Skip to content
ModelCap

Inference provider

Nvidia: AI models and API pricing

Every tracked model Nvidia serves through OpenRouter, with Nvidia's own input and output price per 1M tokens, the context window it serves, disclosed quantization and measured endpoint uptime. Rows link to the model page, where every provider's deployment is listed side by side.

Snapshot as of 11 August 2026

Nvidia serves 4 tracked models through 4 endpoints as of 11 August 2026; the highest-ranked is Nemotron Nano 9B V2 (ModelCap Index #201); mean measured uptime is 90.12%.

Models served
4
On the ModelCap Index
4
Cheapest output price
—

Language models on Nvidia (4)

Ranked models first, in ModelCap Index order. Prices are the lowest Nvidia lists for the model; the endpoint count shows how many deployments carry it.

Language models served by Nvidia, with price, context, quantization and uptime
#ModelModelCap IndexInput $/1MOutput $/1MContextQuantizationUptime (30 min)Endpoints
1Nemotron Nano 9B V2NVIDIA#20112.9FreeFree128Kbf1695.29%1
2Nemotron 3.5 Content SafetyNVIDIA#2340.0FreeFree128K—99.43%1
3Nemotron 3 Nano OmniNVIDIA#2350.0FreeFree256K—97.58%1
4Nemotron Nano 12B 2 VLNVIDIA#2360.0FreeFree128K—68.16%1

Nvidia on ModelCap: common questions

How many AI models does Nvidia serve?

4 tracked models as of 11 August 2026: 4 language models (4 with a public ModelCap Index position), across 4 live endpoints observed through OpenRouter.

What is the best model available on Nvidia?

Nemotron Nano 9B V2 from NVIDIA is the highest-ranked language model Nvidia serves, at ModelCap Index position #201 and Free per 1M output tokens on Nvidia. The table lists every model in Index order.

What is the cheapest model on Nvidia?

Nvidia lists no positive language-token price in the current snapshot.

Which Nvidia model has the largest context window?

Nemotron 3 Nano Omni, served with a 256K-token context window on Nvidia. Providers sometimes serve less than the model's published maximum, so the figure here is the provider's own.

How reliable is Nvidia?

Mean measured uptime across Nvidia endpoints is 90.12% over the last 30 minutes, as reported by OpenRouter at the time of the snapshot. Per-model uptime is in the table; it is a live operational signal, not a service-level guarantee.

Where do the Nvidia prices come from?

From the OpenRouter catalogue entry for each Nvidia endpoint, in USD per 1M tokens, re-observed on every ModelCap refresh. Where Nvidia exposes several deployments of one model at different prices, the table shows the lowest and notes the count; the model page lists each deployment.

How current is this page?

It re-renders within a minute of every dataset refresh; this snapshot was published 11 August 2026. Offers retained from a failed refresh are marked stale in the data and are not counted here.

Explore further