Getting started

This guide walks you from browsing the catalog to a working chat completion.

1. List available models

The catalog is public — no API key is required. Use it to discover model identifiers you will pass as the model field later.

curl https://api.ai.wpengine.com/v1/models

Truncated response:

{
  "object": "list",
  "data": [
    {
      "id": "google/gemini-3.5-flash",
      "object": "model",
      "owned_by": "google",
      "provider": "google",
      "display_name": "Gemini 3.5 Flash",
      "context_window": 1000000,
      "pricing": {
        "input_per_million": "1.5",
        "output_per_million": "9",
        "currency": "USD"
      }
    }
  ]
}

Pick a model id from the response — you will pass it as the model field when you make a chat completion.

2. Create an API key

API keys are issued against a project — a Power console-managed workspace that owns its own keys, model access, and usage quotas. If you don’t have one yet, create it from the Power console’s project picker before continuing.

1. Sign in to the Power console.
2. Open the project you want to issue the key against.
3. Go to API keys → Create key.
4. Copy the key value. It’s shown once — store it in a secret manager. The key has the form wpe_<secret>.

API keys are project-scoped and carry a permission preset (all, read_only, or restricted). For this guide, a key with all — or one that grants chat:write — is enough.

Store the secret immediately

The Power console never re-displays the secret. If you lose it, rotate the key and update your clients.

3. Make a chat completion

curl https://api.ai.wpengine.com/v1/chat/completions \
  -H "Authorization: Bearer wpe_xxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-3.5-flash",
    "messages": [
      {"role": "system", "content": "You are concise."},
      {"role": "user", "content": "What is the speed of light in km/s?"}
    ]
  }'

Truncated response:

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1716240000,
  "model": "google/gemini-3.5-flash",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Approximately 299,792 km/s."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 24,
    "completion_tokens": 9,
    "total_tokens": 33
  }
}

Streaming

Set "stream": true in the request body to receive a stream of Server-Sent Events. Each event is a JSON chunk shaped like chat.completion.chunk; the stream terminates with data: [DONE].

See the curl streaming example for a complete walkthrough.

Next steps

• Authentication — API key scopes and rotation.
• Errors — handle 400, 401, 403, 429, and 502 responses.
• Code samples — the same flow in curl, PHP, and Node.