Early access: features, availability, and pricing may change as Kyara Intelligence evolves.

Get started

What is Kyara Intelligence?

An OpenAI-compatible inference API: one API key, one base URL, and a curated catalog of capable models.

Kyara Intelligence is a general-purpose inference API. It speaks the OpenAI Chat Completions protocol, so the OpenAI SDKs and the apps built on them work with it as they are. Change the base URL, the API key and the model, and your existing code runs on Kyara.

Base URL
https://api.kyara-intelligence.com/v1
Authentication
Bearer kai_…
Endpoint
POST /chat/completions

How it works

To move an existing OpenAI integration to Kyara, change three values:

  1. Set the base URL

    Point your SDK or HTTP client at https://api.kyara-intelligence.com/v1.

  2. Use your Kyara API key

    Send your key as the bearer token. Keep it in an environment variable named KYARA_INTELLIGENCE_API_KEY so it stays out of your source code.

  3. Pick a model ID

    Choose a model from the catalog and put its ID in the model field. deepseek/deepseek-v4-flash is a fast, low-cost place to start.

Your first request

Export your key as KYARA_INTELLIGENCE_API_KEY, then send this request to check it and see a live response.

curl https://api.kyara-intelligence.com/v1/chat/completions \
  -H "Authorization: Bearer $KYARA_INTELLIGENCE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v4-flash",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'

How you pay

A monthly plan includes a weekly allowance of credits that every request draws from, and one-time top-up credits cover heavier weeks. There is no pay-as-you-go invoice, so usage never turns into a surprise bill. See Plans and credits.

Next steps