Home

Developer

Join Us

Contact

See our SDK

Explore Norman

Browse AI models. Use them all through our SDK.

See our SDK

Explore Ready-to-Use Models

From code to creative generation,   Norman makes great models accessible now.

Text
OLMo-2-0425-1B
Open English model for research, text generation, and scientific language studies.
Text
XTTS-v2
Multilingual voice cloning model—clone any voice in 17 languages from a short sample.
Text
Qwen3-4B
Language model with logical reasoning, creative writing, and multilingual support.
Image
FLUX.1-schnell
High-quality, fast text-to-image model with 12B parameters for creative generation.
Audio
parler-tts-mini-v1
Pocket-size text-to-speech that you steer with plain-English prompts.
Audio
wav2vec2-base-960h
Open-source ASR that lives happily on a laptop CPU.
Image
FLUX.1-Kontext-dev
Open-weight, text-guided image editor that keeps your characters and style intact.

Explore Ready-to-Use Models

From code to creative generation,   Norman makes great models accessible now.

Explore Ready-to-Use Models

From code to creative generation,   Norman makes great models accessible now.

Model Libary

Browse our library of open source models that are ready to deploy behind an API endpoint in seconds.

Text

Phi-3-mini-4k-instruct

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

Text

Qwen3-4B

Language model with logical reasoning, creative writing, and multilingual support.

Audio

wav2vec2-base-960h

English speech recognition model trained on 960 hours of audio.

Text

Phi-3-mini-4k-instruct

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

Text

Qwen3-4B

Language model with logical reasoning, creative writing, and multilingual support.

Audio

wav2vec2-base-960h

English speech recognition model trained on 960 hours of audio.

All

Image

Audio

Text

Phi-3-mini-4k-instruct

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

Text

Qwen3-4B

Language model with logical reasoning, creative writing, and multilingual support.

Audio

wav2vec2-base-960h

English speech recognition model trained on 960 hours of audio.

Audio

XTTS-v2

Multilingual voice cloning model—clone any voice in 17 languages from a short sample.

Image

stable-diffusion-v1-5

Text-to-image model for generating photorealistic images from any prompt.

Image

stable-diffusion-2-base

Multilingual model for speech recognition and audio transcription.

Image

koala-lightning-700m

Fast, efficient text-to-image model for generating high-res images from prompts.

Image

PixArt-LCM-XL-2-1024-MS

Ultra-fast text-to-image model for 1024x1024 images.

Image

FLUX.1-schnell

High-quality, fast text-to-image model with 12B parameters for creative generation.

Image

FLUX.1-dev

12B parameter text-to-image model for high-quality, creative image generation.

Image

FLUX.1-Kontext-dev

12B parameter model for editing images using text instructions and references.

Image

FLUX.1-Kontext-dev

12B parameter model for editing images using text instructions and references.

Image

Janus-Pro-7B

Multimodal model for unified understanding and image generation.

Audio

Whisper Large-v3

Advanced model for speech recognition and transcription.

Audio

Whisper Medium

Multilingual model for speech recognition and audio transcription.

Audio

Distil-Whisper

Fast, compact model for English speech recognition and transcription.

Audio

asr-wav2vec2-librispeech

English ASR model with low error rates, trained on LibriSpeech data.

Audio

parler-tts-mini-v1

Open-source text-to-speech model with customizable voices.

Text

gemma-2-2b

Efficient English model for text generation and reasoning.

Text

OLMo-2-0425-1B

Open English model for research, text generation, and scientific language studies.

Text

phi-2

Small English model for chat, QA, and code, focused on safety research.

Text

Qwen2.5-1.5B

Multilingual model with strong coding, math, and long-text generation abilities.

Text

GPT-J-6B

English text generator, 6B parameters, research-focused.

Text

SmolLM2-1.7B

Compact English model for on-device tasks, strong in reasoning and instruction.

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": "image_reverser_model",
    "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": "image_reverser_model",
    "inputs": [
        {
            "display_title": "Input",
            "data": "/Users/alice/Desktop/sample_image.png"
        }
    ]
}