📚SparkAi Public Good Free Commercial Edition
🎉 2026 Special Public-Good Rebuild Commercial System Capabilities Public Good V2.1.0
2026 special rebuild with commercial system capabilities: membership packages, online payment (EasyPay / CodePay / HupiJiao), distribution, and other commercial features are fully supported, so you can deploy it for free and run it commercially; custom AI model integration is coming soon (expected October 2026).
🚀Feature Introduction
The SparkAi Public Good Free Commercial Edition (SparkAI-ChatGPT-AiWeb) · Public Good V2.1.0 (2026 Special Public-Good Rebuild) is one of the few free public-good editions that support commercial operation: deploy it for free and use membership packages, online payment, distribution, and other commercial features.
- Supports user registration and login: WeChat QR code, email, and mobile number.
- Membership packages: Permanent / limited-time membership packages, purchased online on the user end and customized in the admin backend.
- Online payment: EasyPay, CodePay, and HupiJiao Pay (HupiJiao supports a custom payment gateway), so users can buy membership packages online.
- Distribution: Referral invitations, with commission withdrawals to WeChat / Alipay / bank card.
- 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).
- Custom AI model integration Coming soon: Integrate custom AI models in the admin backend, with upcoming support for GPT-6, Claude-Opus-5-5 / Claude-Fable-5-1, Gemini, DeepSeek, and all other models (GitHub update pending, expected October 2026).
- 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)
Version Notes
- Public Good Free Commercial Edition (Public Good V2.1.0 · 2026 Special Public-Good Rebuild): Built on the V3.2.0 feature base (2023.11), providing AI chat, basic DALL·E / Midjourney painting, redemption codes, plus membership packages, online payment, distribution, and other commercial operation features — commercial operation is supported for free. Some features will be updated, and custom AI model integration (GPT-6, Claude, Gemini, DeepSeek, and all other models) is coming soon (GitHub update pending, expected October 2026).
- Commercial License Version: Continuously iterated up to V6.9.6 (2026.09). On top of the public-good edition it adds custom integration of all models, standalone painting modules, AI video generation, Coze agents, multi-channel payment and points details, security and risk control, full system internationalization, and other complete capabilities, with continuous major updates.
📊Feature Comparison
| Feature | Public Good Free Commercial Edition (Public Good V2.1.0) | Commercial License Version (V6.9.6) |
|---|---|---|
| Scope of use | ✅ Commercial operation supported | ✅ Commercial operation supported |
| Version iteration | 2026 Special Public-Good Rebuild (V3.2.0 feature base), with some feature updates | ✅ Continuous major updates |
| AI models | ✅ GPT-3.5 / GPT-4.0, Azure, and some domestic models 🔜 Coming soon: GPT-6, Claude-Opus-5-5 / Claude-Fable-5-1, Gemini, DeepSeek, and all other models (expected 2026.10) | ✅ GPT-6, Claude-Opus-5-5 / Claude-Fable-5-1, Gemini, DeepSeek, and all other models |
| Custom integration of the latest models in the backend (no system update needed) | 🔜 Coming soon (GitHub update pending, expected 2026.10) | ✅ |
| Dual-endpoint routing / model global configuration center | ❌ | ✅ |
| Deep reasoning (o3 / DeepSeek-R1, etc.) | ❌ | ✅ |
| Multi-image understanding / multi-type document understanding and online preview | ❌ | ✅ |
| DALL·E painting | ✅ DALL·E 2 / 3 | ✅ DALL·E 2 / 3 |
| Midjourney painting | ✅ Text-to-image, image-to-image, partial repainting | ✅ Full features: V7 / V8, Niji, character / style reference images, HD video |
| Standalone GPT-Image-2 / Nano Banana 2 painting modules | ❌ | ✅ |
| AI video generation (VEO3.1 / Sora-2 / Pika / Seedance) | ❌ | ✅ |
| AI agents | ✅ Custom Prompt preset apps | ✅ Plus Coze Agent, GPTs apps, and agent store |
| Registration and login | ✅ WeChat QR code / email / mobile number | ✅ Plus login device and remote-login detection |
| Redemption codes | ✅ | ✅ |
| Membership packages | ✅ Permanent / limited-time membership packages | ✅ Multiple points balances; permanent / limited-time / combo packages; custom pricing per model |
| Payment system | ✅ EasyPay / CodePay / HupiJiao Pay | ✅ WeChat Pay / EasyPay / CodePay / HupiJiao Pay |
| Distribution | ✅ Referral invitations, commission withdrawals | ✅ A + B distribution, per-user commission rates, withdrawal thresholds |
| Points details / zero charge on failed model calls | ❌ | ✅ |
| Enhanced risk control (sensitive info masking, "System Function Test" switch, etc.) | ❌ | ✅ |
| Full system internationalization | ❌ | ✅ |
| 2026 new UI (card / Notion dual styles, immersion mode) | ❌ | ✅ |
| Complete commercial admin backend | Basic management | ✅ Data dashboard, model and key pools, dynamic menus, global configuration |
🚀Key Enhancements of the Commercial License Version
🤖 AI Model Dialogue
Full Model Support & New-Generation Dialogue Architecture
- 🧩 Freely integrate the latest models in the backend (no system update needed): OpenAI, Claude, Gemini, domestic, and mainstream third-party models all use the standard chat format, so new models can be added and used in the backend as soon as they are released
- 🔥 Full model support: Covers OpenAI (GPT-6 / GPT-5.4 / o-series / Codex), Anthropic Claude (Claude-Opus-5-5 / Claude-Fable-5-1, etc.), Google Gemini, DeepSeek, Azure OpenAI, and domestic models such as Doubao, Tongyi Qianwen, Zhipu, iFlytek Spark, and Tencent Hunyuan
- 🧭 Dual-endpoint routing [V6.9.6]: Automatically routes between Chat Completions / Responses endpoints by model capability, with built-in fallback retries; the model global configuration center manages routing and billing policies in one place
- 🛡️ Highly reliable dialogue core [V6.9.3]: Switching sessions or closing the page does not interrupt generation; SSE content is saved while generating, with active stop and error fallback
- 📄 Multimodal & document understanding [V6.9.6]: Multi-image understanding (up to 9 images) and photo upload; upload recognition and online preview of PDF / Word / PPT / Excel / Markdown documents
- 🤔 Reasoning & web search: Streaming reasoning chains, web search, dialogue navigation bar, Markdown / KaTeX / Mermaid rendering, mind maps, and TTS voice dialogue
🎨 Professional AI Painting & 🎬 AI Video
Standalone Painting Modules & Video Generation
- 🖌️ Standalone GPT-Image-2 / GPT-Image-2.5 module [V6.9.2]: Text-to-image, up to 8 reference images, online editing and brush/box editing, custom quality and resolution
- 🍌 Standalone Nano Banana 2 module [V6.9.4]: gemini-3.1-flash-image / gemini-3-pro-image, multi-image reference editing, 2K / 4K output (depending on the model)
- 🎨 Full Midjourney / Niji features: V7 / V8, Vary Region repainting, image blending, character / style reference images, separate billing for Fast / Relax channels
- 🔁 Painting experience: "Paint the Same", automatic points refund on failure, AI gallery, and sensitive-word blocking of painting prompts before submission
- 🎬 AI video generation: VEO3.1 / Sora-2 video, Midjourney HD video, Pika text-to-video / image-to-video, and Seedance video (via Coze-Agent)
🧠 AI Agents
Agents & App Ecosystem
- 🤖 Coze Agent: Coze plugins, workflows, functions, and knowledge-base agents, with streaming display of reasoning and tool calls, plus one-click batch import
- 📈 Agent store: Rating / popularity algorithms, keyword search, and link / WeChat QR code / poster sharing
- 🧠 GPTs & preset apps: GPTs app search and integration, custom Prompt preset apps, and user-created agents
💰 Commercial Operation
Multi-Channel Payment, Membership Points & Distribution (Fully Enhanced over the Public-Good Edition)
- 🛍️ Payment system: Official WeChat Pay (Native on PC / JSAPI inside WeChat), EasyPay, CodePay, and HupiJiao Pay, with order status sync checks and management
- 🧑🤝🧑 Membership points: Multiple balances (regular / advanced model points, painting points, Agent points); permanent / limited-time packages; per-use / time-based / combo billing, with custom pricing per model
- 🧾 Points details & zero charge 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 via a switch
- ⏏️ Distribution & growth: A + B distribution, withdrawals (Alipay / WeChat / bank card), invitation rewards, check-in, and guest mode
- ✨ Channel load balancing: Multi-channel call management and multi-API-key rotation (priority / weight / status management)
🔐 Security & 🛠️ Admin Backend
Security, Operation & Multi-Platform Experience
- 🚥 Content risk control: Custom sensitive words + Baidu content moderation, covering dialogue, painting, and mind maps with pre-submission blocking
- 📍 Account security [V6.9.6]: Login device and remote-login detection, forced logout on remote login, forcing specified users offline from the backend, and unified masking of sensitive information
- 🧪 "System Function Test" switch [V6.9.4]: Blocks all AI generation requests until generative AI filing is completed
- 💻 Complete commercial admin backend: Data dashboard, model and API key pool management, model global configuration center, dynamic menus, carousels, dialogue demo data, and site customization
- 🌐 Full system internationalization [V6.9.1]: Full frontend and backend i18n, automatic switching by IP / browser language, and one-click AI internationalization in the admin backend
- 🎨 2026 new UI [V6.9.0]: Card / Notion dual styles and AI dialogue immersion mode, adapted to PC / mobile H5 / tablet / WeChat official account
For the full feature list (61 items), see Introduction - System Core Functions or Commercial License; for license inquiries, see Contact Us.