot.

Each row is a model's most recent change. Its own page has the full history.

ModelDateOld price (in / out)New price (in / out)Blended changeChanges in all
Nemotron 3.5 Super VL2026-11-21$0.15 / $0.50$0.15 / $0.47-5.3% (quoted host changed, not a repricing)4
Nemotron 3 Ultra2026-11-17$0.60 / $2.40$0.50 / $2.20-9.1% (quoted host changed, not a repricing)12
Nemotron 3 Super2026-11-06$0.30 / $2.40$0.075 / $0.40-82.9% (quoted host changed, not a repricing)5
Nemotron 3.5 Lightning2026-10-10$0.0469 / $0.134$0.07 / $0.20+49.3% (quoted host changed, not a repricing)13
Nemotron 3 Nano 30B A3B2026-10-08$0.05 / $0.20$0.06 / $0.24+20.0% (quoted host changed, not a repricing)3

Other makers

Models by maker: every model in the catalogue, including makers with fewer than 3.

These are list prices.

Your real cost also depends on caching and batching, negotiated discounts, marketplace agreements, and the contracts you already have. OptimNow audits exactly that.

Get a FinOps review