API Documentation

API Key Management

Create and manage your secret keys in the dashboard. Keys grant uniform access to all models and endpoints.

Developer Quickstart

Quickstart & Overview

Quancis provides production-ready inference endpoints engineered with composite multi-stage verification and automated prefix caching. It is 100% wire-compatible with standard OpenAI and Anthropic client libraries, SDKs, and REST callers.

Production Base URL

https://api.quancis.space/v1

Direct all standard Chat Completions and Responses requests to this base URL, or use the specialized /pro/v1 route prefix.

Account Balance & Playground Billing

The dashboard Playground draws directly from the exact same account balance as your programmatic API requests. Using the interactive in-app chat consumes credits at the exact same per-token pricing schedule as the API — see the rate card above for each model's exact input, cached-input, and output rates. There are no separate playground quotas.

Execute a cURL Test Request

Send a standard POST request with your API key in the Authorization or x-api-key header:

curl https://api.quancis.space/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-quan-YOUR_API_KEY" \
  -d '{
    "model": "kael-beta",
    "messages": [
      {"role": "user", "content": "Explain the advantages of composite multi-stage verification in language models."}
    ]
  }'

Python Integration (OpenAI SDK)

Pass your key and the Quancis base URL into the official openai client:

from openai import OpenAI

client = OpenAI(
    api_key="sk-quan-YOUR_API_KEY",
    base_url="https://api.quancis.space/v1"
)

completion = client.chat.completions.create(
    model="kael-beta",
    messages=[
        {"role": "system", "content": "You are a senior systems architect."},
        {"role": "user", "content": "Draft an idempotent transaction pattern for distributed billing."}
    ]
)

print(completion.choices[0].message.content)