---
last_updated: 2026-11-20
source_url: https://opper.ai/xai/grok-build-0-1
title: "Grok Build 0.1 by xAI"
description: "Grok Build 0.1 by xAI is a fast coding model for agentic software engineering with a 256k context window and always-on reasoning."
---

# Grok Build 0.1

By [xAI](https://opper.ai/xai).

Released 29 May 2026, 29 days after [Grok 4.3](https://opper.ai/xai/grok-4-3) · [Announcement](https://x.ai/news/grok-build-0-1) · [All xAI releases](https://opper.ai/model-releases/xai)

Grok Build 0.1 is xAI's coding model released in May 2026, trained to act as an autonomous software engineering agent rather than a passive code-completion helper. It powers xAI's Grok Build CLI and is built for refactoring large codebases, multi-step development workflows, invoking tools, generating structured output, and running in loops until tasks complete.

The model accepts text and image input across a 256k token context window, with function calling, structured outputs, and always-on reasoning that thinks through problems before responding. Unlike general-purpose chat models, it is optimized for interactive coding agents and long-horizon development tasks where an autonomous system must make decisions and drive progress across multiple tool invocations.

Served at fast inference speeds and available in public beta through the xAI API, Grok Build 0.1 is designed to embed agentic coding directly into developer workflows for high-throughput, autonomous software engineering.

## Available routes

Grok Build 0.1 runs on 2 different routes through the Opper gateway. Prices are per 1M tokens. Some routes also sell priority processing: the same model at another price, picked per request with service_tier. [How service tiers work](https://docs.opper.ai/build/gateway/service-tiers). Its routes and prices, live from the catalogue, are public JSON with no API key needed at https://api.opper.ai/v3/models?q=xai%2Fgrok-build-0.1.

| Provider | Model id | Region | Zero data retention | Training | Input | Output | Cache read |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [xAI](https://opper.ai/provider/xai) | `xai-zdr/grok-build-0.1` | Multi-region | Yes | No | $1.00 | $2.00 | $0.20 |
| [xAI](https://opper.ai/provider/xai), Priority | `xai-zdr:priority/grok-build-0.1` | Multi-region | Yes | No | $2.00 | $4.00 | $0.40 |
| [xAI](https://opper.ai/provider/xai) | `xai/grok-build-0.1` | Multi-region | Abuse monitoring | No | $1.00 | $2.00 | $0.20 |
| [xAI](https://opper.ai/provider/xai), Priority | `xai:priority/grok-build-0.1` | Multi-region | Abuse monitoring | No | $2.00 | $4.00 | $0.40 |

## Key info

- Model id: `xai/grok-build-0.1`
- Input: Text, Image
- Output: Text
- Features: Tools, Structured output, PDF input
- Context window: 256K
- Max output: n/a
- Input price: $1.00 per 1M tokens ($0.20 cache read)
- Output price: $2.00 per 1M tokens
- Released: 29 May 2026
- Zero data retention on pay-as-you-go
- No training by default

## Data handling per route

Each route hosting Grok Build 0.1 has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

### xAI — Multi-region

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. GLOBAL; SCCs.

- Zero data retention: Yes. Nothing is logged, held for abuse monitoring or used for training.
- Training: No training on customer data.
- Logging: None
- Abuse monitoring: On by default, keeps nothing
- Caching: Content cached for replay
- Transfer mechanism: SCCs

Verified by Opper on 2026-10-15.

### xAI — Multi-region

Zero data retention with abuse monitoring: prompts and outputs are kept for up to 30 days for abuse monitoring only, and are not used for training. No training on customer data. GLOBAL; SCCs.

- Zero data retention: With abuse monitoring, 30-day window.
- Training: No training on customer data.
- Logging: Abuse monitoring (30-day retention)
- Abuse monitoring: On by default, keeps nothing
- Caching: Content cached for replay
- Transfer mechanism: SCCs

Verified by Opper on 2026-10-15.

## Benchmarks

Independent benchmark scores via [Artificial Analysis](https://artificialanalysis.ai) ([view on AA](https://artificialanalysis.ai/models/grok-build-0-1-06-16)). Indices and domain scores are out of 100, Omniscience runs from −100 to 100, Briefcase is an Elo rating, and the other evaluation scores are the share of tasks solved.

- Global rank: #123 of 520 LLMs on the [LLM leaderboard](https://opper.ai/llm-leaderboard)
- Tier: Efficient
- Output speed: 78 tok/s
- Intelligence Index (previous version): 27.2

### Agentic & knowledge work

- GDPval: 29%

### Science & reasoning

- Humanity's Last Exam: 38%
- GPQA Diamond: 90%
- Long-context reasoning: 75%

### Knowledge

- MMMU-Pro: 77%

## Get started

Call Grok Build 0.1 through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.

Grok Build 0.1 is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

### Set it up with your agent

Paste this into a coding agent like Claude Code, Cursor or Codex and it will wire up Opper for you:

```text
Use curl to download, read and follow: https://skills.opper.ai Call Grok Build 0.1
```

### Or call it directly

OpenAI:

```javascript
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.OPPER_API_KEY,
  baseURL: "https://api.opper.ai/v3/compat",
});

const completion = await client.chat.completions.create({
  model: "xai/grok-build-0.1",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);
```

Anthropic:

```javascript
import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  apiKey: process.env.OPPER_API_KEY,
  baseURL: "https://api.opper.ai/v3/compat",
});

const message = await client.messages.create({
  model: "xai/grok-build-0.1",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Hello" }],
});
console.log(message.content);
```

Gemini:

```javascript
import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({
  apiKey: process.env.OPPER_API_KEY,
  httpOptions: { baseUrl: "https://api.opper.ai/v3/compat" },
});

const response = await ai.models.generateContent({
  model: "xai/grok-build-0.1",
  contents: "Hello",
});
console.log(response.text);
```

cURL:

```bash
curl https://api.opper.ai/v3/compat/chat/completions \
  -H "Authorization: Bearer $OPPER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "xai/grok-build-0.1",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'
```

## Use Grok Build 0.1 in your apps

Pick your tool to see how to run it on Grok Build 0.1 through Opper.

- [Claude Code](https://opper.ai/apps/claude-code/grok-build-0-1)
- [Claude Cowork](https://opper.ai/apps/claude-cowork/grok-build-0-1)
- [Codex](https://opper.ai/apps/codex/grok-build-0-1)
- [DeepSeek Harness](https://opper.ai/apps/deepseek-harness/grok-build-0-1)
- [GitHub Copilot CLI](https://opper.ai/apps/github-copilot-cli/grok-build-0-1)
- [Aider](https://opper.ai/apps/aider/grok-build-0-1)
- [Goose](https://opper.ai/apps/goose/grok-build-0-1)
- [Droid](https://opper.ai/apps/droid/grok-build-0-1)
- [OpenCode](https://opper.ai/apps/opencode/grok-build-0-1)
- [Pi](https://opper.ai/apps/pi/grok-build-0-1)
- [OpenClaw](https://opper.ai/apps/openclaw/grok-build-0-1)
- [Hermes](https://opper.ai/apps/hermes/grok-build-0-1)
- [Copilot for Obsidian](https://opper.ai/apps/obsidian-copilot/grok-build-0-1)
- [OmniRoute](https://opper.ai/apps/omniroute/grok-build-0-1)
- [Cursor](https://opper.ai/apps/cursor/grok-build-0-1)
- [Cline](https://opper.ai/apps/cline/grok-build-0-1)
- [Continue](https://opper.ai/apps/continue/grok-build-0-1)
- [Kilo Code](https://opper.ai/apps/kilo-code/grok-build-0-1)
- [GitHub Copilot](https://opper.ai/apps/github-copilot/grok-build-0-1)
- [Zed](https://opper.ai/apps/zed/grok-build-0-1)
- [JetBrains AI Assistant](https://opper.ai/apps/jetbrains-ai-assistant/grok-build-0-1)
- [Voidleap Code](https://opper.ai/apps/voidleap-code/grok-build-0-1)
- [n8n](https://opper.ai/apps/n8n/grok-build-0-1)
- [LibreChat](https://opper.ai/apps/librechat/grok-build-0-1)
- [Open WebUI](https://opper.ai/apps/open-webui/grok-build-0-1)
- [See all apps](https://opper.ai/apps)

## Other models from xAI

- [Grok 4.7](https://opper.ai/xai/grok-4-7)
- [Grok 4.6](https://opper.ai/xai/grok-4-6)
- [Grok 4.5](https://opper.ai/xai/grok-4-5)
- [Grok 4.3](https://opper.ai/xai/grok-4-3)
- [Grok 4.20 Non-Reasoning](https://opper.ai/xai/grok-4-20-0309-non-reasoning)
- [Grok 4.20 Non-Reasoning](https://opper.ai/xai/grok-4-20-non-reasoning)
