A workspace
for the next
decade.
Forty-plus models. Nine capabilities. One canvas. Multimodal chat, multi-agent collaboration, deep research, image and video synthesis, music, voice, persistent memory, and connectors — woven into a single experimental environment.
Nine capabilities,
working in concert.
Every module shares context. Start in chat, route through agents, finish in research — without losing state.
Multimodal AI Chat
Converse across text, images, audio, and video at once. Token-by-token streaming with auto-router routing every turn to the right model.
Multi-agent collaboration
Planner, researcher, critic — orchestrated in parallel or sequence on a single task. Watch each agent's reasoning unfold live.
Deep Research
Multi-step retrieval across the live web. Synthesised answers with traceable citations and source weight, powered by Deep Research Max.
Image & Video synthesis
Imagen 4 Ultra stills, Nano Banana Pro edits, and Veo 3.1 cinematic motion with native audio — up to 4K at 8 seconds.
Voice & Music
Thirty named voices across Gemini 3.1 and 2.5 TTS, plus Lyria 3 music synthesis — from prompt to clip in seconds.
Document Intelligence
Reason across millions of tokens. Context caching keeps your reference corpus warm between sessions, with grounding from URL context and Maps.
Persistent Memory
Auto-captured facts and preferences, recalled across every chat. Inspect, edit, delete, or pause memory anytime.
Connectors
OAuth bridges to Google Drive, Docs, Gmail, Calendar, and Notion. The AI reads only what you authorise — revoke per service.
Study Companion
Auto-generated quizzes and flashcards from any thread or file, with TTS narration in your chosen voice.
Forty models.
One prompt surface.
Auto-router picks the best model for the job — or pin a specific one. Routing is reversible per turn.
- Gemini 3.1 Profrontier
- Gemini 3.5 Flashpreview
- GPT-5.5flagship
- Grok 4.3xAI
- DeepSeek V4 ProDeepSeek
- Qwen 3.7 MaxQwen
- MiniMax-M3MiniMax
- Gemini 2.5 Prostable
- Gemma 4 31Bopen
- Nano Banana Pro3 Pro
- Nano Banana 23.1 Flash
- Nano Banana2.5 Flash
- Imagen 4 Ultraflagship
- GPT Image 2 Pro4K
- Grok Imagine ImagexAI
- MiniMax Image 01MiniMax
- Qwen Image 2.0Qwen
- Veo 3.1 Preview4K · 8s
- Veo 3.1 Fastfast
- Veo 3.1 Lite1080p
- Seedance 2.0BytePlus
- Seedance 2.0 Fastfast
- Grok Imagine VideoxAI
- MiniMax Hailuo 2.3MiniMax
- Lyria 3 Promusic
- Lyria 3 Clip30s
- Gemini 3.1 TTSTTS
- MiniMax Speech 2.8 HDTTS
- Qwen3 TTS FlashTTS
- Deep Research Agentagent
- Deep Research Maxagent
Data handling,
without the fine print.
We treat your data the way we'd want our own treated. Three things you should know:
Full terms & policyWhat we collect
Only your Google profile — name, email, avatar — to verify identity and personalise your space.
How it's stored
History, files and generated media live in encrypted Google cloud storage, scoped to your account, synced across devices.
We don't sell it
Never. No third-party brokerage, no ad-targeting, no training on your private data.