200+ AI models from every major provider
The AI workspace for real work.
The best model keeps changing, and idapt always has it. 200+ models, your files, and your agents in one workspace, so you never switch tools again.
Free to start. No credit card. Never trained on your data.
See it working
Agents
Custom AI agents that actually do work.
- Pick any of 200+ models per agent
- Skills compose like Lego
- Scoped permissions
Drive
A file-first AI workspace.
- Drop anything, query everything
- Real folders, real hierarchy
- Preview in the browser
Computers
Computers your agents can drive.
- Pair your machines
- Persistent disk
- Commands in chat
Every model. Find yours in seconds.
Search 200+ models, compare real outputs, and use the best one for each task.
249 models from 26 providers
Same prompt. Different models. Real outputs.
“Pelican on a bicycle”
Muse Spark 1.1<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 400 300" width="600" height="450"> <!-- Wheels --> <circle cx="110" cy="220" r="42" fill="none" stroke="#2B2B2B" stroke-width="7"/> <circle cx="110" cy="220" r="42" fill="none" stro…
GPT 5.6 Luna<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 800 600" width="800" height="600"> <defs> <linearGradient id="sky" x1="0" y1="0" x2="0" y2="1"> <stop offset="0" stop-color="#dff4ff"/> <stop offset="1" stop-color="#f8f…
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 400 300" width="400" height="300"> <!-- Bicycle wheels --> <circle cx="110" cy="210" r="45" fill="none" stroke="#333" stroke-width="6"/> <circle cx="110" cy="210" r="8" fill="#333"/…
New models land continuously
Create a free account and get an email when new frontier models arrive.
Made for how you work
Pick your workflow and see exactly how idapt fits it.
GPT, Claude, Gemini, Grok, and 200+ more in one chat. New models when they land.
Every model. One workspace.Write with one model, edit with another, and generate the images, audio, and video too.
Every draft, every medium.Everything that isn't editing a repo: sandboxes, agents, real computers, one API.
The workspace around your editor.Triangulate models, scan literature with citations, and keep every source in your Drive.
Research that checks itself.Shared folders, agents, and automations: with roles, budgets, and an audit trail.
One workspace the whole team works in.Agents with memory, real computers they can drive, and schedules that run overnight.
Give it to an agent.Up and working in under a minute


Pick any model
200+ models from every major provider, in one chat, with transparent pricing.
Bring your work
Files, notes, and memory your agents can actually use, organized in one workspace.
Delegate the rest
Agents, automations, and real computers finish the work while you check back later.
One subscription. Every capability.
Every feature. One workspace.
Multi-Model Chat
GPT, Claude, Gemini, Grok, Llama: pick mid-conversation, cheapest-first.
Voice Mode
Voice in, voice out. Claude, GPT, Gemini, whichever you pin.
Voice HUD
A push-to-talk overlay that floats above every app: ask, hear the answer, keep working.
Web Search
Real-time info, cited sources, every model: no per-provider tax.
Image Generation
DALL·E, Imagen, FLUX, Stable Diffusion: same composer, same files.
Video Generation
Veo, Runway, Kling, Luma: short clips generated in chat, saved to your Drive.
Audio Generation
Dozens of voices for text to speech, plus fast accurate transcription: in every chat.
Transcription
Dictate messages and transcribe recordings, accurately, in any chat.
Drive
Folders, previews, and lightweight versioning for AI work.
Secrets
Store API keys, tokens, and passwords: encrypted, never shown to agents.
Sharing
Public URLs for files, agents, and chats: granular, revocable.
Workspaces
Shared folders, agents, computers, and chats: one container.
Tasks
Tasks Lists, multiple assignees, sub-tasks, blockers, and duplicates: clean OR-123 ids.
Memory
A durable, private memory every agent reads and updates as it works.
Agents
Skills, scoped permissions, persistent memory: any model you pick.
Subagents
Parallel subagents, isolated context, full observability.
Automations
Delegated runs with schedules, bounded execution, and full progress traces.
Skills
Installable instruction bundles agents load on demand: curated, forkable, shareable.
Code Execution
Sandboxed Python, Node, and shell: agents and you, side-by-side.
Computers
Daemon-connected machines with real filesystems and agent-friendly controls.
Computer Use
Agents see the screen, click, and type to finish real UI work: with your consent.
Cloud Computers
Spin up cloud machines your agents can use: per-second billing, hibernate when idle.
Local AI
Run open models on your own hardware with Ollama: private, free, no rate limits.
AI Gateway
OpenAI-, Anthropic-, and OpenRouter-compatible endpoints with routing you control.
API & SDK
A typed SDK and a versioned REST API over chats, files, agents, and computers.
CLI
Script files, agents, chats, and 200+ models: from your shell.
MCP
Use your files, agents, and tools from any MCP-compatible client.
Tunnels
One command exposes any port. SSH included.
Private by design
Never trained on, never sold
idapt makes money from subscriptions and credits, never from your data.
Or no provider at all
Run open models on your own computer, with no third-party AI provider involved.
Builders ship with idapt
Already paying for one AI?
Keep the model you use
The model you rely on today is in idapt, at full quality.
Add every other model
Switch mid-conversation whenever another model is better for the task.
Plus a real workspace
Files, agents, computers, and automations that chat apps don't have.
Start free. Upgrade when you need more.
Free
Try everything, every day
- 200+ AI models in one workspace
- Free daily AI usage that resets every day
- Agents, Drive files, web search & image generation
- Local AI: run open models on your own computer
- 1 cloud computer · 0.5 h/week
- Connect 1 of your own computers
- 1 GB storage
- Web & desktop apps · read-only CLI & MCP
Pro
For daily power users
Everything in Free, plus:
- Included usage for every model — refreshes every 5 hours and weekly
- Weekly budget for premium models
- 10 cloud computers · 7.7 h/week
- Connect 20 computers
- 200 GB storage
- 20 workspaces · up to 20 members each
- Priority support
Max
Maximum headroom
Everything in Pro, plus:
- 4× Pro's included usage
- Unlimited cloud computers · 23 h/week
- 1 TB storage
- Unlimited workspaces · connect 50 computers
- Priority routing & priority support
Free includes real daily usage of 200+ models, agents, files, web search, and image generation. No credit card, no trial clock.
Transparent, usage-based pricing, always shown before you pay.
Credits never expire.
Ready to try it?
Create your free account and start working in seconds.
- Every model, always current
- Your files, agents, and computers in one workspace
- Free to start, no credit card