Features
Multi-model chat with GPT-5.5, Claude Opus 4.8, Gemini 3.1 Pro, Grok 4.20, DeepSeek, Llama 4
Side-by-side model comparison (compare responses simultaneously)
Image generation: FLUX.2 Pro, Nano Banana Pro, GPT-5 Image, Seedream 4.5
Video generation: Sora 2, Veo 3.1, Seedance 2.0, Kling 2.6, PixVerse 5.5
AI image editing: paint-over regions and describe changes
Chat with files of any size (PDFs, DOCX, text files)
Web search with real-time citations
Custom AI agents and reusable prompt templates
OpenAI-compatible API for use with coding agents (OpenCode, Aider, Cursor)
App integrations via MCP (8000+ tools)
Voice chat and text-to-speech
Usage dashboard showing daily messages and model usage
Projects: organize chats, files, and instructions
Auto-switching fallback when a model is unavailable
Chat search across history
Image-to-video transformation
Video-to-video style transfer
Aleph 2.0 one-frame editing (Edit Studio)
Runway Agent 2.0 for marketing campaigns with analytics
Seedance 2.0 multi-input (text, image, video, audio)
Nano Banana 2 image generation and editing
Nano Banana 2 Lite fast image generation
Gemini Omni Flash video generation
Seed Audio 1.0 text-to-audio (speech, sound, music)
Inpainting and outpainting
Green screen keying and motion tracking
4K upscaling and high-resolution output
Third-party model integration (Kling 3.0, Veo 3.1, etc.)
