Skip to main content

First API Call

CleverThis exposes an OpenAI-compatible inference API, which means any tool or SDK built for OpenAI works without modification — just point it at the CleverThis base URL and supply a ct_live_ API key.

This page walks you through generating an API key and sending your first chat completion request.

1. Generate an API key​

  1. Open the Dashboard and click your workspace name in the top-left.
  2. Navigate to Settings → API Keys.
  3. Click New Key, give it a name (e.g. dev-test), and confirm.
  4. Copy the key immediately — it is shown only once. Inference keys have the prefix ct_live_.

2. Send a chat completion​

Replace <YOUR_KEY> with your key and <MODEL_ID> with any model ID visible in the Library (e.g. openai/gpt-4o):

curl https://api.cleverthis.com/v1/chat/completions \
  -H "Authorization: Bearer <YOUR_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "<MODEL_ID>",
    "messages": [
      {"role": "user", "content": "Hello, CleverThis!"}
    ]
  }'

A successful response looks like:

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "model": "openai/gpt-4o",
  "choices": [
    {
      "index": 0,
      "message": {"role": "assistant", "content": "Hello! How can I help you today?"},
      "finish_reason": "stop"
    }
  ],
  "usage": {"prompt_tokens": 10, "completion_tokens": 9, "total_tokens": 19}
}

3. Use with the OpenAI Python SDK​

from openai import OpenAI

client = OpenAI(
    api_key="ct_live_YOUR_KEY",
    base_url="https://api.cleverthis.com/v1",
)

response = client.chat.completions.create(
    model="openai/gpt-4o",
    messages=[{"role": "user", "content": "Hello, CleverThis!"}],
)
print(response.choices[0].message.content)
Coming soon

Full error reference and troubleshooting for common first-call failures (401, 402, 429) is being added to the Errors page.