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

# Connections

> Bringing your own model provider, connecting a ChatGPT account, and the secrets your sandboxes get

**Connections** is where you put credentials that belong to you: a model provider
key, a ChatGPT subscription, or environment secrets for the machine.

<Frame caption="A new account has none of these — the platform's own providers are already there">
  <img src="https://mintcdn.com/sploxltd-165e0515/FtagtnY5r9E1DKmP/images/app/connections.png?fit=max&auto=format&n=FtagtnY5r9E1DKmP&q=85&s=6ae92695224dedcc7f8fffdafd2b3363" alt="The Connections screen with no connections yet" width="2880" height="1800" data-path="images/app/connections.png" />
</Frame>

<Note>
  This screen is about **models and secrets**, not about Gmail or Slack. Connecting
  an external service — an MCP server, with OAuth or with an API key — happens on
  the [Tools](/app/tools) screen.
</Note>

## Adding a provider

**Add connection** offers five:

<Frame caption="What you can connect">
  <img src="https://mintcdn.com/sploxltd-165e0515/FtagtnY5r9E1DKmP/images/app/connections-providers.png?fit=max&auto=format&n=FtagtnY5r9E1DKmP&q=85&s=dbc27b54f5d276002e734432729b5ed3" alt="The provider grid: OpenAI, Anthropic, Gemini, Splox and Codex" width="2880" height="1800" data-path="images/app/connections-providers.png" />
</Frame>

| Provider        | What it takes                                                                                                  |
| --------------- | -------------------------------------------------------------------------------------------------------------- |
| OpenAI          | An API key. *Works with OpenAI, Azure OpenAI, local LLMs (Ollama, LM Studio), and most third-party providers.* |
| Anthropic       | An API key for the Claude API or a compatible endpoint.                                                        |
| Gemini          | An API key for Google's Gemini API.                                                                            |
| Splox           | An API key for Splox Models.                                                                                   |
| Codex (ChatGPT) | Not a key — an OAuth authorization of your ChatGPT subscription.                                               |

The key form is short: a name for the connection, the key itself, and under
**Advanced** a custom base URL when the endpoint is not the provider's own.

<Frame caption="An API-key connection, with the base URL override open">
  <img src="https://mintcdn.com/sploxltd-165e0515/FtagtnY5r9E1DKmP/images/app/connection-openai.png?fit=max&auto=format&n=FtagtnY5r9E1DKmP&q=85&s=0d70512cf6712155473aec1bb259175d" alt="The OpenAI connection form with name, API key and custom base URL" width="2880" height="1800" data-path="images/app/connection-openai.png" />
</Frame>

### What OAuth looks like here

**Codex (ChatGPT)** is the one that does not take a key. It routes requests
through the ChatGPT subscription you already pay for: the device flow opens on
`chat.openai.com`, you authorize there, and Splox keeps the rotating tokens for
you afterward. The button says **Connect ChatGPT account** and there is nothing
else to fill in.

## Where the credential lives

Splox keeps the credential and uses it when a run names the endpoint. What you
get in exchange is a new **endpoint** — the same kind of thing the platform's own
OpenAI, Anthropic, Gemini and Splox entries are.

A connected endpoint turns up in two places:

* In a chat, under the composer's **Advanced → Endpoint**, by the name you gave
  it. Picking it there runs that conversation on your credential.
* In a harness, as `text_llm_endpoint_id` on an agent — the id of the endpoint
  row, and the alternative to `provider`, never its companion. The ids come from
  [`/v2/llm-endpoints`](/api/llm-endpoints).

Each card on the Connections screen shows the provider, the base URL if you set
one, and whether it is active. The bin icon disconnects it, after a confirmation;
the credential goes with it, and anything pointed at that endpoint has to be
pointed somewhere else.

## Secrets

The second tab is for the machine rather than the model.

<Frame caption="Environment secrets: key/value pairs the sandbox gets as environment variables">
  <img src="https://mintcdn.com/sploxltd-165e0515/FtagtnY5r9E1DKmP/images/app/connections-secrets.png?fit=max&auto=format&n=FtagtnY5r9E1DKmP&q=85&s=abe540526f57da90804a4879c85a292c" alt="The Secrets tab with the environment secrets description" width="2880" height="1800" data-path="images/app/connections-secrets.png" />
</Frame>

Encrypted key/value pairs, injected as environment variables into your agent
sandboxes — for the agent and its sub-agents, across every chat. Values are never
shown again after you save them.

This is where a token belongs when the *agent's own code* needs it: a GitHub PAT
a script pushes with, an API key a tool of your harness reads from
`os.environ`. Provider keys go in the Providers tab instead, because those are
used by the platform, not by your code.

<CardGroup cols={2}>
  <Card title="Models" icon="brain" href="/concepts/model">
    Which model to reach for, and what an agent's `model` and `provider` mean.
  </Card>

  <Card title="Tools" icon="wrench" href="/app/tools">
    Connecting an external service through an MCP server.
  </Card>
</CardGroup>