Welcome to Floopy Docs
Floopy is an AI Agent Optimization Platform. It includes an AI gateway that sits between your application and LLM providers, and layers feedback-driven routing on top — combining end-user session NPS, LLM-as-judge scoring, admin ratings, and public benchmarks to continuously route each request to the most cost-effective model that keeps quality. Caching, security, and observability come in the same box — all without changing your application code beyond a single line.
Quick Start
Section titled “Quick Start”Point your OpenAI SDK at Floopy and you’re live:
app.ts
// pnpm add floopy-sdk
import { Floopy } from "floopy-sdk";
const floopy = new Floopy({
apiKey: process.env.FLOOPY_API_KEY!,
});
const response = await floopy.chat.completions.create({
model: "gpt-4o",
messages: [{ role: "user", content: "Hello from Floopy!" }],
});
console.log(response.choices[0].message.content);# pip install floopy-sdk
from floopy import Floopy
floopy = Floopy(
api_key=os.environ["FLOOPY_API_KEY"],
)
response = floopy.chat.completions.create(
model="gpt-4o",
messages=[{"role": "user", "content": "Hello from Floopy!"}],
)
print(response.choices[0].message.content)// go get github.com/floopy-ai/floopy-go
package main
import (
"context"
"fmt"
"github.com/floopy-ai/floopy-go"
)
func main() {
client := floopy.NewClient(floopy.WithEnv())
res, _ := client.Chat.Completions.Create(context.Background(), &floopy.ChatRequest{
Model: "gpt-4o",
Messages: []floopy.Message{{Role: "user", Content: "Hello from Floopy!"}},
})
fmt.Println(res.Choices[0].Message.Content)
}// cargo add floopy
use floopy::Floopy;
#[tokio::main]
async fn main() -> anyhow::Result<()> {
let floopy = Floopy::from_env()?;
let response = floopy
.chat()
.completions()
.create(floopy::ChatRequest {
model: "gpt-4o".into(),
messages: vec![floopy::Message::user("Hello from Floopy!")],
..Default::default()
})
.await?;
println!("{}", response.choices[0].message.content);
Ok(())
}// npm i openai
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: "gpt-4o",
messages: [{ role: "user", content: "Hello from Floopy!" }],
});
console.log(response.choices[0].message.content);# pip install openai
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="gpt-4o",
messages=[{"role": "user", "content": "Hello from Floopy!"}],
)
print(response.choices[0].message.content)curl https://api.floopy.ai/v1/chat/completions \
-H "Authorization: Bearer $FLOOPY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-4o",
"messages": [{"role": "user", "content": "Hello from Floopy!"}]
}'No SDK to install. Works with any language that supports the OpenAI API format.
Guides
Section titled “Guides”Getting Started Set up Floopy in under 5 minutes.
Integration Connect your app with Node.js, Python, or curl.
API Keys Create and manage gateway API keys.
Providers Add your LLM provider API keys.
Routing Configure fallback, round-robin, weighted, and latency-based routing.
Headers Reference Complete list of all request and response headers.
API Reference Endpoint schema, request/response formats, error codes.
Security How Floopy protects your data, keys, and LLM traffic.
Benchmarks Real-world performance numbers across 7 scenarios.
Troubleshooting Common errors, debugging tips, and FAQ.
Features
Section titled “Features”Caching Three tiers of intelligent caching to reduce cost and latency.
LLM Firewall Block prompt injection and unsafe content.
Smart Selector Multi-armed bandit optimization for automatic model selection.
Streaming Real-time SSE streaming through the gateway.
Fallbacks Automatic provider failover for high availability.
Observability Logs, sessions, properties, and distributed tracing.
Rate Limiting Per-org, per-key, and per-request rate limits.
Prompt Management Versioned prompts with variables and feedback.
A/B Testing Split traffic between model and prompt variants.
Experiments Evaluate LLM quality with datasets and scoring.
Datasets Test datasets for experiments and A/B tests.
Playground Test prompts directly in the dashboard.
Billing
Section titled “Billing”Plans Free, Starter, Pro, and Enterprise tiers.
Credits How credits work, purchasing, and overage billing.
Team Budgets Set spending limits per team.
Supported Providers
Section titled “Supported Providers”Floopy translates requests to the correct format automatically. You just change the model name:
| Provider | Example Models |
|---|---|
| OpenAI | gpt-4o, gpt-4o-mini, o1, o3-mini |
| Anthropic | claude-sonnet-4-20250514, claude-3-5-haiku-20241022 |
| Google Gemini | gemini-2.5-pro, gemini-2.0-flash |
| Groq | llama-3.3-70b-versatile, mixtral-8x7b-32768 |
| Mistral | mistral-large-latest, mistral-small-latest |
| DeepSeek | deepseek-chat, deepseek-reasoner |
Need Help?
Section titled “Need Help?”- Dashboard — manage your organization, keys, and settings
- Status Page — check gateway health
- GitHub — report issues and request features