Skip to main content
idapt
HomeCodeAI ModelsPricing
Sign inStart free trial
  • Home
  • Pricing
  • AI Models
  • Image models
  • Voice models
  • Video models
  • Rankings
  • New models
  • Model status
  • Multi-Model Chat
  • Agents
  • Computers
  • Drive
  • Automations
  • AI Gateway
  • All features →
  • LLM cost calculator
  • Token counter
  • All free tools →
  • Blog
  • Use cases
  • Comparisons
  • Best of
  • Benchmarks
  • Changelog
  • Help center
  • FAQ
  • Privacy
  • Compare all models
  • Support
  • idapt Code
  • Developers
  • Quickstarts
  • API reference
  • API pricing
  • CLI
  • MCP
  • Downloads
  • Desktop
  • Badges and embeds
© idapt[email protected]TermsPrivacy PolicyLegal noticeReport content
X (Twitter)
Blog

How to Import Your ChatGPT History Into idapt

ITidapt Team·July 2, 2026·Last reviewed July 16, 2026

Years of conversations are the real switching cost of any chat app. idapt removes it: the ChatGPT importer takes the official export ZIP and rebuilds your history, branches included, in your personal workspace. Here's the whole process.

1. Export your data from ChatGPT

In ChatGPT, open Settings → Data controls → Export data and confirm. OpenAI emails you a download link for a ZIP archive. The link expires after 24 hours, so grab it when it arrives.

The ZIP contains conversations.json (every conversation you've ever had, as a branching tree) plus your uploaded files and generated images.

2. Upload the ZIP in idapt

In idapt, open Settings → Import and choose ChatGPT. Pick the ZIP; no need to unpack it. The import streams progress live: conversations first, then binary attachments, each with a per-item result.

Uploads are capped at 1 GB compressed and by your remaining storage. A multi-year archive with thousands of DALL·E images fits comfortably on paid plans; a very large one may need a cleanup first.

3. What you get

  • Every conversation, with its branches. ChatGPT's edit-and-regenerate siblings import as real branches: idapt's message tree keeps them all and restores the branch you had active. Flip between them like you did in ChatGPT.
  • Tool calls preserved. Python runs, DALL·E prompts, and browsing steps survive as structured tool rows; when a model re-reads an imported chat they're folded into readable text so nothing breaks.
  • Your files and images, in a "ChatGPT Import" folder in Drive, attachable to any new chat.
  • Continuable chats. Open any imported conversation and keep typing. Your default agent answers, on GPT models, Claude, Gemini, or any of 200+ others.

Good to know

  • Skips are reported, not hidden. Oversized or over-quota attachments are skipped individually with a reason; the import itself still completes.
  • Re-importing the same ZIP creates duplicate copies of the chats today (titles get a numeric suffix); the attachments folder is reused. Import once, or delete the first batch before retrying.
  • What doesn't come over yet: custom instructions, ChatGPT memories, and custom GPTs. Instructions paste naturally into an idapt agent's system prompt; memory import is on the roadmap.

The full mapping table lives on the ChatGPT migration page, and the help article covers every limit.

After the import

Two things people do next:

  1. Recreate your custom instructions as an agent. Agents carry a system prompt, a default model, tool permissions, and their own memory notes: a strict upgrade over a single instructions box.
  2. Point your API code at idapt. If you also use the OpenAI API, swap one base URL and reach every model through one key.
GuideChatGPTImportAI

Found this helpful? Share it:

  • 1. Export your data from ChatGPT
  • 2. Upload the ZIP in idapt
  • 3. What you get
  • Good to know
  • After the import

Continue reading

  • Cancel ChatGPT Plus Without Losing Your History

    The switcher's checklist: export your ChatGPT archive, import every conversation into idapt in minutes, and know exactly what maps where before you cancel.

  • The Model Treadmill

    The best AI model changes every few months. Chasing it by switching apps is the treadmill; the exit is infrastructure that outlives any model.

  • Why Real Work Needs an AI Workspace

    Chat answers questions; work produces artifacts. Why files, agents, computers, and 200+ models in one workspace beat a standalone chatbot for real output.

  • Fix a Failing Test on Your Own Machine From a Chat

    A worked idapt Code run: two permissions, one prompt, and an agent that reproduces a failing test on your laptop, fixes it, and hands back the diff.

  • Explore idapt

    • idapt vs ChatGPT Plus

      The complete comparison, reviewed and updated.

    • Every migration path

      What moves from each app and how, in one index.

    • Custom AI agents that actually do work.

      Skills, scoped permissions, persistent memory: any model you pick.

    • A file-first AI workspace.

      Folders, previews, and lightweight versioning for AI work.