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

# Connect your AI provider

> Choose the model that powers managed agents and Signal: the Arize-managed model, your own provider key, or your own AI gateway. See where your data goes for each.

Every managed agent run, including [Signal](/docs/ax/observe/signal.md), needs a model behind its [harness](/docs/ax/agents/connect-your-harness.md). You have three options:

| Option | Who pays | Available on |
| - | - | - |
| **Arize-managed model** | Arize | US and EU SaaS regions |
| **Your own provider key** (Anthropic, OpenAI, Azure OpenAI, Vertex AI, or Cursor) | You | Enterprise |
| **Your own gateway or custom endpoint** (LiteLLM, an internal proxy, or a self-hosted model) | You | Enterprise |

To see which company processes agent data under each option, see [Where your data goes](#where-your-data-goes).

If you don't pick a provider, runs use the Arize-managed model. Free and Pro accounts always run Signal on the Arize-managed model.

## Use the Arize-managed model

Nothing to set up. Pick **Arize-managed** in the AI Provider picker, or leave the provider empty. Arize pays for the model and applies per-tier usage limits.

The Arize-managed model isn't available in the CA region or on AWS-hosted deployments, so you need your own provider there.

## Bring your own provider key

Use your own key when you want model traffic covered by your own agreement with the provider, for example a zero-data-retention agreement with Anthropic or OpenAI.

**1. Add the AI provider**

Under **Settings → Account Settings → AI Providers**, add a provider the harness supports. See [Connect your harness](/docs/ax/agents/connect-your-harness.md#the-harness) for the provider each harness supports.

**2. Allow it in agents**

Tick **Managed Agents** on the provider's row in the AI Providers table. You can also do this from the AI Provider picker with **Enable Key**.

**3. Select it**

Choose the provider on an agent config, during agent setup, under **Configure Signal**, or as the space default under **Space Settings**.

## Connect your own gateway

If your company sends all model traffic through its own AI gateway, connect the gateway as a [Custom Model Endpoint](/docs/ax/security-and-settings/integrations-playground/custom-llm-models.md) and use it for managed agents like any other provider. Requests go to your gateway's URL, and your gateway decides which model serves them and what is logged.

Any endpoint that speaks the OpenAI or Anthropic API format works, for example [LiteLLM](/docs/ax/security-and-settings/integrations-playground/litellm.md), an internal proxy, or a self-hosted model server. Arize translates Claude Code's requests when the endpoint uses the OpenAI format.

| Setting | Supported |
| - | - |
| **API format** | OpenAI-compatible (Chat Completions) or Anthropic-compatible (Messages) |
| **Authentication** | Static API key, or OAuth 2.0 client credentials. OAuth works only with OpenAI-compatible endpoints. |
| **Extra headers** | Sent with every request, for gateways that need a tenant, route, or subscription header |
| **Models** | The model names you configure on the integration. Arize uses those names, so gateway aliases and Azure deployment names work. |

**1. Add a Custom Model Endpoint**

Under **Settings → Account Settings → AI Providers**, add a **Custom Model Endpoint**. Enter the base URL, choose an authentication method, add any extra headers, and list the model names your gateway serves. See [Custom Model Endpoint](/docs/ax/security-and-settings/integrations-playground/custom-llm-models.md) for each field.

**2. Test it**

Use **Test integration** to confirm that Arize can reach the gateway and get a response.

**3. Allow it in agents and select it**

Tick **Managed Agents** on the row, then choose the endpoint on an agent config, under **Configure Signal**, or as the space default.

> [!NOTE]
>
> Claude Code can run on Anthropic, OpenAI, Azure OpenAI, and compatible custom endpoints. Codex needs an OpenAI provider, OpenCode needs Anthropic, and Cursor needs a Cursor key. The provider you pick must match the harness.

## Where your data goes

While an agent works, it sends the model everything it reads. That includes project traces, your instructions, issue context, and data from any connected repo, Datadog, or Dynatrace skill. Arize doesn't redact this content before it reaches the model, so the provider you choose is what protects it.

| Provider option | Who receives the agent's prompts | What governs that data |
| - | - | - |
| **Arize-managed model** | Anthropic. In the EU region, Claude on Google Cloud Vertex AI in `europe-west1`, so traffic stays in the EU. | The commercial terms between Arize and that provider. You accept this when you enable Signal or start a run with the Arize-managed model. |
| **Your own provider key** | Your provider account | Your contract with that provider, such as a zero-data-retention agreement |
| **Your own gateway** | Your gateway, and only the models it routes to | Your own infrastructure and policies. No other model provider sees the prompts. |

Some details hold for every option:

* **Arize's gateway relays requests and keeps no copy of them.** Requests pass through Arize's agent gateway, which adds your credential and forwards each one to the provider. Request and response bodies aren't written to Arize's logs.
* **Your credentials never enter the sandbox.** The sandbox holds a placeholder. Arize adds your key or OAuth token to each request as it leaves.
* **Arize keeps run history in your account.** Each run's messages, final answers, and tool activity stay in your Arize account so you can review the run, subject to [managed agent permissions](/docs/ax/agents/connect-your-harness.md#permissions).

If your security policy doesn't allow agent data to go to a provider you don't contract with, use your own provider key or gateway. Contact Arize to turn off Arize-managed models for your account, so nobody can start a run on them.

## Related docs

* [Connect your harness](/docs/ax/agents/connect-your-harness.md): harnesses, skills, and permissions
* [Signal](/docs/ax/observe/signal.md): ranked issues per tracing project
* [Custom Model Endpoint](/docs/ax/security-and-settings/integrations-playground/custom-llm-models.md): base URL, authentication, and extra headers
* [LiteLLM](/docs/ax/security-and-settings/integrations-playground/litellm.md): connect a LiteLLM proxy
* [Anthropic AI Provider](/docs/ax/security-and-settings/integrations-playground/anthropic.md): bring your own Anthropic key
* [OpenAI AI Provider](/docs/ax/security-and-settings/integrations-playground/openai.md): bring your own OpenAI key