NVIDIA models
NVIDIA's Nemotron models are open-weight releases tuned for helpfulness and agentic tasks, built on top of leading open architectures and optimized for NVIDIA hardware. Zeplik carries Nemotron 3.5 Lightning at the head of the line, plus the Nemotron 3 Ultra, Super and Nano sizes and a content-safety classifier.
Ask a NVIDIA model now
All 7 NVIDIA models
NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total.
Switchyard is an open-source model router that switches between multiple models to optimize the cost of requests.
NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total.
NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B.
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE).
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications.
NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems.
Pricing at a glance
| Model | Context | Input cr/M | Output cr/M | Released |
|---|---|---|---|---|
| Nemotron 3.5 Super VL | 1.0M | 1.8 | 6.0 | October 2026 |
| Switchyard | 1M | -1.2e+7 | -1.2e+7 | September 2026 |
| Nemotron 3.5 Lightning | 262K | 0.84 | 2.4 | August 2026 |
| Nemotron 3.5 Content Safety | 131K | 2.4 | 2.4 | June 2026 |
| Nemotron 3 Ultra | 203K | 7.2 | 28.8 | June 2026 |
| Nemotron 3 Super | 1.0M | 3.6 | 28.8 | March 2026 |
| Nemotron 3 Nano 30B A3B | 262K | 0.72 | 2.9 | December 2025 |
Frequently asked questions
- Which NVIDIA models can I use on Zeplik?
- Zeplik carries 7 NVIDIA models: Nemotron 3.5 Super VL, Switchyard, Nemotron 3.5 Lightning, Nemotron 3.5 Content Safety and Nemotron 3 Ultra, and 2 more. They all run in the same chat, so you do not need a separate NVIDIA account or API key.
- How much do NVIDIA models cost on Zeplik?
- Output tokens run from 2.4 to 28.8 credits per million depending on which NVIDIA model you pick (raw provider rates $0.20 to $2.40 per million). 1 credit = $0.10, computed from the raw provider rate with a 1.20x margin.
- Which NVIDIA model has the largest context window?
- Nemotron 3.5 Super VL, at 1.0M tokens (1,048,576). The context window covers the conversation plus any documents you attach.
- Do NVIDIA models support images and tool calling?
- 2 of the 7 accept image input, and 5 support tool calling.
- Do I need a paid plan to use NVIDIA models on Zeplik?
- All 7 need a paid plan (Plus or above). Usage is then billed in credits from your monthly allowance.
- What is the newest NVIDIA model on Zeplik?
- Nemotron 3.5 Super VL, released October 2026. NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total.
Other providers
Explore Zeplik
- 468 AI skillsReady-to-run expert methods that run on any NVIDIA model, or any other model you pick.
- 997 integrationsConnect Gmail, Slack, GitHub, Notion and hundreds more so the assistant can work in your apps.
- Simple pricingPlus, Pro and Max plans with a monthly credit allowance that works across every model.