NVIDIA AI models
Explore 10 live NVIDIA models on FreeInd's multi-model AI platform, each with a fixed credit rate, real sample outputs, and every routing provider that serves it.
FreeInd is an independent platform and is not affiliated with, endorsed by, or sponsored by NVIDIA or the creators or owners of the underlying AI models. The NVIDIA name and mark appear solely to identify the integrations available on this platform.
- Active models
- 10
- Real samples
- 0
- Starting rate
- 7 credits
All NVIDIA models
Every live NVIDIA model with its rate per generation or per second of output and real sample outputs.
- LiveNVIDIA: Nemotron 3 UltraLowest rateNVIDIAText to Text
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
GenerateRate
7 credits
per generation
- LiveNVIDIA Nemotron 3.5 LightningLowest rateNVIDIAPollinations (lowest rate)OpenRouter (lowest rate)Text to Text
Fast open-weight reasoning for high-volume agent tasks, tool use and structured output
GenerateRate
7 credits
per generation
- LiveNVIDIA: Nemotron 3 SuperLowest rateNVIDIAText to Text
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. Built on a hybrid Mamba-Transformer...
GenerateRate
7 credits
per generation
- LiveNVIDIA: Nemotron 3.5 LightningLowest rateNVIDIAText to Text
NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...
GenerateRate
7 credits
per generation
- LiveNVIDIA: Nemotron 3.5 Content SafetyLowest rateNVIDIAText to Text
NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...
GenerateRate
7 credits
per generation
- LiveNVIDIA: Nemotron 3 Nano 30B A3BLowest rateNVIDIAText to Text
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. The model is fully...
GenerateRate
7 credits
per generation
- LiveNVIDIA: Nemotron 3 Nano OmniLowest rateNVIDIAText to Text
NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...
GenerateRate
7 credits
per generation
Showing 1–7 of 7 active models· rates are per generation (images) or per sec of output (video/audio)
Other makers
Continue browsing the catalog by original model maker.