NVIDIA models
llm11 can call 5 NVIDIA models through one API, with Jev, TypeSafe AI's System One model, deciding which one answers each request. Blended prices run from $0.085 to $1.05 per million tokens. The newest is Nemotron 3.5 Lightning, released 2026-08-11.
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Nemotron 3.5 Lightning | $0.060 | $0.160 | 262K | |
| Nemotron 3 Ultra | $0.600 | $2.40 | 262K | |
| Nemotron 3.5 Content Safety | $0.200 | $0.200 | 131K | |
| Nemotron 3 Super | $0.080 | $0.450 | 262K | |
| Nemotron 3 Nano 30B A3B | $0.050 | $0.200 | 262K |
Read from the live catalogue and refreshed daily. Prices are per million tokens.
Questions
- Which NVIDIA models can I call through llm11?
- 5 today, listed with live prices on this page. The list follows the upstream catalogue, so a new NVIDIA model appears here without anyone editing the page.
- What is the cheapest and the most expensive NVIDIA model?
- By blended price, weighting three parts input to one part output: Nemotron 3.5 Lightning is cheapest at $0.085 per million tokens, and Nemotron 3 Ultra is the most expensive at $1.05.
- What is the newest NVIDIA model?
- Nemotron 3.5 Lightning, released 2026-08-11. Call it with model set to nvidia/nemotron-3.5-lightning.