Free AI Sites & Generative Tools
Explore 72 AI services and local/open-source tools with a free starting option. Listings are grouped by access model; quotas, eligibility, account or card requirements, and terms vary by provider.
Anthropic's AI assistant for writing, coding, research, and multimodal work
Google research assistant for working with source documents and generating study materials.
Run open models locally on your hardware or use hosted cloud models through Ollama.
Extensible, feature-rich self-hosted AI interface for Ollama and OpenAI-compatible APIs
Modular, node-based GUI and execution engine for Stable Diffusion and FLUX
AI code editor with codebase context, agentic edits, and code completion.
State-of-the-art open text-to-image suite by Black Forest Labs with superior prompt fidelity
AI video generation and editing tools for image-to-video and creative production workflows.
Flagship video-01 foundation model with fluid physical dynamics and cinematic realism
Apache 2.0-licensed open-weight video generation model with local and hosted execution options.
Hyper-realistic AI voice synthesis, instant voice cloning, and audio sound effects
Free-tier chat, web search, file analysis, image tools, and GPT discovery; access varies by plan.
AI answer engine with web search and citations; advanced research features depend on plan.
High-efficiency open-architecture reasoning and coding frontier models
Mistral AI web assistant for chat, writing, coding, research, and multimodal work.
Alibaba Qwen web assistant for chat, coding, reasoning, and multimodal tasks.
Developer desktop and CLI client for multi-model workflows and agentic coding.
Open-source LLM app development platform combining BaaS and visual Agentic workflows
Generative UI system crafting modern React components from natural language
Full-stack in-browser AI development sandbox powered by WebContainers
Graphic design and image generator with best-in-class text rendering and composition
Infinite canvas generative design tool outputting crisp vector SVG and raster illustrations
AI video generation tools for text-to-video and image-to-video workflows.
High-speed generative video engine with 1080p anime and realistic motion synthesis
Versatile AI video creation platform with anime, realistic, and selective motion brushes
Expressive AI character video creator with realistic voice synchronization and gestures
Cinematic video generation, character motion, and precise camera controls for creators
Generate complete, broadcast-quality songs with vocals and instrumentation from text
High-fidelity music creation studio with granular track extensions and stem separation
Google AI assistant for chat, multimodal tasks, and Workspace-connected workflows.
Open-weight generative image model family optimized for typography and complex compositions
High-speed, physics-accurate generative video with photorealistic camera motion
CapCut generative AI studio with direct video timeline export and canvas editing
Visual workflow automation platform connecting 1,000+ apps and AI models
High-performance C/C++ inference engine for GGML and GGUF quantized models
High-throughput and memory-efficient LLM serving engine with PagedAttention
AI pair programming terminal assistant that edits code directly in your local git repo
Robust, open-source automatic speech recognition (ASR) system with multilingual translation
Ultra-low-latency LPU AI inference delivering 500+ tokens per second
Enhanced open-source AI chat platform supporting all major LLMs and local engines
All-in-one local desktop and enterprise RAG application with zero configuration
Alibaba open-weight coding models achieving frontier code generation benchmarks
Realtime open-source video diffusion transformer running faster than playback speed
Ultra-fast lightweight 82M open-source text-to-speech model rivaling commercial cloud quality
Meta AI assistant for everyday chat, search, and creative tasks.
Open-source chat interface powered by the best open-weight frontier models
Google AI development environment for testing Gemini models and building prototypes.
Visual framework for building multi-agent AI and RAG applications with Python components
Self-hosted, drop-in replacement REST API for OpenAI running on consumer hardware
The leading open-source AI code copilot extension for VS Code and JetBrains
Full creative production suite for game assets, character design, and image editing
Real-time AI canvas, video generation, and high-definition generative upscaling
CogVideoX checkpoints for text-to-video and image-to-video workflows
Text and image to game-ready 3D models with PBR textures and automatic UV unwrapping
Everyday AI companion with web search grounding and free GPT-4o access
Open-source offline ChatGPT alternative that runs 100% locally on your computer
Privacy-focused local ecosystem to run open LLMs on ordinary consumer laptops
Autonomous AI software engineer that plans, codes, and deploys applications in cloud sandboxes
Generative video perceptual foundation model founded by DeepMind alumni
AI workflow and content marketing engine for go-to-market teams
Experimental AI workspace where you train autonomous agents to execute cross-app tasks
Free reasoning model for coding, complex problem-solving, and long-context work.
Script-to-multiscene video with narration, subtitles and optional digital presenter
Self-hosted app · free Agnes API key required
Local script-to-MP4 pipeline with voice, footage, captions and rendering
Self-hosted · optional provider credentials
Script-to-video assembly with voiceover, subtitles and stock-media workflows
Self-hosted · bring an AI key as needed
Local Shorts studio for scripts, captions, narration and long-video clipping
Self-hosted · local models or optional paid APIs
Customizable media interface with optional local inference and MuAPI cloud generation
MIT app · hosted generation may cost
Open video model family with 480p and 720p text, image and speech workflows
Open weights · local GPU required
22B open-weight audio-video model with text, image and synchronized audio workflows
Open weights · community license · GPU required
Text-to-video research model with high-memory GPU requirements
Open weights · community license · 45–60 GB VRAM
Image-to-video model for animating still images into clips
Open weights · community license · 60 GB VRAM
A directory of independently hosted video-generation model demos
Free demos · queues and account quotas vary