Build with the most
powerful AI models.

Frontier models for reasoning, voice, vision, and more. One unified API, every modality, production-ready in minutes.

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-4.3")
chat.append(user("Explain quantum computing"))

response = chat.sample()
print(response.content)

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-4.3",
  messages: [{ role: "user", content: "Explain quantum computing" }],
});

console.log(response.choices[0].message.content);

curl https://api.x.ai/v1/chat/completions \
  -H "Authorization: Bearer $XAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "grok-4.3",
    "messages": [
      { "role": "user", "content": "Explain quantum computing" }
    ]
  }'

Products

Every modality, one API

ImagineExplore →

VoiceExplore →

Capabilities

Models that fit your needs

Text generation

Powerful text and reasoning models for chat, analysis, and problem-solving.

Code

Intelligent coding models for software engineering, building apps, and orchestrating agents.

Voice API

Build real-time voice agents with speech-to-text, text-to-speech, and conversational AI capabilities.

Search

Tap into the now with real-time search, pulling fresh, relevant data from the web and X instantly.

Image and Video generation

Generate high-quality images and short videos with synchronized audio from text prompts or static images.

File management

Upload documents and let Grok intelligently search and reason over your PDFs, spreadsheets, presentations, and more.

Quickstart

Start building in minutes

Our API is compatible with OpenAI and Anthropic's SDKs. Migrating is as easy as generating an API key and changing a URL.

Start building

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-4.3")
chat.append(user("Explain quantum computing"))

response = chat.sample()
print(response.content)

Models and pricing

grok-4.3

New

Our newest flagship model that leads the industry in non-hallucination rate and agentic tool calling capabilities. Supports both non-reasoning and reasoning modes.

Capabilities

Context window

Text Input

$1.25

Output

$2.50

grok-build-0.1

New

xAI's fast coding model trained specifically for agentic coding, currently in early access.

Capabilities

Context window

256k

Text Input

$1.00

Output

$2.00

Model	Capabilities	Context window	Text Input	Output
grok-4.3 New Our newest flagship model that leads the industry in non-hallucination rate and agentic tool calling capabilities. Supports both non-reasoning and reasoning modes.		1M	$1.25	$2.50
grok-build-0.1 New xAI's fast coding model trained specifically for agentic coding, currently in early access.		256k	$1.00	$2.00

Imagine API

Image and video generation & editing

grok-imagine-image-quality

Text, Image → Image

Media Input: $0.01 / img
1K: $0.05 / img
2K: $0.07 / img

grok-imagine-image

Text, Image → Image

Media Input: $0.002 / img
1K: $0.02 / img
2K: $0.02 / img

grok-imagine-video

Text, Image, Video → Video

Media Input: $0.01 / sec
$0.002 / img
480p: $0.05 / sec
720p: $0.07 / sec

Model	Media Input	Resolution	Output
grok-imagine-image-quality Text, Image → Image	$0.01 / img	1K	$0.05 / img
grok-imagine-image-quality Text, Image → Image	$0.01 / img	2K	$0.07 / img
grok-imagine-image Text, Image → Image	$0.002 / img	1K	$0.02 / img
grok-imagine-image Text, Image → Image	$0.002 / img	2K	$0.02 / img
grok-imagine-video Text, Image, Video → Video	$0.01 / sec $0.002 / img	480p	$0.05 / sec
grok-imagine-video Text, Image, Video → Video	$0.01 / sec $0.002 / img	720p	$0.07 / sec