Start here

Quickstart

Create a protected project and send traffic through Panicly
View as Markdown

This guide follows the Panicly onboarding model: choose a plan, create a project, connect a provider, generate a Panicly key, then prove the setup with a first routed request.

1

Create or enter a workspace

Sign in to Panicly and open the dashboard.

2

Choose a plan

Plus is the fixed plan for small apps. Premium adds configurable included requests, configurable throughput, and Custom Rules.

3

Create a project

Pick a project name and environment. The project becomes the unit that owns API keys, provider key, rules, request logs, and model controls.

4

Connect a provider

Connect a supported upstream provider such as OpenAI, Anthropic, OpenRouter, Google, or Vercel. Store provider keys server-side through Panicly settings.

5

Generate a Panicly API key

Copy the generated key immediately. It is returned once and then stored only as a prefix plus hash.

6

Send a first protected request

Route a provider-compatible request to Panicly. Onboarding watches for request evidence before considering the setup operational.

First request

chat-completion.sh
$curl https://panicly.lol/v1/chat/completions \
>  -H "Authorization: Bearer $PANICLY_API_KEY" \
>  -H "Content-Type: application/json" \
>  -d '{
>    "model": "openrouter/auto",
>    "messages": [
>      { "role": "user", "content": "Say hello through Panicly." }
>    ],
>    "max_tokens": 64
>  }'
Operational, not just configured

The setup is complete only when Panicly sees traffic and can show request evidence in the dashboard.

Store keys intentionally

Panicly API keys are shown once. Provider keys are encrypted and used server-side for upstream forwarding.