xAI

Overview

xAI builds Grok, a family of large language models with strong reasoning capabilities. Floopy proxies requests to xAI’s OpenAI-compatible API, supporting both reasoning and non-reasoning modes.

Supported Models

Model	Context Window	Notes
`grok-4.20-reasoning`	131K	Flagship reasoning model
`grok-4.20-non-reasoning`	131K	Flagship model, standard mode
`grok-4.20-multi-agent`	131K	Optimized for multi-agent workflows
`grok-4-1-fast-reasoning`	131K	Cost-efficient reasoning model
`grok-4-1-fast-non-reasoning`	131K	Cost-efficient standard model

Setup

Go to Settings > Providers in the dashboard.
Click Add provider and select xAI.
Paste your xAI API key and click Save.

Usage

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.floopy.ai/v1",
  apiKey: process.env.FLOOPY_API_KEY,
});

const response = await client.chat.completions.create({
  model: "grok-4.20-reasoning",
  messages: [{ role: "user", content: "Explain quantum computing." }],
});

from openai import OpenAI

client = OpenAI(base_url="https://api.floopy.ai/v1", api_key=os.environ["FLOOPY_API_KEY"])

response = client.chat.completions.create(
    model="grok-4.20-reasoning",
    messages=[{"role": "user", "content": "Explain quantum computing."}],
)

curl https://api.floopy.ai/v1/chat/completions \
  -H "Authorization: Bearer $FLOOPY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "grok-4.20-reasoning", "messages": [{"role": "user", "content": "Explain quantum computing."}]}'

Provider-Specific Features

Reasoning modes — Grok 4.20 supports both reasoning and non-reasoning modes. Use the -reasoning suffix for complex tasks requiring chain-of-thought, or -non-reasoning for faster general-purpose responses.
Cached input discount — xAI offers 90% discount on cached input tokens, reducing cost for repeated contexts.
Multi-agent support — The grok-4.20-multi-agent variant is optimized for orchestrating multi-agent workflows.