Pick the model per conversation
Choose the model from the composer — a fast one for quick edits, a frontier one for hard problems. Change it whenever you like.
Any model.
Your terms.
alexandr is model-agnostic by design — use the leading models, or your own Claude or ChatGPT subscription, and switch whenever a better one ships. Your workspace doesn’t move.
- No lock-in
- Your own subscription
- Every major provider
- Switch any time
Works with the models you already trust
- OpenAI
- Anthropic
Three ways in
Whichever model you pick — today’s, tomorrow’s, or your own subscription — the workspace is the same.
Or your own subscription
Already pay for Claude or ChatGPT? Connect your subscription and the assistant uses it — your provider bills you, as it does today.
Works with the leading providers
OpenAI, Anthropic and Google today, more as they ship. Your apps, skills and history don't care which model answers.
What model-agnostic means in practice
Switch mid-conversation
Change the model from the composer, whenever you like. Draft with a fast model, finish with a strong one — the conversation carries over.
Your workspace stays put
Apps, skills, files and history belong to your workspace, not to a provider. Switching models moves nothing and breaks nothing.
Nothing to migrate
There's no export day. Because nothing is tied to one provider, trying a new model is a dropdown, not a migration project.
The model is one half of the story — the assistant is what puts it to work across your files and apps.