Try NVIDIA NIM APIs

google gemma-3n-e4b-it

An edge computing AI model which accepts text, audio and image input, ideal for resource-constrained environments

language generation speech recognition visual qa chat google

google gemma-3n-e2b-it

An edge computing AI model which accepts text, audio and image input, ideal for resource-constrained environments

language generation speech recognition visual qa chat google

mistralai mistral-medium-3-instruct

Powerful, multimodal language model designed for enterprise applications, including software development, data analysis, and reasoning.

language generation image-to-text multimodal visual question answering mistralai

meta llama-4-maverick-17b-128e-instruct

A general purpose multimodal, multilingual 128 MoE model with 17B parameters.

language generation image-to-text vision assistant visual question answering meta

meta llama-4-scout-17b-16e-instruct

A multimodal, multilingual 16 MoE model with 17B parameters.

language generation image-to-text vision assistant visual question answering meta

google gemma-3-27b-it

Cutting-edge open multimodal model exceling in high-quality reasoning from images.

vision assistant visual question answering language generation image-to-text google

microsoft phi-4-multimodal-instruct

Cutting-edge open multimodal model exceling in high-quality reasoning from image and audio inputs.

speech recognition visual qa language generation image-to-text chart and table understanding microsoft

igenius colosseum_355b_instruct_16k

NVIDIA DGX Cloud trained multilingual LLM designed for mission critical use cases in regulated industries including financial services, government, heavy industry

heavy industry government chat highly regulated use case support financial services igenius

writer palmyra-creative-122b

Powerful LLM designed for creative thinking and writing.

content generation chat chat text-to-text writer

zyphra zamba2-7b-instruct

Efficient hybrid state-space model designed for conversational and reasoning tasks.

chat chat language generation text-to-text zyphra

meta llama-3.2-11b-vision-instruct

Cutting-edge vision-language model exceling in high-quality reasoning from images.

image-text retrieval visual qa image-to-text image captioning visual grounding meta

meta llama-3.2-90b-vision-instruct

Cutting-edge vision-Language model exceling in high-quality reasoning from images.

image-text retrieval visual qa image captioning image-to-text visual grounding meta

microsoft phi-3.5-vision-instruct

Cutting-edge open multimodal model exceling in high-quality reasoning from images.

vision assistant visual question answering language generation image-to-text microsoft

ai21labs jamba-1.5-mini-instruct

Cutting-edge MOE based LLM designed to excel in a wide array of generative AI tasks.

chat chat language generation text-to-text ai21labs

ai21labs jamba-1.5-large-instruct

Cutting-edge MOE based LLM designed to excel in a wide array of generative AI tasks.

chat chat language generation text-to-text ai21labs

nvidia nv-dinov2

NV-DINOv2 is a visual foundation model that generates vector embeddings for the input image.

image-to-embedding computer vision deepstream nvidia nim object classification nvidia

microsoft florence-2

Vision foundation model capable of performing diverse computer vision and vision language tasks.

image classification image object detection cv multimodal vision assistant vlm visual question answering computer vision language generation image-to-text text-to-image microsoft

nvidia usdvalidate

Verify compatibility of OpenUSD assets with instant RTX render and rule-based validation.

validation openusd synthetic data generation digital twin usd visualization 3d nvidia

nvidia ocdrnet

OCDNet and OCRNet are pre-trained models designed for optical character detection and recognition respectively.

optical character recognition image optical character detection cv vlm computer vision tao toolkit video nvidia

nvidia visual-changenet

Visual Changenet detects pixel-level change maps between two images and outputs a semantic change segmentation mask

image image generation cv image segmentation vlm computer vision tao toolkit video nvidia nim nvidia

ipd rfdiffusion

A generative model of protein backbones for protein binder design.

biology nim bionemo drug discovery protein generation ipd

microsoft phi-3-vision-128k-instruct

Cutting-edge open multimodal model exceling in high-quality reasoning from images.

image cv vision assistant vlm visual question answering computer vision language generation image-to-text video microsoft

google paligemma

Vision language model adept at comprehending text and visual inputs to produce informative responses

image cv vision assistant vlm visual question answering computer vision language generation image-to-text video google

stabilityai stable-diffusion-xl

Generate images and stunning visuals with realistic aesthetics.

image generation text-to-image stabilityai

microsoft kosmos-2

Groundbreaking multimodal model designed to understand and reason about visual elements in images.

image cv multimodal vlm visual question answering computer vision image understanding image-to-text video microsoft

google deplot

Translate images of plots into tables with one-shot visual language understanding.

nemo retriever multimodal data ingestion image-to-text google

nvidia neva-22b

Multi-modal vision-language model that understands text/images and generates informative responses

image cv vision assistant non-commercial use only vlm visual question answering computer vision image-to-text video nvidia