📚SparkAi Free Public Version

🚀Feature Introduction

• Supports user registration and login: WeChat QR code, email, and mobile number.
• AI large model support: Integrates with OpenAI GPT-3.5 / GPT-4.0 models, plus Microsoft Azure and some domestic AI models (Baidu ERNIE Bot, Alibaba Cloud Tongyi Qianwen, Zhipu ChatGLM, iFlytek Spark).
• DALL·E Painting: Supports DALL·E 2 and DALL·E 3.
• AI Painting: MJ text-to-image, image-to-image, and local editing/redrawing.
• TTS Voice Recognition: Whisper & TTS for voice recognition dialogue.
• AI Agents: Custom preset prompt applications and support for custom AI agent applications.
• ...and more

🛠️Installation and Deployment

• Click here for the Detailed Graphic Installation and Deployment Tutorial
• Install Pagoda Panel (version 9.2.0 or above). Go to the official Pagoda Panel website and download the official version script for installation.
• After installation, log in to the Pagoda Panel, click on Docker in the menu bar. If it's your first time, you will be prompted to install the Docker service. Click "Install Now" and follow the prompts.
• Once installation is complete, search for SparkAi in the app store, find SparkAI-ChatGPT-AiWeb, click install, and configure the basic options to complete the installation.

🌟Commercial License Version (Additional Supported Features)

• Full Model Support / Custom Integration: Freely add and integrate the latest large models in the admin backend (no system update needed); supports the official OpenAI API + any standard chat-format API on the market, covering OpenAI (GPT-6 / GPT-5.4 / o-series), Anthropic Claude (Claude-Opus-5-5 / Claude-Fable-5-1, etc.), Google Gemini, DeepSeek, and mainstream domestic models.
• Dual-Endpoint Dialogue Architecture (V6.9.6): Automatically routes between the Chat Completions / Responses endpoints based on model capabilities, with built-in automatic fallback retries; the large model global configuration center manages routing and billing policies in one place.
• Multimodal & Document Understanding: Multi-image understanding (up to 9 images), upload recognition and online preview of PDF / Word / PPT / Excel / Markdown and other documents, reasoning chain display, and web search.
• Highly Reliable Dialogue Core (V6.9.3): Decoupled upstream/downstream connections, so switching sessions or closing the page does not interrupt generation; SSE content is saved while generating, with support for active stop and fallback on errors.
• Professional Painting System: Standalone GPT-Image-2 / GPT-Image-2.5 painting module, standalone Nano Banana 2 painting module, full Midjourney / Niji features (V7 / V8, inpainting, character / style reference images, image blending), and DALL·E 2 / 3.
• AI Video Generation: VEO3.1 / Sora-2 video, Midjourney HD video, Pika text-to-video / image-to-video, and Seedance video (via Coze-Agent).
• Agents: Coze agents with plugins, workflows, functions, and knowledge bases; GPTs app integration; custom Prompt preset apps.
• Membership Store System: Multiple balances (regular model points, advanced model points, painting points, Agent points), permanent / limited-time packages, and billing methods such as per-use, time-based, and combo packages.
• Points Details & Zero Charges on Failure (V6.9.6): Consumption, refunds, and exemptions are recorded consistently on the user end and admin backend; failed model calls, timeouts, and empty replies can be exempted from charges via a switch.
• Payment System: Supports official WeChat Pay (Native on PC / JSAPI inside WeChat), EasyPay, CodePay, and HupiJiao Pay, with synchronous order status checks, order search, and management.
• Distribution & Growth: A + B distribution model, invitation rewards, check-in, redemption codes, and guest mode.
• Security & Risk Control: Sensitive words + Baidu content moderation (covering dialogue, painting, and mind maps), login device & remote-login detection, sensitive information masking, and the "System Function Test" switch (blocks AI generation requests before filing is completed).
• Full System Internationalization: Full frontend and backend i18n, automatic switching by IP / browser language, and one-click AI internationalization in the admin backend.
• Brand-New UI: Card style / Notion style themes, AI dialogue immersion mode, and multi-platform support for PC + H5 + WeChat official account.
• Complete Admin Backend: Data dashboard, model and API key pool management, dynamic menus, and site customization.
• For more features, see Introduction - System Core Functions.