Quickstart

This guide takes you from zero to a streamed response. You need a Vaelor account; the Free plan includes 20 credits every 12 hours, which is plenty to follow along.

1. 1

   Create an API key

   Open API keys in the dashboard, select Create key, and give it a name like local-dev. Copy the key — it starts with vk_live_.

2. 2

   Store it as an environment variable

   Keep the key out of your source code. Export it in your shell, or add it to your .env file.

   Shell

   export VAELOR_API_KEY="vk_live_..."

3. 3

   Send your first request

   Call the chat endpoint with the flash model. The response body is the generated text, streamed as it's written.

   cURLTypeScriptPython

   curl https://api.vaelor.chat/v1/chat \
     -H "Authorization: Bearer $VAELOR_API_KEY" \
     -H "Content-Type: application/json" \
     -d '{
       "text": "Write a haiku about the first snow in Lisbon.",
       "attachments": [],
       "config": { "model": "flash", "modes": [], "uncensored": false }
     }'

4. 4

   Stream tokens as they arrive

   For chat UIs, read the body incrementally instead of waiting for the full reply.

   TypeScript

   const reader = response.body!.pipeThrough(new TextDecoderStream()).getReader()
   
   while (true) {
     const { value, done } = await reader.read()
     if (done) break
     process.stdout.write(value)
   }

5. 5

   Check what it cost

   Every response carries an x-vaelor-usage-request-id header. Look it up in usage to see the credits it was charged.

Next steps#