Quickstart

Get a completion back from PlainField in under five minutes. You will create an account, generate an API key, and send your first request.

Prerequisites

• A web browser, to sign up at app.plainfield-ai.com 
• curl (or any HTTP client)

1. Create your account

Go to app.plainfield-ai.com/signup  and sign up with your email. After confirming your email, you are asked to create an organization — this is the workspace that owns your API keys, usage, and billing.

2. Create an API key

In the dashboard, open Keys → API Keys and select Create key. Give it a name (for example, production) and select Generate.

Your key is shown once, in the form pt_live_.... Copy it now and store it somewhere safe — you cannot view it again. If you lose it, revoke it and create a new one.

3. Send a request

Send an OpenAI-format request to the gateway. The provider is selected by the provider/model prefix in the model field, and your API key goes in the Authorization header.

curl -X POST https://api.plainfield-ai.com/ai/chat/completions \
  -H 'Authorization: Bearer pt_live_...' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "openai/gpt-4o-mini",
    "messages": [{"role": "user", "content": "Say hello in one sentence."}]
  }'

Expected output

An OpenAI-format chat completion:

{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "model": "gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "message": { "role": "assistant", "content": "Hello! How can I help you today?" },
      "finish_reason": "stop"
    }
  ],
  "usage": { "prompt_tokens": 12, "completion_tokens": 9, "total_tokens": 21 }
}

PlainField logged this request and estimated its cost from the usage token counts. Open Analytics in the dashboard to see it appear.

Common errors

Next steps

• Use the OpenAI SDK instead of curl: Your first request with the OpenAI SDK
• Attribute spend to prompts and users: Track prompt costs
• Compare models without code: Workbench
• See every endpoint: API reference