What is the difference between a foundation model and an application built on one?

A foundation model is the underlying trained system — the weights, checkpoint, or API that generates text, images, or other outputs. Applications built on top of it add a user interface, specific prompting, and workflow logic for a particular use case. This category of 268 listings covers the models themselves, such as DeepSeek-R1, GPT-5, and Stable Diffusion XL, rather than the applications built around them.

What are open-weight models and how do they differ from proprietary APIs?

Open-weight models like DistilGPT2 and DeepSeek-R1 release their trained weights publicly, allowing developers to download, fine-tune, and self-host the model without depending on an external API. Proprietary models like those from OpenAI are accessed via an API where you pay per token but never see the underlying weights. Open-weight models offer more control and lower ongoing costs at scale, while proprietary APIs are easier to get started with and receive continuous updates.

How do multimodal vision-language models differ from text-only LLMs?

Multimodal models accept both images and text as input — you can show the model a photo and ask questions about it, have it describe an image, or use visual context alongside written instructions. Text-only LLMs process and generate language only. Many frontier models available through APIs now support multimodal input, though the quality of visual understanding varies across models.

How do I choose the right LLM for a specific task?

The right choice depends on the task type (reasoning, coding, creative writing, vision), latency requirements, context window size, cost per token, and whether you need to fine-tune or self-host. Tools like Roboflow Computer Vision and Firecrawl in this category are examples of specialized models or infrastructure serving specific developer use cases. Evaluating models on a representative sample of your actual task is more reliable than relying on benchmark scores alone.

Best AI Models & LLMs

471 tools

Discover the best AI Models & LLMs — from AI Models and AI Apps to AI Hugging Face, AI GitHub Repos, and AI Platforms, this is where developers and researchers discover tools that elevate their projects: training computer vision systems, deploying language models, experimenting with reasoning algorithms, and managing model versions. Browse 471 AI Models & LLMs across AI Models, AI GitHub Repos, LLMs, AI Apps and AI Platforms and more.

471 tools

Compact voice-action model that converts speech directly into function calls. It operates offline, requires no GPU, and adapts to various tools through JSON schemas.NeuDecide is a compact voice-action model that converts speech directly into function calls. It operates offline, requires no GPU, and adapts to various tools through JSON schemas.

AI Models & LLMs

See the Top 5 AI Models

Versatile omni-modal parsing model that converts diverse inputs like documents, images, charts, and videos into structured JSON. It excels in perception…Youtu-Parsing-Omni is a versatile omni-modal parsing model that converts diverse inputs like documents, images, charts, and videos into structured JSON. It excels in perception…

AI Models & LLMs

See the Top 5 AI Models

High-performance OCR model offering advanced layout and visual understanding capabilities. It provides accurate transcription and bounding box coordinates for…LightOnOCR-3-4B is a high-performance OCR model offering advanced layout and visual understanding capabilities. It provides accurate transcription and bounding box coordinates for…

AI Models & LLMs

See the Top 5 AI Models

Contextual embedding model designed for document chunks in RAG systems. It encodes document chunks together, reflecting their surrounding…pplx-embed-v2-context-9b-preview is a contextual embedding model designed for document chunks in RAG systems. It encodes document chunks together, reflecting their surrounding…

AI Models & LLMs

See the Top 5 AI Models

Compact multilingual text model supporting translation across 150 languages. It excels in multimodal image translation and follows detailed translation…Index-Translate-2B is a compact multilingual text model supporting translation across 150 languages. It excels in multimodal image translation and follows detailed translation…

AI Models & LLMs

See the Top 5 AI Models

Open-source model designed for making rapid decisions across various domains. It utilizes a 0.8 billion parameter 'System 1' model to provide calibrated probabilities…Jeff is an open-source model designed for making rapid decisions across various domains. It utilizes a 0.8 billion parameter 'System 1' model to provide calibrated probabilities…

AI Models & LLMs

See the Top 250 AI GitHub Repos

GitHub project that transforms any large language model (LLM) into a Jev-style decision model. It offers typed decisions and real probabilities without requiring…AnyJev is a GitHub project that transforms any large language model (LLM) into a Jev-style decision model. It offers typed decisions and real probabilities without requiring…

AI Models & LLMs

See the Top 250 AI GitHub Repos

Public GitHub repository showcasing a demo project. It allows developers to contribute and collaborate on the development of AI models and tools,…claude-opus-5-5-demo is a public GitHub repository showcasing a demo project. It allows developers to contribute and collaborate on the development of AI models and tools,…

AI Models & LLMs

See the Top 250 AI GitHub Repos

Family of System One-style models fine-tuned from Qwen3.5. It is designed for making one-pass typed decisions with calibrated probabilities, providing a streamlined…Decider is a family of System One-style models fine-tuned from Qwen3.5. It is designed for making one-pass typed decisions with calibrated probabilities, providing a streamlined…

AI Models & LLMs

See the Top 250 AI GitHub Repos

Official inference framework for 1-bit large language models (LLMs) developed by Microsoft. It enables efficient processing and deployment of LLMs, optimizing…BitNet is an official inference framework for 1-bit large language models (LLMs) developed by Microsoft. It enables efficient processing and deployment of LLMs, optimizing…

AI Models & LLMs

See the Top 250 AI GitHub Repos

Research initiative by Fudan NLP Lab, focusing on developing comprehensive evaluation frameworks for large language models across various disciplines. It offers…LLMEval is a research initiative by Fudan NLP Lab, focusing on developing comprehensive evaluation frameworks for large language models across various disciplines. It offers…

AI Models & LLMs

See the Top 250 AI Apps

Fast CPU-based optical character recognition tool designed for line detection, CTC recognition, reading order, and markdown processing. It is ideal for developers…Indra OCR is a fast CPU-based optical character recognition tool designed for line detection, CTC recognition, reading order, and markdown processing. It is ideal for developers…

AI Models & LLMs

See the Top 250 AI GitHub Repos

llm-architecture-from-scratch is a GitHub repository by Yeonwoo Sung that focuses on implementing large language model architectures from scratch using PyTorch. It provides a…

AI Models & LLMs

See the Top 250 AI GitHub Repos

Accelerated version of Qwen-Image-2.1, designed for efficient text-to-image generation and image editing. It features an 8-step denoising process and…Qwen-Image-2.1-Turbo is an accelerated version of Qwen-Image-2.1, designed for efficient text-to-image generation and image editing. It features an 8-step denoising process and…

AI Models & LLMs

See the Top 5 AI Models

Language and dialect classifier for Arabic script. It identifies Modern Standard Arabic, various Arabic dialects, and non-Arabic languages using the same…LIDstral Arabic is a language and dialect classifier for Arabic script. It identifies Modern Standard Arabic, various Arabic dialects, and non-Arabic languages using the same…

AI Models & LLMs

See the Top 5 AI Models

StepFun's flagship AI model designed for agentic work. It excels in software engineering, professional knowledge work, and finance, offering advanced…Step 5 Preview is StepFun's flagship AI model designed for agentic work. It excels in software engineering, professional knowledge work, and finance, offering advanced…

AI Models & LLMsFinance & Banking

See the Top 5 AI Models

Supervised fine-tuned text-to-image model from OpenMOSS. It supports natural-language prompts, tag sequences, and JSON layouts for text and object arrangement,…MOSS-Image-SFT is a supervised fine-tuned text-to-image model from OpenMOSS. It supports natural-language prompts, tag sequences, and JSON layouts for text and object arrangement,…

AI Models & LLMs

See the Top 5 AI Models

Offers open decision models ranging from 0.8B to 27B parameters, providing calibrated probabilities for each option. It generates concise thoughts when…StartLux-Decision offers open decision models ranging from 0.8B to 27B parameters, providing calibrated probabilities for each option. It generates concise thoughts when…

AI Models & LLMs

See the Top 250 AI GitHub Repos

AI model designed for speculative decoding, enabling parallel drafting with adjacent causal injection. It enhances performance by unfolding the causal…Qwen3-8B-DSpine-b16 is an AI model designed for speculative decoding, enabling parallel drafting with adjacent causal injection. It enhances performance by unfolding the causal…

AI Models & LLMs

See the Top 5 AI Models

Multimodal model offering strong reasoning capabilities with constant memory usage. It supports O(N) generation and O(1) persistent history, providing efficient…EdgeRock is a multimodal model offering strong reasoning capabilities with constant memory usage. It supports O(N) generation and O(1) persistent history, providing efficient…

AI Models & LLMs

See the Top 250 AI GitHub Repos

5B-parameter base DiT model designed for high-quality text rendering, layout generation, and efficient fine-tuning. It serves as a robust tool for developers and…MOSS-Image is a 5B-parameter base DiT model designed for high-quality text rendering, layout generation, and efficient fine-tuning. It serves as a robust tool for developers and…

AI Models & LLMs

See the Top 250 AI GitHub Repos

Frequently Asked Questions

A foundation model is the underlying trained system — the weights, checkpoint, or API that generates text, images, or other outputs. Applications built on top of it add a user interface, specific prompting, and workflow logic for a particular use case. This category of 268 listings covers the models themselves, such as DeepSeek-R1, GPT-5, and Stable Diffusion XL, rather than the applications built around them.
Open-weight models like DistilGPT2 and DeepSeek-R1 release their trained weights publicly, allowing developers to download, fine-tune, and self-host the model without depending on an external API. Proprietary models like those from OpenAI are accessed via an API where you pay per token but never see the underlying weights. Open-weight models offer more control and lower ongoing costs at scale, while proprietary APIs are easier to get started with and receive continuous updates.
The right choice depends on the task type (reasoning, coding, creative writing, vision), latency requirements, context window size, cost per token, and whether you need to fine-tune or self-host. Tools like Roboflow Computer Vision and Firecrawl in this category are examples of specialized models or infrastructure serving specific developer use cases. Evaluating models on a representative sample of your actual task is more reliable than relying on benchmark scores alone.

Know a standout that belongs in AI Models & LLMs?

ToolPotion is the AI tools directory people browse to find the best AI Models & LLMs. Listing is free and every submission is editor-reviewed — put your tool where the search starts.

Submit an AI Tool for AI Models & LLMs

Menu

Best AI Models & LLMs

NeuDecide

Youtu-Parsing-Omni

LightOnOCR-3-4B

pplx-embed-v2-context-9b-preview

Index-Translate-2B

Jeff

AnyJev

claude-opus-5-5-demo

Decider

BitNet

LLMEval

Indra OCR

LLM architecture from scratch

Qwen-Image-2.1-Turbo

LIDstral Arabic

Step 5 Preview

MOSS-Image-SFT

StartLux-Decision

Qwen3-8B-DSpine-b16

EdgeRock

MOSS-Image

Frequently Asked Questions

Know a standout that belongs in AI Models & LLMs?