Get started with xAI

Intelligent, fast, and cost-effective models across code, text, voice, image, and video.

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);

Models

Grok Build 0.1

New

grok-build-0.1

Our coding model — trained specifically for agentic coding workflows. Use Grok Build for code.

View model

Context256k tokens

Input$1.00 / 1M tokens

Output$2.00 / 1M tokens

Grok 4.3

grok-4.3

For everything except code, audio, image, and video. The most intelligent and fastest model we’ve built.

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$15.00 / 1M chars

STT (Batch)$0.10 / hour

STT (Streaming)$0.20 / hour

Read docs Try in playground

Imagine API

Turn ideas into reality with image and video generation.

ModesGeneration & editing

SpeedIndustry-leading

Image · 1K / 2K- / image

Video · 480p / 720p / 1080p- / sec

Read docs Try in playground

Jump straight in

Try code, text, voice, image, and video models below

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);

Responses API

Agentic coding with Grok Build on the API—refactor, debug, and build in your own tools.

Agentic coding
IDE & tool integrations
Early access
- / 1M input tokens
- / 1M output tokens

Read docs