Agents > Inference & providers
SuperGrok subscription
# SuperGrok subscription Warp lets you connect your **SuperGrok subscription** to use Grok models in Warp's agents through your xAI account. If you already subscribe to Grok, you can run Grok models in Warp without consuming your Warp [credits](/support-and-community/plans-and-billing/credits/). Connecting a subscription works like [Bring Your Own API Key (BYOK)](/agent-platform/inference/bring-your-own-api-key/), except you sign in to your xAI account instead of pasting an API key. There is no xAI API key field in Warp today — the subscription is the way to bring your own Grok access. :::note Like BYOK, connecting a SuperGrok subscription is available on Free and all eligible paid plans for individual users and organizations with 10 or fewer employees, subject to Warp's [Terms of Service](https://www.warp.dev/legal/terms-of-service). See [Warp pricing](https://www.warp.dev/pricing) for current availability. ::: ## How it works When you connect your subscription, Warp opens your browser to xAI's consent screen and completes a standard OAuth login. Warp receives OAuth tokens for your xAI account and stores them **only on your device** (in your OS keychain or equivalent secure storage), never on Warp's servers. Warp refreshes the tokens automatically in the background, so you typically only need to connect once. When you send a prompt with a Grok model selected and a subscription connected: 1. Your local Warp client sends the access token to Warp's backend along with your prompt. 2. Warp's agent harness assembles the full request and uses your token in-flight to call xAI, authenticating as your xAI account instead of Warp's. 3. xAI's response streams back through Warp's backend to your client. Your token passes through Warp's servers on each request but is used only in-flight to call xAI, then discarded — the same model as [BYOK](/agent-platform/inference/bring-your-own-api-key/#how-byok-works). Once connected, supported Grok models show a **key icon** in the model picker, indicating requests will route through your xAI account. Usage and rate limits for these requests are governed by your SuperGrok subscription with xAI. ## Connecting your SuperGrok subscription 1. In the Warp app, open **Settings** and search for `SuperGrok` to jump to the **Connect SuperGrok subscription** row in your AI settings. 2. Click **Connect**. Warp opens your browser to xAI's consent screen and shows a toast with a **Copy URL** fallback in case the browser doesn't open. 3. Approve the connection in your browser. The page confirms with "Grok connected," and back in Warp the row shows a "Connected on..." timestamp. 4. Select a Grok model with the key icon from the model picker in your prompt input. Connecting a subscription doesn't change your selected model, so this last step is what actually routes your requests through your subscription. See [Model choice](/agent-platform/inference/model-choice/) for the list of available models. ## Usage and billing behavior When a Grok model with the key icon is selected: * Warp **does not consume** any of your [credits](/support-and-community/plans-and-billing/credits/) for the request. * Inference runs through your xAI account, within your SuperGrok subscription's usage limits. * If a request fails because your subscription hits a limit, Warp does not retry with Warp credits unless you enable **Warp credit fallback** in the same settings section. See [failover and fallback behavior](/agent-platform/inference/bring-your-own-api-key/#failover-and-fallback-behavior). ### Auto models Warp's **Auto** models always use Warp's own inference and **always consume Warp credits**, even with a SuperGrok subscription connected. Auto never routes requests through your subscription. To use your subscription, select a specific Grok model from the model picker. :::caution A connected SuperGrok subscription does not apply to [Cloud Agents](/agent-platform/cloud-agents/overview/). Because tokens are stored locally on your device, they are not available to cloud-hosted agent runs, which always consume [Warp credits](/support-and-community/plans-and-billing/credits/). ::: ### Zero data retention (ZDR) Warp has Zero Data Retention agreements with its contracted LLM providers, including xAI, for Warp-managed inference. When you connect your own subscription, data retention on xAI's side is governed by your own xAI account and its terms — Warp cannot enforce ZDR for requests sent through your subscription. Warp itself never stores your tokens on its servers. ## Disconnecting To disconnect, open **Settings**, search for `SuperGrok`, and click **Disconnect**. Warp removes the tokens from your device's secure storage, and Grok models go back to running on Warp credits. ## Troubleshooting ### "Couldn't start Grok login" Warp listens on a fixed local port for the browser to complete the connection. This error means the port is busy: usually another connection attempt is still in progress, or another app that uses the same xAI login flow (like Grok CLI) is running. Close the other app or wait for the other attempt to finish, then click **Connect** again. ### The browser never opened Click **Copy URL** on the toast that appears after clicking **Connect**, then paste the URL into your browser manually. ### "Couldn't connect SuperGrok: timed out waiting for the Grok authorization callback" Warp waits 5 minutes for you to approve the connection in your browser. Click **Connect** and approve the consent screen within that window. ## Related resources * [Model choice](/agent-platform/inference/model-choice/) — Full list of supported models and `model_id` values. * [Bring Your Own API Key](/agent-platform/inference/bring-your-own-api-key/) — Use your own Anthropic, OpenAI, or Google API keys. * [Custom inference endpoint](/agent-platform/inference/custom-inference-endpoint/) — Route Warp through any OpenAI-compatible endpoint. * [Credits](/support-and-community/plans-and-billing/credits/) — How Warp credits work and when they're consumed.Connect your SuperGrok subscription to Warp and use Grok models through your xAI account instead of Warp credits.
Warp lets you connect your SuperGrok subscription to use Grok models in Warp’s agents through your xAI account. If you already subscribe to Grok, you can run Grok models in Warp without consuming your Warp credits.
Connecting a subscription works like Bring Your Own API Key (BYOK), except you sign in to your xAI account instead of pasting an API key. There is no xAI API key field in Warp today — the subscription is the way to bring your own Grok access.
How it works
Section titled “How it works”When you connect your subscription, Warp opens your browser to xAI’s consent screen and completes a standard OAuth login. Warp receives OAuth tokens for your xAI account and stores them only on your device (in your OS keychain or equivalent secure storage), never on Warp’s servers. Warp refreshes the tokens automatically in the background, so you typically only need to connect once.
When you send a prompt with a Grok model selected and a subscription connected:
- Your local Warp client sends the access token to Warp’s backend along with your prompt.
- Warp’s agent harness assembles the full request and uses your token in-flight to call xAI, authenticating as your xAI account instead of Warp’s.
- xAI’s response streams back through Warp’s backend to your client.
Your token passes through Warp’s servers on each request but is used only in-flight to call xAI, then discarded — the same model as BYOK.
Once connected, supported Grok models show a key icon in the model picker, indicating requests will route through your xAI account. Usage and rate limits for these requests are governed by your SuperGrok subscription with xAI.
Connecting your SuperGrok subscription
Section titled “Connecting your SuperGrok subscription”- In the Warp app, open Settings and search for
SuperGrokto jump to the Connect SuperGrok subscription row in your AI settings. - Click Connect. Warp opens your browser to xAI’s consent screen and shows a toast with a Copy URL fallback in case the browser doesn’t open.
- Approve the connection in your browser. The page confirms with “Grok connected,” and back in Warp the row shows a “Connected on…” timestamp.
- Select a Grok model with the key icon from the model picker in your prompt input. Connecting a subscription doesn’t change your selected model, so this last step is what actually routes your requests through your subscription. See Model choice for the list of available models.
Usage and billing behavior
Section titled “Usage and billing behavior”When a Grok model with the key icon is selected:
- Warp does not consume any of your credits for the request.
- Inference runs through your xAI account, within your SuperGrok subscription’s usage limits.
- If a request fails because your subscription hits a limit, Warp does not retry with Warp credits unless you enable Warp credit fallback in the same settings section. See failover and fallback behavior.
Auto models
Section titled “Auto models”Warp’s Auto models always use Warp’s own inference and always consume Warp credits, even with a SuperGrok subscription connected. Auto never routes requests through your subscription. To use your subscription, select a specific Grok model from the model picker.
Zero data retention (ZDR)
Section titled “Zero data retention (ZDR)”Warp has Zero Data Retention agreements with its contracted LLM providers, including xAI, for Warp-managed inference. When you connect your own subscription, data retention on xAI’s side is governed by your own xAI account and its terms — Warp cannot enforce ZDR for requests sent through your subscription. Warp itself never stores your tokens on its servers.
Disconnecting
Section titled “Disconnecting”To disconnect, open Settings, search for SuperGrok, and click Disconnect. Warp removes the tokens from your device’s secure storage, and Grok models go back to running on Warp credits.
Troubleshooting
Section titled “Troubleshooting””Couldn’t start Grok login”
Section titled “”Couldn’t start Grok login””Warp listens on a fixed local port for the browser to complete the connection. This error means the port is busy: usually another connection attempt is still in progress, or another app that uses the same xAI login flow (like Grok CLI) is running. Close the other app or wait for the other attempt to finish, then click Connect again.
The browser never opened
Section titled “The browser never opened”Click Copy URL on the toast that appears after clicking Connect, then paste the URL into your browser manually.
”Couldn’t connect SuperGrok: timed out waiting for the Grok authorization callback”
Section titled “”Couldn’t connect SuperGrok: timed out waiting for the Grok authorization callback””Warp waits 5 minutes for you to approve the connection in your browser. Click Connect and approve the consent screen within that window.
Related resources
Section titled “Related resources”- Model choice — Full list of supported models and
model_idvalues. - Bring Your Own API Key — Use your own Anthropic, OpenAI, or Google API keys.
- Custom inference endpoint — Route Warp through any OpenAI-compatible endpoint.
- Credits — How Warp credits work and when they’re consumed.