What Is SpaceXAI (x.ai)?

SpaceXAI (x.ai) is the company behind Grok, a family of frontier AI models. It offers reasoning, code, voice, image, and video capabilities, and exposes them to developers through a single unified API. If you want to use Grok in an app, the site's developer path (API key, docs, console) is the relevant entry point; if you just want to try the assistant, the consumer apps are the starting point.

What SpaceXAI provides

The site describes Grok as "frontier AI models for everything you build," covering multiple modalities:

• Reasoning and text — answering questions, explaining concepts, and working through problems step by step.
• Code — working inside a project context, reading files, searching a codebase, and proposing edits.
• Voice — a dedicated Voice surface.
• Images — an Imagine surface for image generation.
• Video — listed among the supported modalities.

The homepage shows these in action: a chat answering "Explain quantum entanglement simply" and "Why is the sky blue?", and a coding session that reads src/middleware/auth.ts, greps for "session" across src/, and drafts a JWT migration edit.

One API for every modality

For developers, the core claim is "One API. Every modality." Text, code, voice, images, and video are reachable through a single unified API, with the stated goal of letting you "start building in seconds."

The site lists these scale figures:

The current model named on the homepage is Grok 4.7, described as "our new model," trained on what the site calls the world's largest supercluster.

How to get started

The homepage offers two paths under "Choose how to get started":

For developers

1. Get an API key.
2. Read the docs.
3. Send requests to https://api.x.ai/v1.

For everyone else

• Grok on the web, on iOS, and on Android
• Grok on X
• Grok Bot

There are also product pages for Grok, Business, and Government, plus a Contact Sales option.

Calling the API

The API is OpenAI-compatible: you point an OpenAI client at baseURL: "https://api.x.ai/v1" and pass your XAI_API_KEY. The site shows four equivalent ways to make the same request.

cURL

curl https://api.x.ai/v1/chat/completions \
  -H "Authorization: Bearer $XAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "grok-4.7",
    "messages": [
      { "role": "user", "content": "Explain quantum computing" }
    ]
  }'

Python (xai_sdk)

import os
from xai_sdk import Client
from xai_sdk.chat import user

client = Client(api_key=os.getenv("XAI_API_KEY"))
chat = client.chat.create(model="grok-4.7")
chat.append(user("Explain quantum computing"))
response = chat.sample()
print(response.content)

TypeScript (Vercel AI SDK)

import { xai } from "@ai-sdk/xai";
import { generateText } from "ai";

const { text } = await generateText({
  model: xai.responses("grok-4.7"),
  prompt: "Explain quantum computing",
});
console.log(text);

JavaScript (OpenAI SDK)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.XAI_API_KEY,
  baseURL: "https://api.x.ai/v1",
});

const response = await client.chat.completions.create({
  model: "grok-4.7",
  messages: [{ role: "user", content: "Explain quantum computing" }],
});
console.log(response.choices[0].message.content);

In each case the inputs are your API key, the model name (grok-4.7), and a user message; the expected result is the model's reply in response.content / text / choices[0].message.content.

Where to go next

• Pricing — the site has a dedicated pricing page at x.ai/pricing; check it for current rates rather than assuming any tier is free.
• Documentation — linked from the homepage and the developer section.
• API Console — for managing keys and access.
• News — the homepage carries a "Latest news" section for model and product updates.

If your goal is to build with Grok, start at the API Console for a key, then follow the docs. If your goal is simply to use Grok as an assistant, the web, iOS, Android, and X integrations are the shortest route.