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

# Use Claude Cowork with abliteration.ai

> Configure Claude Cowork on 3P (Claude Desktop's third-party inference mode) to route through abliteration.ai.

**To use Claude Cowork with abliteration.ai**, configure Claude Desktop's third-party inference mode with `inferenceProvider: gateway` and `inferenceGatewayBaseUrl: https://api.abliteration.ai`. Once configured, every Cowork and Claude Code Desktop session routes through abliteration; Anthropic never sees prompts or completions. The same Claude Desktop binary runs both standard and 3P modes — the managed configuration profile activates 3P.

## Requirements

| | |
| - | - |
| OS | macOS 13 (Ventura) or later, Windows 10 or 11 (Virtual Machine Platform feature enabled) |
| App | Claude Desktop, downloaded from [claude.com/download](https://claude.com/download) |
| Gateway endpoint | `https://api.abliteration.ai` |
| API key | An `ak_...` key from the [console](https://abliteration.ai/console) |

## Configuration keys

Cowork reads its configuration once at launch. Quit and relaunch after any change.

| Key | Required | Value |
| - | - | - |
| `inferenceProvider` | Yes | `gateway` |
| `inferenceGatewayBaseUrl` | Yes | `https://api.abliteration.ai` |
| `inferenceGatewayApiKey` | Yes | `ak_YOUR_API_KEY` |
| `inferenceGatewayAuthScheme` | No | `bearer` (default) or `x-api-key` |
| `inferenceGatewayHeaders` | No | JSON-string array of extra `"Name: Value"` headers (e.g. `["X-Org-Id: team1"]`) |
| `inferenceModels` | No | JSON-string array. Omit to auto-discover via `GET /v1/models`. |

## Setup via the in-app UI

For a single device or to generate a profile for fleet rollout:

1. Open Claude Desktop. **Help → Troubleshooting → Enable Developer Mode**.
2. **Developer → Configure third-party inference**.
3. Select `Gateway`, enter the values from the table above, save.
4. Use **Export** to write `.mobileconfig` (macOS) or `.reg` (Windows) for distribution.

## Setup via MDM

Push the same keys directly to the OS preference store.

### macOS

Domain: `com.anthropic.claudefordesktop`. Deliver via Jamf, Kandji, Mosyle, or any MDM that supports App Configuration.

```xml theme={"system"}
<key>inferenceProvider</key>
<string>gateway</string>
<key>inferenceGatewayBaseUrl</key>
<string>https://api.abliteration.ai</string>
<key>inferenceGatewayApiKey</key>
<string>ak_YOUR_API_KEY</string>
```

Array-typed keys must be a `<string>` containing a JSON array, not a native plist `<array>`:

```xml theme={"system"}
<key>inferenceModels</key>
<string>["abliterated-model"]</string>
```

### Windows

Registry path: `HKCU\SOFTWARE\Policies\Claude` (per-user) or `HKLM\SOFTWARE\Policies\Claude` (machine-wide). Deliver via Group Policy, Intune, or any MDM that supports `.reg` files.

```ini theme={"system"}
[HKEY_CURRENT_USER\SOFTWARE\Policies\Claude]
"inferenceProvider"="gateway"
"inferenceGatewayBaseUrl"="https://api.abliteration.ai"
"inferenceGatewayApiKey"="ak_YOUR_API_KEY"
```

## Authentication

| Scheme | Header sent |
| - | - |
| `bearer` (default) | `Authorization: Bearer ak_...` |
| `x-api-key` | `x-api-key: ak_...` |

Both are accepted on `/v1/messages`. For environments that disallow static keys, point `inferenceCredentialHelper` at an executable that prints a short-lived credential to stdout (TTL via `inferenceCredentialHelperTtlSec`, default 3600 s).

## Models

When `inferenceModels` is unset, Cowork populates the picker from `GET /v1/models`. Today that surfaces `abliterated-model`. To pin explicitly:

```json theme={"system"}
"inferenceModels": ["abliterated-model"]
```

The first entry is the default.

## Verifying the install

Launch Claude Desktop on a test machine. You should see:

* **Cowork** and **Code** tabs in the left navigation
* No **Chat** tab
* A **Gateway** sign-in option

If users see an error at launch, check that `inferenceProvider` is set and that the gateway key is valid. macOS console logs and Windows Event Viewer surface deeper errors.

## Per-user policy

Cowork's blanket usage caps (`inferenceMaxTokensPerWindow`, `inferenceTokenWindowHours`) apply per device. For different policies by team, issue [project-scoped keys](/api/authentication) for the relevant projects. Published policies scoped to a project apply to its Cowork traffic. See [Policies](/policy-gateway/overview).

## Data handling

Inference traffic terminates at abliteration.ai — Anthropic never sees prompts, completions, or tool inputs. Telemetry to Anthropic is metadata only (token counts, error diagnostics) and can be disabled with `disableEssentialTelemetry` and `disableNonessentialTelemetry`. See [Policy data and access](/policy-gateway/security) for policy decision data.

## Reference

* Anthropic [configuration key reference](https://claude.com/docs/cowork/3p/configuration)
* Anthropic [gateway provider page](https://claude.com/docs/cowork/3p/gateway)
* Anthropic support: [install and configure](https://support.claude.com/en/articles/14680741-install-and-configure-claude-cowork-with-third-party-platforms), [use with 3P](https://support.claude.com/en/articles/14680729-use-claude-cowork-with-third-party-platforms)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.