Get started with SpaceXAI

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

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

const { text } = await generateText({
  model: xai.responses("grok-4.7"),
  prompt: "Fix this function and explain the bug: function median(a){a.sort();return a[a.length/2]}",
});

console.log(text);

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-4.7",
    input="Fix this function and explain the bug: function median(a){a.sort();return a[a.length/2]}",
)

print(response.output_text)

curl https://api.x.ai/v1/responses \
  -H "Authorization: Bearer $XAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "grok-4.7",
    "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-4.7")
chat.append(user("Fix this function and explain the bug: function median(a){a.sort();return a[a.length/2]}"))

print(chat.sample().content)

Models

Grok 4.7

New

grok-4.7

Our flagship model for code and everything else: agentic tool calling, minimal hallucinations, configurable reasoning.

Context: 500k tokens
Input: $2.00 / 1M tokens
Output: $6.00 / 1M tokens
Reasoning: Configurable

View model Try in playground

Voice API

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

STS: $0.08 / min
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.

Modes: Generation & editing
Speed: Industry-leading
Image · 1K / 2K: Starting at $0.02 / image
Video · 480p / 720p / 1080p: Starting at $0.02 / sec

Read docs Try in playground

Jump straight in

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

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

const { text } = await generateText({
  model: xai.responses("grok-4.7"),
  prompt: "Fix this function and explain the bug: function median(a){a.sort();return a[a.length/2]}",
});

console.log(text);

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-4.7",
    input="Fix this function and explain the bug: function median(a){a.sort();return a[a.length/2]}",
)

print(response.output_text)

curl https://api.x.ai/v1/responses \
  -H "Authorization: Bearer $XAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "grok-4.7",
    "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-4.7")
chat.append(user("Fix this function and explain the bug: function median(a){a.sort();return a[a.length/2]}"))

print(chat.sample().content)

Responses API

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

Agentic coding
IDE & tool integrations
Powers Grok Build
$2.00 / 1M input tokens
$6.00 / 1M output tokens

Read docs

Explore the documentation