WeaveAI SAAS - AI Chat, Image, Video, Audio, Code / 65+ Models Available

DISCLAIMER: This app integrates with external AI providers, including OpenRouter, Replicate, ElevenLabs, which are paid services and require registering an account in order to get access to their API.

Overview

WeaveAI is a comprehensive AI platform that supports 100+ AI models from many different providers. Seamlessly switch between text, image, video, and audio generation models while maintaining full conversation history and file management. By combining best-in-class providers – WeaveAI offers just the right set of tools, thoughtfully integrated and ready for production use.

Blazing fast by design, built with modern technologies and scalability in mind. Seamless user experience with intuitive chat interface and modern UI. SaaS-ready: Built for business growth.

Try out the demo!

Landing page URL: demo.weaveai.cc
App URL: demo.weaveai.cc/newchat
Admin dashboard URL: demo.weaveai.cc/admin
Demo login credentials are available on the login page: demo.weaveai.cc/login

To prevent abuse, only the following models are enabled in the Demo:
GPT OSS, Gemma 3, Kimi K2, GLM 4.5 Air

Key Features

Seamless User Experience:
- Responsive mobile-first, modern UI
- Dark/Light theme with auto-detection
- Multilingual support
- Guest user access

Media Generation & Management:
- Text generation (40+ models)
- Image generation (30+ models)
- Video generation (30+ models)
- Audio generation tools
- Image editing
- Dedicated Library page for Media
- Dedicated History page for Audio

Advanced Chat Features:
- Multi-model conversations
- Chat history with pinning
- Multimodal support (text + images + videos)
- Clean URL routing

Complete Authentication System:
- Email/password registration & login
- OAuth integration (Google, Apple, X, Facebook)
- Password reset flow
- Session management with caching

Full Billing Infrastructure:
- Stripe Checkout integration
- Subscription management
- Usage tracking
- Subscription plan Upgrade/Downgrade capability
- Payment history & receipts
- Multi-tier pricing plans (configurable via admin dashboard)
- Customer billing portal

Smart Storage:
- Cloudflare R2 cloud storage integration
- Cloud storage signed URLs
- Admin configurable storage settings

Powerful Admin Dashboard:
- Analytics with beautiful charts
- User Management
- Subscriptions and Transactions table views
- System settings (APIs, AI models, OAuth, Storage, Security, Payment Methods, Mailing, Site Settings, etc…)

Email System:
- Welcome emails
- Email verification
- Password reset notifications
- Template-based system
- Admin-configurable SMTP

Security:
- XSS Prevention
- Rate Limiting & Brute Force Protection
- Bot Protection (Cloudflare Turnstile)
- Security Headers
- Password Hashing
- Session Hardening
- Security Event Monitoring
- GDPR Compliant

WeaveAI is perfect for:
- Entrepreneurs wanting to launch an AI SaaS
- Developers looking to deploy a ready-made product
- Agencies looking for a white-label solution
- Startups needing rapid MVP deployment
- Indie Hackers seeking passive income
- Companies wanting internal AI tools

Available AI Models

OpenAI:

• GPT-5.2, GPT-5.1, GPT-5-Mini, GPT-5-Nano, GPT-5.1-Chat, GPT-5.1-Codex, GPT-5.1-Codex-Max, GPT-4.1-Mini, GPT-o3-Mini, GPT-o1, GPT-o4-Mini, GPT OSS 20B
• Image gen: GPT Image 1, GPT Image 1 Mini, DALL-E 3, DALL-E 2
• Video gen: Sora 2, Sora 2 Pro

Anthropic:

• Claude Opus 4.5, Claude Sonnet 4.5, Claude Haiku 4.5

Google:

• Gemini 2.5 Pro, Gemini 3 Pro, Gemini 2.5 Flash, Gemini 2.5 Flash Lite
• Image gen: Nano Banana, Nano Banana Pro, Imagen 4, Imagen 4 Ultra, Imagen 4 Fast, Imagen 3, Imagen 3 Fast
• Video gen: Veo 3.1, Veo 3.1 Fast, Veo 3, Veo 3 Fast, Veo 2

Meta:

• Llama 4 Maverick, Llama 4 Scout

DeepSeek:

• DeepSeek v3.2 Speciale, DeepSeek v3.2, DeepSeek v3.2 Exp, DeepSeek R1

xAI:

• Grok 4, Grok 3, Grok 3 Mini, Grok Code Fast 1, Grok 4 Fast
• Image gen: Grok 2 Image

Alibaba:

• Qwen3 Coder, Qwen3 Thinking, Qwen3 30B A3B
• Image gen: Wan 2.2 Image, Qwen Image
• Video gen: Wan 2.5 T2V, Wan 2.5 T2V Fast, Wan 2.5 I2V, Wan 2.5 I2V Fast, Wan 2.2 5b Fast

Moonshot:

• Kimi K2 0905, Kimi K2 Thinking

Mistral:

• Mistral Devstral, Mistral Nemo, Mistral Small 3.2

ZAI:

• GLM 4.6V, GLM 4.6, GLM 4.5 Air

StabilityAI:

• Image gen: Stable Image Ultra, Stable Image Core, Stable Diffusion 3.5 Large, Stable Diffusion 3.5 Large Turbo, Stable Diffusion 3.5 Medium, Stable Diffusion 3.5 Flash

KlingAI:

• Video gen: Kling 2.5 Turbo Pro, Kling 2.1, Kling 2.1 Master, Kling 2.0, Kling 1.6 Standard, Kling 1.6 Pro, Kling 1.5 Standard, Kling 1.5 Pro

Black Forest Labs:

• Image gen: FLUX 2 Pro, FLUX 2 Flex, FLUX 2 Dev, FLUX Krea Dev, FLUX 1.1 Pro Ultra, FLUX.1 Kontext Pro, FLUX.1 Kontext Max, FLUX.1.1 Pro, FLUX.1.1 Ultra

Luma Labs AI:

• Image gen: Photon-1, Photon Flash-1
• Video gen: Ray-2, Ray Flash-2

ByteDance:

• Image gen: SeeDream 4, SeeDream 3, Dreamina 3.1
• Video gen: SeeDance 1 Pro, SeeDance 1 Pro Fast, SeeDance 1 Lite

Tencent:

• Image gen: Hunyuan Image 3, Hunyuan Image 2.1

Leonardo AI:

• Image gen: Lucid Origin, Phoenix 1.0
• Video gen: Motion 2.0

Ideogram:

• Image gen: Ideogram V3 Quality, Ideogram V3 Balance, Ideogram V3 Turbo, Ideogram V2, Ideogram V2 Turbo

Pixverse:

• Video gen: Pixverse v5, Pixverse v4.5, Pixverse v4

NOTE: In order to use the platform as a SaaS and charge other end-users, you need to purchase the Extended license.

CHANGELOG

[March-24-2026] v2.5

 * Refactor the Authentication system to a better Auth library * Performance optimizations - pages should load much faster now (even on serverless environments) * Add new LLM models * Various styling/UI bugfixes and improvements 

[Feb-18-2026] v2.1

 * Add new LLM models * Add new 'Projects' feature     * Dedicated 'Projects' page     * Create a Project, and define custom instructions and upload text files (with instructions, context, information, etc)     * View all project chats within the Project page * Bugfixes and vulnerability patches 

[Feb-05-2026] v2.0

 * New page and UI for image and video generation     * New UI elements for image and video generation models like model selector with search functionality, categories, model description     * Add uploaded image preview     * New prompt input area     * New select options for generating images and videos: quality, aspect ratio, resolution, style, duration, seed     * Video gen specific options like Start Image Reference, and End Image Reference     * All history of generated images and video are now on the same image/video generation page     * New grid/gallery design for the generated images and videos     * New details/metadata page for the generated images and videos     * New feature that allows you to use the generated images as a reference to generate other images or videos     * New feature that allows you to use existing prompts and parameters as a reference to generate other images or videos * Refactor the model selector on the /newchat page for LLMs     * You can now toggle to only show models from specific providers     * Search functionality so you can search for LLM models     * Add favorite models feature * New features within the chat conversation page     * Add edit feature for user-sent messages (this reprompts the AI with the newly saved message)     * Add retry/re-generate feature for AI-sent messages     * Add copy buttons for both AI and User sent messages     * Better markdown formatting and better code syntax highlighting, code snippets now tells you which programming language the code is     * Add conversation branching feature, you can now branch a conversation to message to start a new chat from that point     * Add 'Read Aloud' feature that allows you to play AI messages via text-to-speech (TTS)     * Add the following buttons to AI messages: 'Generate image', 'Generate video', 'Generate TTS', 'Generate music', which takes the AI message and inputs it as a prompt to the option you selected * New Tool Calling components - it now shows up in the conversation when a tool has been used, and its output * New web search functionality - you can now select to use web search on models that support it * Refactored the file upload functionality * Add new 'Take a screenshot' feature in the file upload functionality which allows you to take a screenshot and attach the screenshot directly * Add new models (LLMs, image & video generation, Audio generation) * Remove OpenAI API Key from admin dashboard as it's no longer needed * Lots of fixes in terms of functionality and visual styling issues 

[Dec-12-2025] v1.4.0

 * Add ElevenLabs integration for AUDIO tools - TTS (Text to Speech), STT (Speech to Text), Voice Changer (Speech to Speech), Music generation, Sound Effects * Add new image generation models:     * Nano Banana, Nano Banana Pro, FLUX 2 Pro, Flex, Dev, Krea Dev * Add new language models:     * Gemini 3 Pro, Claude Opus 4.5, Sonnet 4.5, GPT 5.2, GPT 5.1, GPT 5.1 Chat, GPT 5.1 Codex, GPT 5.1, Codex Max, DeepSeek v3.2 Speciale, DeepSeek v3.2, DeepSeek v3.2 Exp, Kimi K2 Thinking, Mistral Devstral, GLM 4.6V, GLM 4.6 * Add setting in the admin dashboard to configure the app's default page - Landing Page or App Page * Add setting in the admin dashboard to configure a global system prompt for all chats * New installation docs with expanded guides to deploy the app on multiple environments (new guides coming soon too) - docs.weaveai.cc * Fix a bug related to updating the app's logos and favicon in the Branding section of the admin dashboard * Fix a bug when saving a new pricing plan usage limit as 0 (zero), it would get saved as null (unlimited) usage instead in the database * Fix a bug on the /pricing page where a pricing card would still show a checkmark even though usage was not included in the plan * Fix a bug where the cache for the site settings in the admin dashboard would ocassionally not get invalidated and therefore require a server restart in order for the changes to take effect 

[Nov-13-2025] v1.3.5

 * Add new video generation models:     * Pixverse: v5, v4.5, v4 * Fix a bug related to video generation models not accepting image as a reference * Other minor bug fixes 

[Nov-6-2025] v1.3.0

 * Added new models     * Image generation: GPT Image 1 Mini, Imagen 4 Fast, Imagen 3 Fast, Qwen Image, Flux Schnell, SeeDream 4, SeeDream 3, Dreamina 3.1, Hunyuan Image 3, Hunyuan Image 2.1, LeonardoAI Lucid Origin & Phoenix 1.0, Ideogram V3 & V2     * Video generation: Sora 2, Sora 2 Pro, Veo 3.1, Veo 3.1 Fast, Veo 3 Fast, Wan 2.5, SeeDance 1 Pro, SeeDance 1 Lite, LeonardoAI Motion 2.0, Kling v2.5, Kling 1.6, Kling 1.5 * Refactored the image & video generation models integration, now uses Replicate as the API provider * Update the /admin/settings/ai-providers page, now you can add a Replicate API token * Fix storage race condition issues on GET/POST media operations on serverless platforms * Fix race condition bug where the app would fallback to local storage even though cloud storage is integrated * Fix bug related to image upload URL/URI logic * Fix security header issue where videos would not load in the UI when using cloud storage  ### Notes * By reworking the API integration to Replicate, now you only need to provide one API key to enable and use all image and video generation models * It will be much more straightforward to add new models in the future, cleaner code, more reliable, and easier to maintain 

[Oct-28-2025] v1.2.0

 * Add smooth text streaming for AI responses * The landing page is now on the index route instead of /landing * Refactor the OpenRouter integration for LLMs and multi-modal models * Refactor the Tool Calling feature for OpenRouter models * Fix a bug on the /library page where a link leading to the original chat for the generated media was not working 

[Oct-23-2025] v1.1.0

 * Add a visual 'spinner' component indicating the model is generating its response * Add new models: Claude Sonnet 4.5, Claude Haiku 4.5, GPT 5 Codex * Fix a bug that would make the images on the /library page not load occasionally when using cloud storage * Fix a race condition bug that would make the response from a model save to a different chat if a user navigates to it while the response is being generated * Fix database schema deprecation warning * Fix a minor responsiveness bug on the /settings/billing page 

[Oct-14-2025] v1.0.0

 * Product launch