Skip to content

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.

All makers
Provider
Mode
  • Live
    NVIDIA
    Text 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...

    Rate

    7 credits

    per generation

    Generate
  • Live
    NVIDIA
    Pollinations (lowest rate)OpenRouter (lowest rate)
    Text to Text

    Fast open-weight reasoning for high-volume agent tasks, tool use and structured output

    Rate

    7 credits

    per generation

    Generate
  • Live
    NVIDIA
    Text 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...

    Rate

    7 credits

    per generation

    Generate
  • Live
    NVIDIA
    Text 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...

    Rate

    7 credits

    per generation

    Generate
  • Live
    NVIDIA
    Text 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...

    Rate

    7 credits

    per generation

    Generate
  • Live
    NVIDIA
    Text 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...

    Rate

    7 credits

    per generation

    Generate
  • Live
    NVIDIA
    Text 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...

    Rate

    7 credits

    per generation

    Generate

Showing 17 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.

Cookies keep FreeInd working. Optional analytics require your permission. Read our cookie policy.