# Connect a personal ChatGPT plan as a model provider

> Self-hosted users can sign in with ChatGPT from provider settings to run on their own ChatGPT plan, with account status, reconnect controls and private models.

Source: <https://everruns.com/docs/changelog/2026-10-03-chatgpt-plan-provider/>

Date: 2026-10-03
Products: Platform
Category: Feature
Available: In 0.38.0
Pull request: everruns/everruns#4136

![Everruns and OpenAI logos side by side, announcing ChatGPT plan connections](https://everruns.com/docs/_astro/integration@2x.Bs2HiplC_19f9XT.webp)

ChatGPT now appears in the provider grid. Open **Models > Providers > Connect provider > ChatGPT > Sign in with ChatGPT**, approve plan use in ChatGPT, and return to Everruns. The connection belongs to you, not the organization: its models are available only to you, and the detail page shows account status, quota guidance, and reconnect and disconnect controls.

Self-hosted deployments use OpenAI’s Sign in with ChatGPT for open-source applications. The ChatGPT plan transport is now part of `everruns-drivers`.

See [ChatGPT plan](https://everruns.com/docs/features/chatgpt/). PR [#4136](https://github.com/everruns/everruns/pull/4136).