Does Grok Build work with Standard Compute?

Yes. Grok Build supports a custom OpenAI-compatible base URL, so it works with Standard Compute. Set the base URL to https://api.stdcmpt.com/v1, paste your API key, and set the model to "standardcompute".

What base URL do I use for Grok Build?

Use https://api.stdcmpt.com/v1 as the OpenAI-compatible base URL in Grok Build, with your Standard Compute API key and the model "standardcompute".

Do I need to change my code or model names?

No code changes. The model "standardcompute" routes each request to a frontier or an efficient model, so you don't pick or update model names; an exact model ID from the Models page pins one model instead.

← All integrations

OpenAI-compatible · Custom base URL · Terminal coding agent

Use Standard Compute with Grok Build

xAI's open-source coding agent with a fullscreen terminal UI, headless mode and ACP support, which accepts custom OpenAI-compatible and Anthropic Messages models. Paste three settings into Grok Build: the base URL, your Standard Compute API key and the model.

Grok Build resolves credentials per model: model.api_key, then model.env_key, then your xAI session, then XAI_API_KEY. A custom model with its own env_key works while you stay signed in to xAI for Grok models.

Connect Grok Build

Eligible new accounts can try $0.25 of compute, with no card. See trial terms →

Your connection settings

Copy these values, then put them where Grok Build expects them (steps below).

Base URL

https://api.stdcmpt.com/v1

API Key

Your Standard Compute key

Model

standardcompute

Where to set them in Grok Build

Open ~/.grok/config.toml (on Windows %USERPROFILE%\.grok\config.toml) and add a [model.standardcompute] table.
Set model = "standardcompute", base_url = "https://api.stdcmpt.com/v1", env_key = "STANDARDCOMPUTE_API_KEY" and api_backend = "chat_completions". Add default = "standardcompute" under [models] to make it the default.
Export STANDARDCOMPUTE_API_KEY, run grok inspect to confirm the config loaded, then start grok or switch with /model standardcompute.

Grok Build docs ↗

What changes in Grok Build

Billing: Grok Build requests draw on one monthly compute budget, with plans from $19 a month. There is no per-token bill. When the budget is used, requests stop until renewal or an upgrade, unless you turn on pay as you go.
Models: The model standardcompute picks a frontier or an efficient model for each request. An exact model ID from the Models page pins one model instead.
Good to know: Grok Build is free and open source (Apache 2.0). xAI's own models run on your xAI login or an XAI_API_KEY; custom models bill through their provider. api_backend also accepts responses or messages.