xAI's Grok Build 0.1 Lands in Warp's Terminal for 1 Million Developers

xAI's Grok is now natively available inside Warp, the AI-powered terminal used by nearly one million developers. SuperGrok subscribers can connect their xAI account directly to Warp and run grok-build-0.1 -- xAI's dedicated coding model -- without touching their Warp credit balance. It's a clean integration that makes an existing subscription work harder.

What just landed

SuperGrok subscribers can connect their xAI accounts to Warp and gain access to the grok-build-0.1 model natively inside the terminal environment. No plugins, no workarounds, no credit deductions from Warp's own system.

Warp operates on a credit-based system for AI model usage, so getting Grok access without tapping into that balance is a genuine perk for paying xAI customers. Think of it as a Bring Your Own Key (BYOK) flow -- except instead of pasting an API key, you log in with OAuth. Connecting a subscription works like BYOK, except you sign in to your xAI account instead of pasting an API key.

Grok joins a roster of models already available inside Warp, including Claude Code from Anthropic, OpenAI's Codex, and Google's Gemini CLI. The pattern is clear: Warp is becoming the neutral terminal layer where you bring whatever model you're already paying for.

What is Grok Build 0.1, exactly?

Grok Build 0.1 is xAI's fast coding model trained specifically for agentic software engineering workflows. The key word is agentic -- meaning the model is designed to take a goal, break it into steps, run shell commands, edit files, check for errors, and loop until the task is done, rather than just responding to a single prompt.

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 on Grok Build 0.1. There is no non-reasoning mode and reasoning effort is not configurable, so every response includes structured analysis before the final output.

A few specs worth knowing:

• 256,000 token context window -- large enough to hold an entire mid-sized codebase in memory.
• Multimodal input: supports text and image inputs, so you can feed it UI mockups, diagrams, or error screenshots.
• No output token cap -- there is no fixed output token cap, which matters for long autonomous coding sessions that generate large amounts of code.
• SWE-bench Verified score of 70.8% -- the standard benchmark for agentic coding performance on real GitHub issues.
• Up to 8 parallel agents in a plan-search-build pipeline.

How to connect it in 3 steps

The setup is genuinely minimal. 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, then select grok-build-0.1 from the model picker.

Your OAuth token is stored only in your local OS keychain, never on Warp's servers, and Warp refreshes it automatically in the background. One important caveat: this does not work with Warp's Cloud Agents -- since tokens are stored locally, cloud-hosted agent runs will still consume Warp credits.

What it's good for -- and where it falls short

Grok Build 0.1 is heavily optimized for interactive coding agents, tool use, and multi-step development tasks. It is built to reason through a problem, write code, use your terminal, check for errors, and fix its own mistakes in a continuous loop. Early users report it's particularly fast at greenfield builds -- it's good at creating landing pages and product pages in a particular style, from coding to design, and built a professional-level landing page in 40 seconds.

The honest picture on weaknesses: xAI has positioned Grok Build as best suited for parallel-heavy migrations and high-volume API workloads, while Claude Code remains the stronger option for engineering depth and Cursor for IDE-bound teams. Price and parallelism may be enough to earn Grok Build a place in multi-agent orchestration stacks -- just not necessarily the top spot.

The pricing math

The $99/month SuperGrok subscription includes unlimited Grok Build usage plus access to all xAI products (Grok chat, image generation, etc.). For comparison: Claude Code requires a $100/month Max plan for heavy use, and Codex CLI uses OpenAI API credits. If you're not a SuperGrok subscriber and want raw API access, pricing is $1 per million input tokens and $2 per million output tokens, with cached prompts at $0.20 per million input tokens.

The bigger picture

xAI has been expanding Grok's footprint beyond its original home in the X platform's chat interface, pushing it into environments where it can deliver tangible utility rather than just conversation. The Warp integration is the latest in a rapid expansion that has also included opening grok-build-0.1 via public API, integrations with OpenCode, Cursor, and Kilo Code, and a forthcoming Arena Mode where multiple agents compete on the same task and you pick the winner.

Grok Build is xAI's first dedicated coding agent for the terminal, bringing multi-agent architecture, a Skills/Plugins marketplace, and native CLAUDE.md support to a CLI that feels immediately familiar if you've used Claude Code or Codex CLI. The Warp integration is a distribution play as much as a technical one -- xAI gets access to nearly a million terminal users, and Warp gets another flagship model to offer without building anything new. Both sides win, and the developer pays once.