Grok Build 0.1
Grok Build 0.1 by xAI is an agentic coding model with 256k context, MCP support, plan mode, parallel subagents, and native AGENTS.md compatibility.
Model Overview
Capabilities, design details, and architectural traits
Grok Build 0.1 – Agentic Coding Model for Multi-Step Software Engineering
Grok Build 0.1 (grok-build-0.1) is xAI's first model purpose-built for agentic coding tasks. It is specifically trained for multi-step software engineering workflows web development, debugging, and MCP support rather than general-purpose conversation. It powers the Grok Build CLI, a terminal-native coding agent whose CLI is written in Rust.
CLI Architecture
The Grok Build CLI is written in Rust and introduces a plugin and skills marketplace, allowing community-contributed extensions to be installed within the agent session. Subagents can run in parallel across separate git worktrees, enabling concurrent execution on independent parts of a codebase.
Ecosystem Compatibility
Officially documented to work out of the box with conventions from AGENTS.md — the same project-instruction format used by Claude Code — meaning existing Claude Code project configurations, MCP servers, and sub-agent designs require no modification to run under Grok Build.
Integrations
Officially available in Grok Build CLI, Cursor, Hermes Agent, OpenClaw, Kilo Code, and OpenCode.
Benchmark Performance
Independent evaluations · Artificial Analysis
Accuracy & Capability Details
Independent evaluation data provided by Artificial Analysis. To view the latest benchmarks and full details, visit their official site.
Compare Models Side-by-Side
Evaluate specifications, pricing, and independent benchmark indices
| Model Details | xAIHost Grok Build 0.1 | ||
|---|---|---|---|
| General Info | |||
| Provider | xAI | Anthropic | Anthropic |
| Release Date | May 20, 2026 | June 9, 2026 | May 28, 2026 |
| Knowledge Cutoff | — | — | — |
| Context & Limits | |||
| Context Window | 256K | 1M Best Context Window | 1M Best Context Window |
| Pricing (per 1M tokens) | |||
| Input Pricing | $1 Best Input Pricing | $10 | $5 |
| Output Pricing | $2 Best Output Pricing | $50 | $25 |
| Modalities | |||
| Inputs | textimage | textimagefile | textimagefile |
| Outputs | text | text | text |
| Benchmarks (0-100) | |||
| Intelligence Index | 39.8 | 59.9 Best Intelligence Index | 55.7 |
| Coding Index | 51.5 | 76.5 Best Coding Index | 74.3 |
| Agentic Index | 28.0 | 52.8 Best Agentic Index | 47.2 |
GPQA Benchmark
Graduate-level reasoning and expert Q&A evaluation.
Humanity's Last Exam
Extremely difficult logical reasoning and knowledge.
Long Context Reasoning
Logical reasoning over long context windows.
Benchmark scores are independent evaluations sourced from Artificial Analysis. Intelligence, Coding, and Agentic indices reflect composite performance ratings (0–100).