Home

Developers

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.

Video
LTX-Video
Fast, controllable text-to-video for quick iteration on motion and scenes.
Image
FLUX.1-schnell
High-quality, fast text-to-image model with 12B parameters for creative generation.
Text
Qwen3-4B
Language model with logical reasoning, creative writing, and multilingual support.
Audio
wav2vec2-base-960h
Open-source ASR that lives happily on a laptop CPU.
Audio
parler-tts-mini-v1
Pocket-size text-to-speech that you steer with plain-English prompts.
Image
FLUX.1-Kontext-dev
Open-weight, text-guided image editor that keeps your characters and style intact.
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.
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.
Image
FLUX.1-schnell
High-quality, fast text-to-image model with 12B parameters for creative generation.

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.

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.

Video

LTX-Video

Fast, controllable text-to-video for quick iteration on motion and scenes.

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.

Video

LTX-Video

Fast, controllable text-to-video for quick iteration on motion and scenes.

All

Image

Video

Audio

Text

Phi-4-mini-instruct

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

Image

Qwen3-VL-4B-Instruct

Lightweight vision-language model for image understanding and instruction following.

Text

Qwen3-4B-Instruct-2507

Balanced instruction-tuned LLM with solid reasoning at moderate size.

Text

Qwen3-4B

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

Text

Ministral-3-3B-Instruct-2512

Efficient 3B instruction-tuned LLM for fast, reliable text tasks.

Text

AI21-Jamba-Reasoning-3B

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

Video

HunyuanVideo-1.5

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

Video

Wan2.2-TI2V-5B

Text + image guided video generation with balanced quality and compute.

Video

Wan2.2-T2V-A14B

High-fidelity text-to-video focused on stable scenes and motion.

Video

Wan2.2-I2V-A14B

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

Image

Janus-Pro-7B

Multimodal model for unified understanding and image generation.

Text

Granite-4.0-micro

Ultra-light LLM for fast, safe, large-scale text processing.

Text

EXAONE-4.0-1.2B

Ultra-light instruction-tuned LLM for fast, low-cost text tasks.

Text

SmolLM2-1.7B

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

Image

FLUX.1-Kontext-dev

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

Image

FLUX.2-dev

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

Image

FLUX.1-dev

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

Image

FLUX.1-schnell

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

Text

gemma-2-2b

Efficient English model for text generation and reasoning.

Text

Qwen2.5-1.5B

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

Text

Phi-3-mini-4k-instruct

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

Video

LTX-Video

Fast, controllable text-to-video for quick iteration on motion and scenes.

Text

OLMo-2-0425-1B

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

Audio

parler-tts-mini-v1

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

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.

Audio

SongGeneration

Text-to-song generation focused on full musical structure, not clips.

Image

SDXL Turbo

Near-real-time text-to-image generation with minimal diffusion steps.

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.

Text

phi-2

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

Audio

XTTS-v2

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

Image

stable-diffusion-2-base

Multilingual model for speech recognition and audio transcription.

Image

stable-diffusion-v1-5

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

Audio

asr-wav2vec2-librispeech

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

Audio

wav2vec2-base-960h

English speech recognition model trained on 960 hours of audio.

Text

GPT-J-6B

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

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"
        }
    ]
}