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

Get started

Quickstart

Go from zero to your first response: choose a plan, create a key, pick a model, and send a request.

  1. Create an account and choose a plan

    Sign up, then choose Spark or Ember on the pricing page. Requests need an active plan or top-up credits; without either they return 403 no_active_plan.

  2. Create an API key

    On the dashboard overview, click Generate API key. The key is shown once, so copy it right away and store it somewhere safe.

    Export it as an environment variable so it never ends up in your code:

    export KYARA_INTELLIGENCE_API_KEY="your-api-key"
  3. Choose a model

    Browse the model catalog, or call GET /v1/models, and copy the ID of the model you want. This guide uses deepseek/deepseek-v4-flash, a fast, low-cost default.

  4. Send a request

    Point your client at https://api.kyara-intelligence.com/v1 and call chat completions. For the SDK examples, install the official OpenAI package first: npm install openai or pip install openai.

    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!" }
        ]
      }'
  5. Check your balance

    Every request spends credits. Read what you have left at any time:

    curl https://api.kyara-intelligence.com/v1/balance \
      -H "Authorization: Bearer $KYARA_INTELLIGENCE_API_KEY"

    See Balance for the response fields.

What's next