Quickstart | xAI Docs

Welcome! In this guide, we'll walk you through the basics of using the xAI API, from creating an account to making your first request.

Step 1: Create an xAI account

Step 2: Generate an API key

Create an API key via the API Keys page, then export it or add it as an environment variable.

Bash

export XAI_API_KEY="your_api_key"

Or add it to a .env file in your project directory:

Bash

XAI_API_KEY=your_api_key

Step 3: Install an SDK

Pick your language and install the SDK:

pip install xai-sdk

pip install openai

npm install ai @ai-sdk/xai zod

npm install openai

Step 4: Make your first request

Send a coding prompt to Grok Build (grok-build-0.1) and get a response. The same model powers agentic coding in Grok Build and is available on the API in early access:

curl https://api.x.ai/v1/responses \
  -H "Authorization: Bearer $XAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "grok-build-0.1",
    "input": "Fix this function and explain the bug: function median(a){a.sort();return a[a.length/2]}"
  }'

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-build-0.1")
chat.append(user("Fix this function and explain the bug: function median(a){a.sort();return a[a.length/2]}"))

print(chat.sample().content)

from openai import OpenAI

client = OpenAI(
    api_key="<YOUR_XAI_API_KEY_HERE>",
    base_url="https://api.x.ai/v1",
)

response = client.responses.create(
    model="grok-build-0.1",
    input="Fix this function and explain the bug: function median(a){a.sort();return a[a.length/2]}",
)

print(response.output_text)

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

const { text } = await generateText({
  model: xai.responses('grok-build-0.1'),
  prompt: 'Fix this function and explain the bug: function median(a){a.sort();return a[a.length/2]}',
});

console.log(text);

import OpenAI from 'openai';

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

const response = await client.responses.create({
  model: 'grok-build-0.1',
  input: 'Fix this function and explain the bug: function median(a){a.sort();return a[a.length/2]}',
});

console.log(response.output_text);

For multi-turn chat, reasoning, and structured outputs, see the Text Generation Guide. For agentic coding workflows, see the Grok Build overview.

Step 5: Generate an image

Use the Imagine API to generate images from text prompts:

import os
import xai_sdk

client = xai_sdk.Client(api_key=os.getenv("XAI_API_KEY"))

response = client.image.sample(
    prompt="A futuristic city skyline at sunset",
    model="grok-imagine-image-quality",
)

print(response.url)

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("XAI_API_KEY"),
    base_url="https://api.x.ai/v1",
)

response = client.images.generate(
    model="grok-imagine-image-quality",
    prompt="A futuristic city skyline at sunset",
)

print(response.data[0].url)

import { xai } from '@ai-sdk/xai';
import { generateImage } from 'ai';

const { image } = await generateImage({
  model: xai.image('grok-imagine-image-quality'),
  prompt: 'A futuristic city skyline at sunset',
});

console.log(image.base64);

import OpenAI from 'openai';

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

const response = await client.images.generate({
  model: 'grok-imagine-image-quality',
  prompt: 'A futuristic city skyline at sunset',
});

console.log(response.data[0].url);

curl -X POST https://api.x.ai/v1/images/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $XAI_API_KEY" \
  -d '{
    "model": "grok-imagine-image-quality",
    "prompt": "A futuristic city skyline at sunset"
  }'