Claude Cowork

Claude Cowork sends model inference through a Tetrate Agent Router gateway in third-party inference mode. tare integrate claude-cowork writes the gateway config from the logged-in session.

Persona: Developer running Claude Cowork in Claude Desktop against an Agent Router gateway.

Estimated time: 10 minutes.

Outcomes

By the end of this guide:

Claude Desktop is configured for third-party inference through the Agent Router gateway.
A tare integrate claude-cowork apply has written the configLibrary entry and set it active, or the same values were entered in the Developer dialog by hand.
Cowork traffic appears in Request Logs with X-Title: Claude-Cowork and X-Provider: Tetrate AgentRouter.

Prerequisites

A fully set up management plane and data plane.
Claude Desktop with Cowork installed from claude.ai/download.
The tare CLI installed and authenticated:
```
curl -fsSL https://tare.tetrate.ai/tools/install.sh | bash
tare --version
tare api login --base-url https://api.example.tetrate.ai
```
--base-url is the management plane API host (https://api.<tenant>.tetrate.ai), not the Console gateway Base URL. How to derive <tenant> is covered under Configure coding tools with the tare CLI.

Login can be skipped on integrate by passing --gateway-url, --api-key, and --model explicitly, but then nothing is reused from the account.
A dataplane id for the gateway to route through. After tare api login, list dataplanes:
```
tare integrate dataplanes
```
Example output:
```
DATAPLANE   NAME              GATEWAY URL
acme-prod   Acme Production   https://acme-prod.gateway.example.com
acme-dev    Acme Dev          https://acme-dev.gateway.example.com
```
--dataplane takes the workspace id from the DATAPLANE column (for example acme-prod), not the display name in NAME.
Claude Desktop launched at least once on the machine so the Claude-3p user-data directory exists. Without it, tare integrate reports that auto-config is unavailable.

Pro and Max subscriptions and passthrough mode are not supported for Claude Cowork

Claude Cowork through Agent Router runs in gateway mode only: the Agent Router inference key authenticates every request as Authorization: Bearer, and inference is billed through Agent Router.

Signing in with a Claude.ai account (Google or email) bypasses Agent Router entirely: Cowork runs, but traffic does not appear in Request Logs, cost is not attributed through Agent Router, and inference is billed to the Anthropic subscription instead.

Passthrough mode (keeping a Claude Max or Pro subscription as the billing path while the gateway routes and observes traffic) is supported for Claude Code via tare integrate claude-code --passthrough. It is not supported for Claude Cowork.

Configure integration with `tare` CLI (recommended)

After tare api login, preview then apply:

tare integrate dataplanes
tare integrate claude-cowork --dry-run --dataplane <dataplane-id>
tare integrate claude-cowork --dataplane <dataplane-id>

The optional --dry-run flag prints the planned changes with the API key masked and writes no files.

On apply, the CLI:

Asks for confirmation.
Allows selecting a default model.
Configures Claude Desktop to use the gateway instead of the standard sign-in:
- Registers a third-party inference entry named Tetrate AgentRouter in the Claude Desktop user-data directory configLibrary.
- Sets inferenceProvider to gateway, inferenceCredentialKind to static, and writes the Agent Router inference key as inferenceGatewayApiKey.
- Points appliedId in configLibrary/_meta.json at that entry so it becomes active on relaunch.
- Validates the key with GET /v1/models using Authorization: Bearer <key>.

Config files are written under the Claude Desktop user-data directory:

Platform	Path
macOS	`~/Library/Application Support/Claude-3p/configLibrary/`
Linux	`${XDG_CONFIG_HOME:-~/.config}/Claude-3p/configLibrary/`
Windows	`%LOCALAPPDATA%\Claude-3p\configLibrary\`

The entry file is 6167656e-7472-4000-8000-6f7574657200.json; _meta.json indexes it alongside any other saved configurations.

If Claude Desktop is running when apply runs, the CLI prints a warning. Quit Claude Desktop (Cmd+Q on macOS, File then Quit on Windows) before applying, because the app reads configLibrary only at launch.

After apply, quit Claude Desktop completely and reopen it. The sign-in screen opens on the standard Anthropic options (Google and email). The gateway path is the Or sign in with Gateway link at the bottom, which appears only when a third-party inference configuration is present.

Or sign in with Gateway at the bottom of the Claude Desktop sign-in screen

Selecting it opens Welcome to Claude, which confirms that Claude runs through a custom inference gateway using the configuration saved on the device. Select Continue to start Cowork through the gateway. Or sign in with Claude.ai returns to the standard Anthropic sign-in.

Welcome to Claude confirming gateway configuration, with the Continue button

Where more than one configuration is saved, the active entry is switched in Developer, then Configure Third-Party Inference, not from either sign-in screen.

Alternative: manual configuration in Claude Desktop

Where tare integrate cannot write files, or the in-app path is preferred, configure third-party inference in Claude Desktop directly.

Enable Developer Mode

Developer Mode can be turned on from the sign-in screen without signing in to an Anthropic account first. On macOS, use the menu bar. On Windows, open the application menu at the top left of the sign-in screen. In both cases, go to Help, then Troubleshooting, then Enable Developer Mode.

Enable Developer Mode in Claude Cowork

Open third-party inference settings

Go to Developer, then Configure Third-Party Inference. Choose Gateway as the inference provider.

Open Configure Third-Party Inference from the Developer menu

Enter gateway settings

Field	Value
Gateway base URL	GATEWAY URL from `tare integrate dataplanes` (scheme and host only, no `/v1` suffix)
Credential kind	Static API key
Gateway API key	Inference key minted or reused by `tare integrate claude-cowork` on apply
Gateway auth scheme	`bearer`
Gateway extra headers	`X-Title: Claude-Cowork`, `X-Provider: Tetrate AgentRouter`
Models	A Claude model from the catalog (for example `claude-sonnet-5`), or leave empty for model discovery

The Models field takes an explicit list, one model per line, and the first entry becomes the default in the Cowork picker. Left empty, Cowork discovers models from the gateway instead. An explicit list is the more predictable choice for a team, because the picker then offers exactly the approved models.

Discovery calls GET /v1/models, which returns what the inference key can actually call: a model enabled for the organization is listed only where it is also granted to the key's project. See Create a project and grant models.

Cowork always runs in gateway mode, with the Agent Router inference key sent as Authorization: Bearer, so discovery always has the credential it needs. Claude Code differs on both counts: its picker has no explicit model list, and gateway discovery there is off by default and unavailable in passthrough mode. See Connect Claude Code.

Fill the Claude Cowork gateway form with Agent Router settings

Click Apply locally, then relaunch when prompted.

Where auto-config cannot write files, or the write prompt was declined, tare integrate claude-cowork --dataplane <dataplane-id> --yes mints or reuses an inference key and prints paste-ready values. Keys can also be created in the Console under API Keys; see Make an API call.

Verify

Send a prompt in Cowork. With Developer Mode enabled, open Developer, Developer Console, Request Logs. Cowork requests appear as Anthropic Messages traffic with headers such as X-Title: Claude-Cowork and X-Provider: Tetrate AgentRouter.

Claude Cowork request shown in the Developer Console Request Logs

Troubleshooting

Symptom	Likely cause	Fix
Auto-config unavailable; `Claude-3p` directory missing	Claude Desktop never launched on this machine	Launch Claude Desktop once, then re-run `tare integrate claude-cowork`
No Or sign in with Gateway link on the sign-in screen	Third-party inference config was not read	Confirm `configLibrary/_meta.json` has the expected `appliedId`; fully quit and relaunch
Welcome to Claude screen missing after apply	Claude Desktop was not fully quit before relaunch	Quit completely (Cmd+Q or File then Quit), reopen, select Or sign in with Gateway, then Continue
Cowork works but no traffic in Request Logs	Signed in with a Claude.ai account instead of the gateway path	Sign out, reopen, select Or sign in with Gateway, then Continue
Fewer models listed than the administrator enabled	Discovery returns what the key can call	A model enabled organization-wide also has to be granted to the key's project
Validation warning after apply	Wrong dataplane, revoked key, or unreachable gateway	Re-run with `--dry-run`, confirm `--dataplane` id and GATEWAY URL, then re-run with `--yes` to mint and write a fresh key
Manual steps not printed	Confirm prompt declined	Re-run with `--yes` to print paste-ready values including the API key

Where to go next

Configure coding tools with the tare CLI

Shared tare integrate workflow, key rotation, and dry-run preview for all supported tools.

Connect Claude Code

Managed mode and passthrough mode for the Claude Code CLI, including Max subscription billing.

Outcomes​

Prerequisites​

Configure integration with tare CLI (recommended)​

Sign in with Gateway​

Alternative: manual configuration in Claude Desktop​

Enable Developer Mode​

Open third-party inference settings​

Enter gateway settings​

Verify​

Troubleshooting​