xAI Unavailable from Russia Code and terminal
Grok Build
A bet on parallelism: subagents in isolated worktrees, background workflows and a headless mode for CI; included in every paid X Subscription plan.
Price and access
- Free?
- A free plan with limits
- Price
- free with limits / Plus $8 / Premium $30 / Super $100 / Ultra $200
- From Russia
- Grok Build is sold within the X Subscription; the service is unavailable from Russia.
- Models
- Grok 4.7 · Grok 4.7 Fast · Grok 4.6
- Licence
- Apache 2.0
- Our benchmark
- Models in our benchmark →
Official pricing page ↗ Checked 3 November 2026.
Unavailable from Russia. Similar tools that work: Kimi Code CLI, ZCode, DeepSeek Harness.
What changed in price and access
- Grok Build is now part of the X Subscription: Plus $8, Premium $30, Super $100, Ultra $200 a month; limited on the free plan ↗
- Grok 4.7 released: $2 per million input and $6 per million output tokens; a fast variant is twice as fast at twice the price ↗
- Grok Build left beta with version 1.0 under the Apache 2.0 licence
What it gives a manager
- Workflows and /loop: a saved workflow fans a change review out to subagents in the background, and /loop repeats a prompt on a schedule for up to 7 days.
- Policies via MDM: /etc/grok/requirements.toml switches off telemetry, the no-approval mode and unwanted tools, and developers cannot override it.
- Cost control: the status line shows the running session cost; team admins see each seat's weekly pool and set a monthly cap on extra usage.
- One X Subscription covers Grok, Cursor and Grok Build: $30 Premium team seats come with SSO, consolidated billing and usage analytics.
Weak points
- The 460-line installer checks neither signature nor checksum: 164 MB of executable code runs with your user rights (Edward Grishin).
- By default it reads Claude Code and Cursor configs without asking, including files holding keys, and always runs their global hooks.
- Remote settings exist: the server can switch on telemetry and file capture wherever a value is not pinned in requirements.toml.
- Not usable from Russia: download, sign-in and payment run through xAI domains, so a VPN and a foreign card are required.
How to check this agent’s work
- An admin can ban the no-approval mode through requirements.toml – turn that on for the team.
- Give background and /loop tasks a deadline and a definition of done: they can run for up to 7 days.
- Run the outcome of a long task through a second model before passing it on.
Picking an agent takes an evening. After that the question is not the price but whether you can trust what it did.
You’re on the list
We will write when enrolment opens. Meanwhile, here is what the course covers.
The short course programmeWhat the course covers: programme and price
Strengths
- Rust harness under Apache 2.0; a third-party or local model can be set in the config, and the free plan lets you try it.
- Goal mode switches to plan on its own and ends with a skeptic agent: for Arcade it rejected the result, then re-checked only the delta.
- Parallel subagents: Arcade got 57 subagents in about three minutes to review files; the docs say 8 by default in isolated git worktrees.
- Lead Gen Jay's head-to-head via the Claude Code bridge: Grok finished in 12 min 53 s vs about 30 min for Codex, 45 passing tests vs 33.
Alternatives
Kilo Code
ZCode
Kimi Code CLIWho it is for
- Engineering team outside Russia that needs a CI mode
- Manager outside Russia whose team already pays for Cursor or an X subscription
Example from a review: Get a repo to 'clone and run in under five minutes'
Arcade gave Grok Build a goal on a Next.js demo repo: bring it to a state where a first-time contributor can clone it and run the demo in under five minutes. The agent switched itself into plan mode, went through .gitignore, migrations and environment variables, then launched a skeptic agent to verify. The skeptic found that better-sqlite3 fails under Bun, refuted the result, the main agent added prerequisites and a troubleshooting note, and the re-check covered only the delta and passed on attempt two of six. Total: 23 minutes and roughly 150,000 tokens.
Source: Arcade, 'Grok Build Spawned 57 Agents in 3 Minutes. Here's Why I Wasn't Worried.'
Reviews (4)
The video authors’ opinions, not our conclusions.
- Grok 4.6 Is INSANE for $10/Month · Gui Bibeau, 3 September 2026The reviewer calls Grok Build bundled with the $10 X Premium a steal on price and speed, even though his 15-minute 3D scene came out 'childish' and not shareable.
- Grok Build Spawned 57 Agents in 3 Minutes. Here's Why I Wasn't Worried. · Arcade, 9 September 2026Two thumbs up from the reviewer for goal mode with a verifying agent and the transparent UI; his caveat is that git only protects you inside the repo.
- Everything You Need to Know About Grok Bot (Full Grok Build) · Lead Gen Jay, 26 August 2026The reviewer keeps the Grok subscription for the model as a second reviewer inside Claude Code, but Grok Bot did not replace his Hermes agent.
- DeepSeek Harness, Grok Build, OpenWorker, qm. ОБЗОР 4 HARNESS. ЧТО Я НАШЕЛ В КОДЕ, ВАС УДИВИТ! · Эдвард Гришин | AI и автоматизация бизнеса, 1 September 2026In the reviewer's view it is the richest of the four summer harnesses, but only worth installing if you already pay for Grok, and only after disabling foreign-config reading.
Facts with sources
- Left beta on August 7 as version 1.0 under the Apache 2.0 license. Source (in Russian)
- Since October 12, Grok Build is part of the X Subscription: Plus $8, Premium $30, Super $100, Ultra $200 a month; team seats cost the same. Source
- The free plan also includes Grok Build, with limits and without the faster Grok 4.7 Fast. Source
- The default model is Grok 4.7; the Fast variant runs only in Grok Build and Cursor and draws twice as much from your plan. Source
- For companies: managed_config.toml and requirements.toml roll out via MDM, and zero data retention is switched on per team. Source
- Terminal-Bench 4.0: 20.30% of tasks solved on high effort, at a run cost of $3.6K. Source (in Russian)
