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

# Claude Cowork

> Route Claude Desktop (Cowork) through Requesty to access 300+ models with a single gateway

[Claude Cowork](https://www.anthropic.com/product/claude-cowork) is Anthropic's desktop app for working with Claude. It now ships with a built-in **Third-Party Inference** mode. Once enabled, Claude Cowork sends every request to the Anthropic-compatible gateway of your choice instead of Anthropic's cloud.

Point it at Requesty and you get:

* **300+ models** available directly from the Claude Cowork model picker: Sonnet, Opus, Haiku, GPT, Gemini, Mistral, Llama, and more.
* **Policies** for [Fallback](/features/fallback-policies), [Load Balancing](/features/load-balancing-policies), and [Latency Routing](/features/latency-routing) without changing a thing on the client.
* **Spend tracking**: every Cowork session shows up in [usage analytics](/features/usage-analytics) and [cost tracking](/features/cost-tracking), tagged as Claude Cowork traffic via the `X-Title` header.
* **No Anthropic account required**. "Continue with Gateway" lets teams use Claude Cowork with just a Requesty key.
* **Enterprise deployment**: export a `.mobileconfig` (macOS) or `.reg` (Windows) file from the Cowork setup UI to roll the Requesty configuration out via MDM / Group Policy.

## How it works

```mermaid theme={"dark"}
sequenceDiagram
    participant CC as Claude Cowork
    participant RQ as Requesty Router
    participant AI as Model Providers

    CC->>RQ: POST /v1/messages (Authorization: Bearer ..., X-Title: Claude-Cowork)
    rect rgb(30, 30, 46)
    Note right of RQ: Authenticate, apply policy, route
    end
    RQ->>AI: Forward to best provider (Anthropic, Bedrock, Vertex, OpenAI, ...)
    AI-->>RQ: Response
    RQ-->>CC: Anthropic-compatible response
```

## Prerequisites

* **Claude Cowork** installed. [Download from Anthropic](https://claude.ai/download).
* A **Requesty API key** from the [API Keys page](https://app.requesty.ai/api-keys).

## Configuration

<Steps>
  <Step title="Enable Developer Mode">
    Open Claude Cowork (no sign-in required) and go to **Help > Troubleshooting > Enable Developer Mode**.

    <Frame>
      <img src="https://mintcdn.com/requesty/WMizieWVJZKS7MCq/images/claude_enable_dev_mode.png?fit=max&auto=format&n=WMizieWVJZKS7MCq&q=85&s=11710114bbbb4a1752491cc7e9344ae3" alt="Claude Cowork Help menu showing Troubleshooting and Enable Developer Mode" width="1902" height="1798" data-path="images/claude_enable_dev_mode.png" />
    </Frame>

    A new **Developer** menu appears in the menu bar.
  </Step>

  <Step title="Open the third-party inference panel">
    From the new menu bar item, choose **Developer > Configure Third-Party Inference**.

    <Frame>
      <img src="https://mintcdn.com/requesty/WMizieWVJZKS7MCq/images/claude_config_gateway.png?fit=max&auto=format&n=WMizieWVJZKS7MCq&q=85&s=72c589a1203311b85452ee12db51589f" alt="Developer menu with Configure Third-Party Inference highlighted" width="1912" height="1792" data-path="images/claude_config_gateway.png" />
    </Frame>
  </Step>

  <Step title="Select Gateway and fill in the Requesty credentials">
    In the **Configure third-party inference** panel, pick **Gateway** (Anthropic-compatible) as the inference backend and enter:

    | Field                     | Value                        |
    | ------------------------- | ---------------------------- |
    | **Gateway base URL**      | `https://router.requesty.ai` |
    | **Gateway API key**       | Your Requesty API key        |
    | **Gateway auth scheme**   | `bearer`                     |
    | **Gateway extra headers** | `X-Title: Claude-Cowork`     |

    <Frame>
      <img src="https://mintcdn.com/requesty/WMizieWVJZKS7MCq/images/claude_requesty_config.png?fit=max&auto=format&n=WMizieWVJZKS7MCq&q=85&s=a7ecc25cbf12fbf74bf60d4dd3e51ec1" alt="Claude Cowork gateway configuration filled in with Requesty router URL, bearer auth, and the X-Title: Claude-Cowork header" width="1868" height="1452" data-path="images/claude_requesty_config.png" />
    </Frame>

    <Info>
      **Why `X-Title: Claude-Cowork`?** Requesty reads the [`X-Title`](/quickstart#optional-headers) header to tag requests in analytics. Setting it to `Claude-Cowork` lets you filter Cowork traffic separately from your API, Claude Code, or Cline usage in [Usage Analytics](/features/usage-analytics) and [Cost Tracking](/features/cost-tracking). You can use any value you like, for example `Claude-Cowork-Design-Team`, to segment further.
    </Info>

    Click **Apply locally** to save. Use **Export** if you want a `.mobileconfig` for macOS MDM or a `.reg` file for Windows Group Policy / Intune (see [MDM deployment](#mdm-deployment) below).

    <Info>
      The other three backends (**Bedrock**, **Vertex**, **Foundry**) talk directly to AWS / GCP / Azure and bypass Requesty. Use **Gateway** if you want routing, fallbacks, spend tracking, and access to non-Anthropic models.
    </Info>
  </Step>

  <Step title="Restart Claude Cowork and continue with Gateway">
    Quit and reopen Claude Cowork. On launch you'll see a chooser. Pick **Continue with Gateway** (labeled *Local configuration*). No Anthropic account is needed.

    <Frame>
      <img src="https://mintcdn.com/requesty/WMizieWVJZKS7MCq/images/claude_continue_gateway.png?fit=max&auto=format&n=WMizieWVJZKS7MCq&q=85&s=3932489015ae7643450a0b22f69eaea6" alt="Claude Cowork startup screen with Continue with Gateway and Sign in to Anthropic options" width="1118" height="1050" data-path="images/claude_continue_gateway.png" />
    </Frame>
  </Step>

  <Step title="Pick a model or policy">
    The model picker in the top-right now lists every model and policy your Requesty org has access to. Select one and start working.

    <Frame>
      <img src="https://mintcdn.com/requesty/WMizieWVJZKS7MCq/images/claude_select_model.png?fit=max&auto=format&n=WMizieWVJZKS7MCq&q=85&s=206d37807a4b0b0be722ac3ce47ac41d" alt="Claude Cowork model picker showing Requesty policies and models like policy/gemini-3-pro, policy/opus-4-6, policy/claude-4" width="1792" height="1584" data-path="images/claude_select_model.png" />
    </Frame>
  </Step>
</Steps>

## Model selection

Any entry from the [Model Library](https://app.requesty.ai/model-list) works. Model IDs follow the familiar `provider/model-name` format:

| Provider               | Example                         |
| ---------------------- | ------------------------------- |
| Anthropic              | `anthropic/claude-sonnet-4-5`   |
| Anthropic (1M context) | `anthropic/claude-opus-4-6[1m]` |
| OpenAI                 | `openai/gpt-4o`                 |
| Google                 | `google/gemini-2.5-pro`         |
| AWS Bedrock            | `bedrock/claude-opus-4-6`       |
| Mistral                | `mistral/mistral-large-latest`  |

**Policies** follow `policy/<policy-name>`:

* `policy/reliable-sonnet-4-5`
* `policy/opus-4-6`
* `policy/gemini-3-pro`

Policies are the recommended default for Cowork. A single policy gives you automatic fallback, load balancing, and latency-aware routing without the user ever needing to pick a specific model.

<Info>
  To use the **1M token context window** for Opus 4.6 or Sonnet 4.5, append `[1m]` to the model name, for example `anthropic/claude-opus-4-6[1m]`.
</Info>

## EU data residency

For EU-only routing, change the gateway base URL to the EU router:

```
https://router.eu.requesty.ai
```

Everything else (auth scheme, headers, model IDs) stays the same. See [EU Routing](/features/eu-routing) for the full list of EU-approved models.

## MDM deployment

The **Export** button in the Configure third-party inference panel produces a ready-to-deploy configuration file so you can roll Requesty out to an entire team:

* **macOS**: `.mobileconfig` payload you can push with Jamf, Intune, Kandji, or any Apple MDM.
* **Windows**: `.reg` file suitable for Group Policy Preferences or Intune custom profiles.

Recommended payload for a fleet rollout:

```
Gateway base URL        https://router.requesty.ai
Gateway auth scheme     bearer
Gateway extra headers   X-Title: Claude-Cowork
Gateway API key         <per-user service-account key>
```

Issue one Requesty key per user (or per team) from the [API Keys page](https://app.requesty.ai/api-keys) or the [Key Management API](/features/key-management-api) so you can attribute spend, set per-user limits, and revoke individual keys without disturbing the fleet.

## Benefits of Requesty + Claude Cowork

<CardGroup cols={2}>
  <Card title="300+ Models, One App" icon="brain">
    Sonnet, Opus, GPT, Gemini, Mistral, Llama, all selectable from the Cowork picker.
  </Card>

  <Card title="Policy-Driven Routing" icon="route" href="/features/fallback-policies">
    Point Cowork at a policy and get fallback + load balancing without touching the client.
  </Card>

  <Card title="Spend Visibility" icon="chart-line" href="/features/cost-tracking">
    Filter Cowork traffic in analytics via the `X-Title: Claude-Cowork` tag.
  </Card>

  <Card title="MDM-Ready" icon="shield-check">
    Export `.mobileconfig` / `.reg` once and push the setup to your whole org.
  </Card>
</CardGroup>

## Troubleshooting

### Still seeing "Sign in to Anthropic" on launch

Claude Cowork only shows **Continue with Gateway** after a valid configuration has been saved. Re-open **Developer > Configure Third-Party Inference**, verify the four fields, and click **Apply locally** again. A full app restart is required.

### `401 Unauthorized` from the gateway

* Confirm **Gateway auth scheme** is set to `bearer` (not `x-api-key`, which is reserved for URLs ending in `*.anthropic.com`).
* Re-paste your Requesty API key. Trailing whitespace from the clipboard is a common culprit.
* Verify the key is active at [app.requesty.ai/api-keys](https://app.requesty.ai/api-keys).

### Model isn't in the picker

Cowork pulls the model list through the gateway, so the model must be approved for your Requesty org. Check:

* The model exists in the [Model Library](https://app.requesty.ai/model-list).
* It's in your org's [Approved Models](/features/approved-models) list (if your org restricts models).
* For policies, the policy name must match `policy/<name>` exactly.

### Cowork traffic isn't tagged in analytics

Open **Developer > Configure Third-Party Inference** and confirm the **Gateway extra headers** field contains `X-Title: Claude-Cowork` (or your custom value). The header is sent on every request and surfaces in [Usage Analytics](/features/usage-analytics) as a filterable field.

### Developer menu doesn't appear

**Help > Troubleshooting > Enable Developer Mode** is a toggle. If the menu isn't showing, it may have been disabled by an MDM profile. Ask your admin, or deploy the exported `.mobileconfig` directly so end users don't need Developer Mode at all.

### Reset the configuration

**Help > Troubleshooting > Reset App Data** wipes the Cowork configuration. Useful when switching between gateway and Anthropic cloud mode during testing.

## Resources

* [Claude Cowork product page](https://www.anthropic.com/product/claude-cowork)
* [Anthropic's official Cowork third-party setup guide](https://support.claude.com/en/articles/14680741-install-and-configure-claude-cowork-with-third-party-platforms)
* [Requesty API Keys](https://app.requesty.ai/api-keys)
* [Requesty Model Library](https://app.requesty.ai/model-list)
* [Fallback Policies](/features/fallback-policies), [Load Balancing](/features/load-balancing-policies), [Latency Routing](/features/latency-routing)
* [EU Routing](/features/eu-routing)