Documentation

Base URL and authentication

All requests go to https://api.quobit.ai/v1. Authenticate with the header Authorization: Bearer <your-api-key>. Keys are created in the dashboard under API Keys and are shown in full only once.

Example request — curl

curl https://api.quobit.ai/v1/chat/completions \
  -H "Authorization: Bearer $QUOBIT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"model-alias","messages":[{"role":"user","content":"Hello"}]}'

Example request — Python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.quobit.ai/v1",
    api_key="your-api-key",
)

response = client.chat.completions.create(
    model="model-alias",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Requires the openai package (pip install openai). Any OpenAI-compatible client works with the same base URL and key.

Example response

{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "model": "model-alias",
  "choices": [
    {
      "index": 0,
      "message": { "role": "assistant", "content": "Hello! How can I help?" },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 8,
    "completion_tokens": 7,
    "total_tokens": 15
  }
}

The reply is returned under choices; token counts are reported under usage.

Error codes

Rate limits

Rate limits apply per account and per API key. Your current limits are shown in the dashboard; the API returns 429 when a limit is exceeded. No specific numbers are guaranteed here — limits can change as capacity is managed.

API key security

Do not commit keys to repositories, do not paste keys into public tickets or chat, and do not write keys into logs. Prefer environment variables or a secret store.