> ## Documentation Index > Fetch the complete documentation index at: https://docs.weaveos.com/llms.txt > Use this file to discover all available pages before exploring further. # What to connect for your plan > Exactly what each Claude and ChatGPT/Codex plan needs to work with Weave Router, and when you need your own API key Every engineer needs a Weave Router key (`rk_…`). Beyond that, what you connect depends on how Claude Code or Codex is signed in, not on the plan name. If the client is signed in with a Claude or ChatGPT account, the router reuses that login automatically. If it is signed in with an API key, the router does not use that key. > [!NOTE] > > **Short answer for Claude Enterprise:** no Anthropic API key is needed. Sign in to Claude Code with your Enterprise claude.ai account, install the router, and Claude turns run on your Enterprise plan. Anthropic bills that usage to your Enterprise organization exactly as it would without the router. > [!WARNING] > > Weave Router **Max** seats (not the same thing as Claude Max) are limited to open-source models on every request, so a Claude or ChatGPT login doesn't unlock Claude or GPT models on a Max seat. Plan coverage works on a Weave Router **Boost** seat or a router key with no individual seat. See [billing](https://docs.weaveos.com/router/billing.md). ## The three things you might connect | What | Who needs it | Where | | - | - | - | | Router key (`rk_…`) | Everyone | The installer, from [Router onboarding](https://router.workweave.ai/start/install) | | Router credits or your own provider key | Anyone whose turns aren't covered by a plan: other model families, plan limits reached, or API-key sign-ins | [Billing & spend](https://docs.weaveos.com/router/billing.md) | | Subscription account enrollment | Optional. Lets the router use a Claude or ChatGPT seat from any client and share seats across your organization | [Subscription accounts](https://docs.weaveos.com/router/subscription-accounts.md) | Your Claude or ChatGPT login is never entered in Weave for ordinary use. It stays in Claude Code or Codex, and the router forwards it with each request it serves on that plan. ## Claude Code | How Claude Code is signed in | Plans | What the router does | What you connect | | - | - | - | - | | claude.ai account | Pro, Max | Forwards your login. Claude turns use your plan's included usage. | Router key | | claude.ai account invited to your organization | Team, Enterprise | Forwards your login. Claude turns use your organization's plan. On Enterprise, Anthropic bills usage to your organization at its contracted rates and spend limits. | Router key | | `CLAUDE_CODE_OAUTH_TOKEN` from `claude setup-token` | Pro, Max, Team, Enterprise | Same as signing in with that account. Useful for CI and containers. | Router key | | Claude Console account or `ANTHROPIC_API_KEY` | Anthropic API (pay as you go) | Does not forward the key. Claude turns run on Weave's provider account or on your own Anthropic key added in Weave. | Router key, plus router credits or your Anthropic key under **Billing & spend → Your provider keys** | | Amazon Bedrock, Google Cloud Agent Platform (Vertex AI), Microsoft Foundry | Your cloud agreement | Claude Code sends these requests straight to the cloud provider, so they don't pass through the router. | To route them, unset `CLAUDE_CODE_USE_BEDROCK`, `CLAUDE_CODE_USE_VERTEX`, or `CLAUDE_CODE_USE_FOUNDRY` and use one of the rows above. Foundry Claude can be added as a [custom endpoint](https://docs.weaveos.com/router/custom-endpoints.md#microsoft-entra-id) to keep billing on your Azure account. | > [!WARNING] > > If `ANTHROPIC_API_KEY` is set anywhere in your shell or Claude Code settings, Claude Code uses it instead of your claude.ai login, and you lose plan coverage. Run `unset ANTHROPIC_API_KEY`, remove it from your shell profile and Claude Code settings, and restart Claude Code. Run `/status` in Claude Code to see which login is active. ### Claude Enterprise and Team admins * Members sign in with the organization account they were invited with. Nothing is entered in Weave. * If you deploy managed settings with `allowedProviders`, add `"customEndpoint"` and set `ANTHROPIC_BASE_URL` to `https://router.workweave.ai` in the same managed settings file. Otherwise Claude Code refuses to send requests to the router. * `forceLoginMethod` and `forceLoginOrgUUID` keep working. The router key travels in its own header and does not count as a login. * Remote Control needs a direct connection to Anthropic, so it is unavailable while routing is on. See [Remote Control troubleshooting](https://docs.weaveos.com/router/troubleshooting.md#claude-code-remote-control). ## Codex | How Codex is signed in | Plans | What the router does | What you connect | | - | - | - | - | | Sign in with ChatGPT | Plus, Pro | Forwards your login. Native Codex models use your plan's included usage. | Router key | | Sign in with ChatGPT, workspace account | Business, Enterprise, Edu | Forwards your login. Native Codex models use your workspace's included usage or credits, up to the limits your admin set. | Router key. A workspace admin must allow Codex for members. | | Sign in with ChatGPT | Free, Go | OpenAI includes Codex on these plans in the Codex app only, not the Codex CLI the router configures. Treat these engineers as having no plan. | Router key, plus router credits or your OpenAI key | | API key (`codex login --with-api-key`) | OpenAI API (pay as you go) | Does not forward the key. Turns run on Weave's provider account or on your own OpenAI key added in Weave. | Router key, plus router credits or your OpenAI key under **Billing & spend → Your provider keys** | A ChatGPT login covers OpenAI's native Codex models only. The router checks how much included usage is left before it sends a turn to your plan. When that usage runs out, or the router picks a model outside the Codex family, the turn uses router credits or your own provider key if [paid fallback](https://docs.weaveos.com/router/billing.md#paid-fallback) is on, and stops with a limit error if it is off. The hosted router does not spend extra ChatGPT credits you bought on top of a Plus or Pro plan. ### ChatGPT Business, Enterprise, and Edu admins * In workspace settings, turn on **Allow members to use Codex locally** (or **Allow members to use Codex and Work locally**). * If you pin Codex with managed configuration, keep `forced_login_method = "chatgpt"`. Setting it to `"api"` makes every engineer an API-key user, so nothing is covered by your plan. * `forced_chatgpt_workspace_id` keeps working with the router. ## When you need credits or your own key Plan coverage only applies to the plan's own model family: Claude models for a Claude plan, native Codex models for a ChatGPT plan. You need router credits or your own provider key when: * The router picks a model from another family, for example an OpenAI or open-weight model during a Claude Code session. * An engineer reaches their plan's limit and paid fallback is on. * An engineer is signed in with an API key instead of a Claude or ChatGPT account. Provider keys you add in Weave bill your provider account directly, and Weave charges a 5% platform fee against your credit balance, so a small funded balance is still needed. See [billing](https://docs.weaveos.com/router/billing.md). To keep everything on your plan, set [subscription routing](https://docs.weaveos.com/router/models-and-routing.md#subscription-routing) to **Let router choose** or **Strict pass-through until low** (**Use prepaid credits only** ignores plans entirely), restrict [models](https://docs.weaveos.com/router/models-and-routing.md#models) to your plan's family, and turn [paid fallback](https://docs.weaveos.com/router/billing.md#paid-fallback) off. Engineers then get a limit error instead of paid usage when their plan runs out. ## Checking that it worked Run a short prompt, then open [router.workweave.ai](https://router.workweave.ai). Turns served on a plan show `$0` in credit spend while still appearing in usage reports. If plan-covered turns are spending credits, check for `ANTHROPIC_API_KEY` or an API-key Codex login first. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.