Grok Build 0.1

Language modelCard summarized

SpaceXAI's intelligent coding model for agentic software, engineering, and workflow tasks.

● Re-checked 12 Oct 2026 · 44 facts · 0 correctionsSource: Grok Build 0.1 on API (launch post; no system card published)

Use it via API

$516 /month

$10.32 per 1K requests

RAG over docs: 12K in · 600 out · 50K requests/mo · 30% cached · change

Code example Compare

Where to call it

xAI APIgrok-build-0.1

Supports

Image input
Structured outputs
Tool calling
Prompt caching

Full feature support

Good for

Agentic coding: web development, debugging, MCP support
Powers the Grok Build coding agent
General-purpose agentic and tool-calling tasks where speed and cost matter

Overview

xAI · 01Build

Grok Build 0.1

SpaceXAI's intelligent coding model for agentic software, engineering, and workflow tasks.

Cost: $1.00 in
Context: 256K

Input / output: $1.00 / $2.00
Max output: —
Knows up to: —
Released: 29 May 2026

xAI's coding model, trained specifically for agentic coding tasks including web development, debugging and MCP support. It is the same model that powers the Grok Build coding agent and launched on the xAI API in public beta. xAI also offers it as a fast, low-cost option for general agentic and tool-calling work. launch post; release notes

grok-build-0.1

Input / output per 1M: $1.00 / $2.00
Context window: 256K
Max output: —
Knows up to: —
Reasoning: Reasoning (effort levels not documented)
Weights: Closed

About this card. A model card is the maker's own account of a model: what it's for, how it was trained and tested, and where it falls short. This page condenses xAI (SpaceXAI)'s Grok Build 0.1 on API (launch post; no system card published). Every claim carries its source page.