Warp Lets SuperGrok Subscribers Run xAI's Grok Build 0.1 Free

If you're already paying for a SuperGrok subscription, you can now put it to work inside Warp , the AI-native terminal that has been positioning itself as the central hub for agentic development workflows. Warp just added native SuperGrok subscription support to its agent, letting you route requests through your xAI account instead of consuming Warp's own credit system. The headline model unlocked by this: Grok Build 0.1, xAI's purpose-built coding agent.

What Grok Build 0.1 Actually Is

Released in public beta, Grok Build 0.1 is a coding model with a specific purpose: to function as an autonomous software engineering agent. It's trained from the ground up to handle end-to-end development tasks , planning what needs to be done, executing work step by step, debugging failures, and integrating with the tools developers already rely on. This is not a general-purpose model with a coding prompt bolted on.

Where general-purpose Grok models handle coding alongside other tasks, Grok Build 0.1 is trained to act as an autonomous engineering agent: refactoring code, invoking tools, producing structured outputs, and iterating through multi-step tasks until completion. Reasoning is always active , there is no non-reasoning mode, and reasoning effort is not configurable, so every response includes structured analysis before the final output.

The key specs worth knowing:

• 256K context window with no text output limit, making it well suited for long-horizon coding and automation workflows.
• Served at 100+ tokens per second, priced at $1/M input tokens and $2/M output tokens.
• Accepts text and image input , meaning it can read diagrams, UI mockups, and error screenshots alongside source code. It supports tool calling and structured outputs, fitting agent loops that orchestrate file edits, test runs, and external APIs.
• Up to 8 parallel subagents, each isolated in its own Git worktree.

On SWE-Bench Verified , the most-cited agentic coding benchmark , the model scored 70.8%, putting it roughly 15-18 points below the current frontier leaders. Respectable for a v1 release, but behind Claude Opus 4.7 and GPT-5.5. The real pitch is speed and cost, not raw benchmark dominance.

How the Warp Integration Works

Connecting your SuperGrok subscription lets you 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. Think of it as Bring Your Own Key, but with an OAuth flow instead of a pasted API string.

Connecting a subscription works like 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.

Setup takes four steps according to the official Warp docs:

1. Open Settings in Warp and search for SuperGrok.
2. Click Connect , Warp opens your browser to xAI's OAuth consent screen.
3. Approve the connection. The page confirms with "Grok connected."
4. Select a Grok model with the key icon from the model picker in your prompt input.

Your token passes through Warp's servers on each request but is used only in-flight to call xAI, then discarded. Once connected, supported Grok models show a key icon in the model picker, indicating requests will route through your xAI account.

The Credit Math

Grok Build is bundled into SuperGrok and X Premium Plus plans. Deeper agentic features sit on SuperGrok Heavy at $300/mo, though xAI launched a SuperHeavy tier at $299/mo with a $99/mo introductory promo for the first six months. If you're already on one of those plans, the Warp integration costs you nothing extra.

If you already pay for X Premium Plus or SuperGrok, the bundle math is hard to beat , you get the coding agent, Skills, and Connectors at the subscription you're already paying. For those who want pure API access without a subscription, the API is priced at $1 per million input tokens, $2 per million output tokens, with $0.20/M for cached input.

Where It Fits in the Agentic Terminal Race

The market for terminal-native AI coding agents is now four players deep: Claude Code (Anthropic), Codex CLI (OpenAI), Cursor Composer, and now Grok Build. Warp's move here is strategic , rather than betting on a single model provider, it's building a model-agnostic terminal that lets users plug in whatever subscription they already hold.

Warp already lets you bring your favorite coding agents into the terminal , Claude Code, Codex, Gemini CLI, and more , with vertical tabs, notifications, and interactive code review built in. The SuperGrok integration extends that same philosophy to xAI's ecosystem.

One important caveat: usage and rate limits for these requests are governed by your SuperGrok subscription with xAI, not Warp. And the integration only applies to local agents , cloud-hosted Warp agent runs still consume Warp credits, since OAuth tokens are stored locally on your device and aren't available to cloud-side execution.

For teams already in the xAI ecosystem, this is a clean zero-friction unlock. For everyone else, it's a useful signal that Warp is building the terminal layer that sits above the model wars , letting you swap providers as the benchmark leaderboard shifts.