Model retirement · May 15, 2026.

Several older models will be retired on May 15 at 12:00pm PT, including grok-4-1-fast, grok-4-fast, grok-4, grok-code-fast-1, and grok-imagine-image-pro. See the migration guide for recommended replacements.

Get started with xAI

Build with intelligent, fast, and cost effective models across text, voice, images, and video.

Models

We offer a range of models supporting multiple use cases and modalities.

Grok 4.3

New

Strong agentic tool calling with minimal hallucinations. Supports non-reasoning mode.

Context- tokens
Input- / 1M tokens
Output- / 1M tokens
ReasoningConfigurable
View model

Voice API

Real-time conversations, speech-to-text, and text-to-speech.

Agent$3.00 / hour
TTS$4.20 / 1M characters
STT
LatencySub-second

Imagine API

Turn ideas into reality with image and video generation.

ModesGeneration & editing
Image- / image
Video- / second
Resolution1K & 2K

Jump straight in

Try text, voice, image, and video models below

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

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

chat = client.chat.create(model="grok-4.3")
chat.append(system("You are Grok, a chatbot inspired by the Hitchhiker's Guide to the Galaxy."))
chat.append(user("What is the meaning of life, the universe, and everything?"))
response = chat.sample()

print(response)

Responses API

Generate text, have conversations, use tools, and build AI-powered applications.

Generate text
Multi-turn chat
Function calling
- / 1M input tokens
- / 1M output tokens