Ploofy OpenAI-compatible API setup

Use Ploofy’s OpenAI-compatible text chat endpoint in a roleplay client or your own server-side integration. The examples below contain placeholders, never working credentials.

Before you connect

Create your Ploofy account, confirm your email or sign in with a supported provider, and complete the account’s required verification and policy steps. Subscribe from your hub when a spot is available. The subscription is $19.99 USD per month, billed monthly, with five-hour and weekly usage limits. Your hub shows the remaining allowance and reset times.

In your hub, create and name an API key for this client. Copy it when it is first displayed; it cannot be revealed again. Keep it in the client’s private settings. Ploofy does not email your API key. If it is lost or shared, revoke it and create a replacement.

Use the public model IDs

The current Ploofy lineup is sage, novelist, bard, and swift. Enter the lowercase ID, not a model’s underlying download name. Your account and the authenticated model list show which models your key can currently access. Availability can change while a model is offline.

Discover the models available to your key

Set PLOOFY_API_KEY privately in your shell or server environment, then request the authenticated model list. Do not embed the key in a public webpage, URL, source repository, or support screenshot.

curl --fail-with-body https://ploofy.ai/llm/v1/models   -H "Authorization: Bearer $PLOOFY_API_KEY"

Use an id returned in the data array. A model can be absent if your key cannot access it or its serving instance is unavailable.

Send a short roleplay request

curl --fail-with-body https://ploofy.ai/llm/v1/chat/completions   -H "Authorization: Bearer $PLOOFY_API_KEY"   -H "Content-Type: application/json"   -d '{
    "model": "swift",
    "messages": [
      {"role": "system", "content": "You narrate a fictional fantasy adventure."},
      {"role": "user", "content": "Describe the village at sunrise."}
    ],
    "max_tokens": 256,
    "stream": false
  }'

Read the completed reply from choices[0].message.content. Include the conversation history you want the model to use in each request. Input history and generated output must fit the selected model’s active context limit.

Streaming and retries

Set "stream": true and use a client that parses Server-Sent Events. Append text from choices[0].delta.content when present, and stop at data: [DONE]. Role or finish events can have no text. Handle a disconnected stream as an incomplete reply.

Your keys share the account’s five-hour and weekly usage windows; creating another key does not reset the allowance. Check the hub for reset times. Use bounded retries with delays, not simultaneous repeated requests. Optional model features vary: compatibility with chat completions is not a promise of every OpenAI API feature.

When a connection fails

• 401 or 403: check that you used a Ploofy API key, that it has not been revoked, and that your subscription and model access are active. An OpenRouter or OpenAI key is not interchangeable with a Ploofy key.
• 404: check the endpoint format. A base URL ends in /llm/v1; a complete chat endpoint ends in /llm/v1/chat/completions. Do not append either suffix twice.
• 400 or 422: check the model ID, request format, and conversation length. Reduce saved history and output length if the context is too large.
• 429: check your five-hour and weekly usage in the hub. Respect any retry delay and reduce simultaneous requests. Repeated retries do not increase your allowance.
• Timeout or 5xx: check the model status in your account, wait, and retry once rather than repeatedly submitting the same request.

For help, email support@ploofy.ai with your client version, model ID, and error code. Never include your API key, payment details, or private conversations. These instructions describe verified configuration interfaces; a successful connection on your installed client still needs a short in-client test.