Getting Started

1. Create Your Account

Sign up at app.floopy.ai/signup — it’s free and no credit card is required. The onboarding flow will create your organization automatically.

2. Add a Provider

Go to Settings > Providers in the dashboard and add at least one LLM provider API key (OpenAI, Anthropic, Google Gemini, etc.). This is the key Floopy uses to call the provider on your behalf.

1. Click Add provider.
2. Select a provider from the list.
3. Paste your provider API key.
4. Click Save.

Your provider key is encrypted at rest and never shown again after saving.

3. Create an API Key

Go to Settings > API Keys and create a Floopy API key. This is the key your application uses to authenticate with the gateway.

1. Click Create API key.
2. Give the key a name (e.g. dev-local).
3. Copy the key immediately — it is shown only once.

4. Make Your First Request

Point your existing code at https://api.floopy.ai/v1 and use your Floopy API key. No SDK changes needed.

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);

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!"}]
  }'

5. Verify in the Dashboard

Open the Requests page in the dashboard. You should see your request listed with:

• Model — the model that handled the request (e.g. gpt-4o)
• Provider — which provider was called (e.g. OpenAI)
• Latency — end-to-end response time in milliseconds
• Tokens — prompt and completion token counts
• Cost — estimated cost based on provider pricing

Click any row to see the full request and response payload, headers, and cache status.

Next Steps

• Routing — control which provider and model handles each request
• Caching — reduce latency and cost with exact and semantic caching
• Firewall — block prompt injections and harmful content
• Prompts — manage and version prompt templates
• Headers Reference — full list of Floopy request and response headers