> ## Documentation Index
> Fetch the complete documentation index at: https://docs.baseten.co/llms.txt
> Use this file to discover all available pages before exploring further.

# Roll out Grid to developers

> Send developers a ready-to-edit announcement, script setup across machines, and know what setup changes in each coding agent.

Developers connect to Grid by running [`baseten grid setup`](https://docs.baseten.co/reference/cli/baseten/grid#setup), which walks them through the rest. Send them a short announcement that names their team, models, and limit. On machines you manage centrally, script setup instead.

## Before you announce

* Each team has at least one route, and its harness defaults and spend limits are set.
* Developers are members of the right teams in Baseten, through invitations or [SCIM](https://docs.baseten.co/organization/sso-and-scim.md).
* Developers can install the [Baseten CLI](https://docs.baseten.co/reference/cli/baseten/overview.md), or you install it for them.

## Pilot with one team

Before a wider rollout, ask a few developers to complete [developer setup](https://docs.baseten.co/grid/developers/set-up.md) using the team's defaults, then test representative tasks. Include developers with custom agent settings. Confirm that they can:

* Send a request through a team route and use their required MCP tools.
* Check usage attribution and request a higher limit.

Use the team's measured usage to choose models and limits. A lower token price alone doesn't establish lower cost for the same task; compare completed work and usage over the same period. Treat external-provider costs in Grid as estimates.

## Announcement template

Copy this message into your internal docs, email, or chat, and replace the bracketed parts.

```md theme={"system"}
Subject: Use [Claude Code / Codex / OpenCode / Pi] with Baseten Grid

You now have access to coding models through Baseten Grid. Your team, [team name],
can use [list the models], with a monthly limit of $[amount] per person.

To connect your coding agent (macOS or Linux):

1. Sign in to Baseten with your company account: [SSO sign-in link or instructions].
2. Install the Baseten CLI: [install command or link to your managed package].
3. Sign in from the CLI:
     baseten auth login
4. Connect your coding agent and follow the prompts:
     baseten grid setup --team "[team name]"
5. Restart your coding agent and pick one of the [team name] models.

Check your spend this month at any time:
     baseten grid user-settings describe --team "[team name]"

Setup replaces your coding agent's model and endpoint settings without saving the
previous values. If you've customized those, copy the agent's configuration file
first. MCP servers and other settings aren't changed.

If you hit your limit or need a model that isn't listed, contact [admin contact or channel].
Setup guide: https://docs.baseten.co/grid/developers/set-up
```

## What setup changes

Tell developers what to expect before they run setup:

* **Model and endpoint settings are replaced.** Setup overwrites the coding agent's model list, default models, and Baseten endpoint settings without saving the previous values. Developers who pointed their agent at another gateway or proxy lose that configuration.
* **Other configuration stays.** Setup preserves MCP servers, plugins, permissions, and other unrelated settings in the agent's configuration files. Developers still need to verify tool authentication and model support for their workflows. Claude connectors added through a Claude account don't work while Claude Code points at Grid; configure those tools as MCP servers in Claude Code instead.
* **Codex signs out of OpenAI.** For Codex, setup signs out of OpenAI and ChatGPT and disables ChatGPT login while Grid is configured.
* **Coding agents use short-lived tokens.** Setup configures Claude Code, Codex, and Pi to get short-lived Grid tokens from the Baseten CLI, so no long-lived key is stored. OpenCode gets a Grid API key for the machine on its first run.

To remove the Grid integration settings, a developer runs [`baseten grid teardown`](https://docs.baseten.co/reference/cli/baseten/grid#teardown). Teardown doesn't restore replaced values. For the removal and restoration procedure, see [Remove Grid from a coding agent](https://docs.baseten.co/grid/developers/set-up.md#remove-grid-from-a-coding-agent).

## Script setup

`baseten grid setup` prompts for confirmation, so pass `--yes` and name the harness and team when you run it from a script or a device-management tool:

```sh theme={"system"}
baseten grid setup --harness claude-code --team "<team>" --yes
```

Prefer the standard setup so each developer's coding agents use their own Grid credentials. Spend is attributed to the developer, and personal Baseten API keys aren't subject to Grid spend limits. Sharing a key across developers loses per-developer attribution.

To install an existing key, set `BASETEN_API_KEY` and pass `--use-session-credential`. Confirm its owner and scope before distributing it. The CLI never creates, rotates, or deletes that key:

```sh theme={"system"}
BASETEN_API_KEY="<api-key>" baseten grid setup \
  --harness claude-code --team "<team>" --use-session-credential --yes
```

## Keep agents up to date

When you add, remove, or change a team's routes or defaults, developers' coding agents pick up the change the next time setup runs. [`baseten grid sync`](https://docs.baseten.co/reference/cli/baseten/grid#sync) replays each machine's last setup with the team's current routes, and does nothing when there's nothing to change.

> [!WARNING]
>
> For Codex, sync can restart the background server and interrupt an in-progress turn. With `--yes`, it skips the confirmation prompt. Schedule sync when developers aren't actively using Codex.

```sh theme={"system"}
baseten grid sync
```

Pass `--yes` to skip confirmation in non-interactive automation, where the flag is required. After syncing, restart the coding agent and confirm that its model picker lists the updated routes.

A route the team has removed falls back to its default, with a warning.