Home

Developers

Join Us

Contact

See our SDK

Home

Developers

Join Us

Contact

See our SDK

Norman is how
you run AI

Norman is how you run AI

Deploy and use AI models now
No setup. No waiting. No code. Just Norman it.

Try it for free

Featured Models

Text

Nemotron-Cascade-2-30B-A3B

An open 30B MoE model with 3B activated parameters that delivers strong reasoning and agentic capabilities.

Text

NVIDIA-Nemotron-3-Nano-4B

Next-gen compact LLM for lightning-fast local reasoning and efficient edge processing.

Video

FLUX.2 [klein] 9B

Real-time high-speed generation balancing professional quality with sub-second latency.

Video

LTX-2

Generates high-res video with synchronized audio from text or images.

Video

Wan2.2-I2V-A14B

High-quality image-to-video generation focused on smooth, consistent motion.

Video

HunyuanVideo-1.5

High-end text-to-video focused on cinematic motion and scene depth.

Text

AI21-Jamba-Reasoning-3B

Compact LLM optimized for step-by-step reasoning and logic tasks.

Text

Phi-4-mini-instruct

Compact instruction-tuned LLM with strong reasoning for its size.

Image

FLUX.2-dev

Next-gen text-to-image with stronger prompt alignment and cleaner visuals.

Explore models

Text

NVIDIA-Nemotron-3-Nano-4B

Next-gen compact LLM for lightning-fast local reasoning and efficient edge processing.

Video

FLUX.2 [klein] 9B

Real-time high-speed generation balancing professional quality with sub-second latency.

Video

Wan2.2-I2V-A14B

High-quality image-to-video generation focused on smooth, consistent motion.

Video

HunyuanVideo-1.5

High-end text-to-video focused on cinematic motion and scene depth.

Text

Phi-3-mini-4k-instruct

Compact, fast language model for instructions and advanced reasoning tasks.

Explore models

Go live in minutes.

Publish in three steps:

Upload your model

From your Server, Drive or your very own laptop.

Setup your endpoint

Config + Input + Output. That’s it.

Instantly available

Share, Distribute and get user feedback.

Go live in minutes.

Publish in three steps:

Upload your model
From your Server, Drive or your very own laptop.
Setup your endpoint
Config + Input + Output. That’s it.
Instantly available
Share, Distribute and get user feedback.

Install the Norman SDK

Use any AI model with just a few lines of code.
One API that just works.

View Docs

Install

pip install norman

Initialize

norman = Norman(api_key=
"nrm_sk_2a96b7b1a9f44b09b7c3f9f1843e93e2")

Define

invocation_config = {
    "model_name": "iwhisper-large-v3",
    "inputs": [
        {
            "display_title": "Input",
            "data": "/Users/alice/Desktop/sample_image.png"
        }
    ]
}

Install the Norman SDK

Use any AI model with just a few lines of code.
One API that just works.

View Docs

Install

pip install norman

Initialize

norman = Norman(api_key=
"nrm_sk_2a96b7b1a9f44b09b7c3f9f1843e93e2")

Define

invocation_config = {
    "model_name": "iwhisper-large-v3",
    "inputs": [
        {
            "display_title": "Input",
            "data": "/Users/alice/Desktop/sample_image.png"
        }
    ]
}