Use a server-created API key.

Create a key from your account dashboard and keep it server-side. The API accepts a Bearer key. The playground uses your Clerk session and never places a key in browser storage.

Streaming by default in your app.

curl https://ai.venym.io/v1/chat/completions \
  -H "Authorization: Bearer $VENYM_AI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "venym/qwen3.8-27b-obliterated-iq4-dflash2",
    "messages": [{"role":"user","content":"Say hello."}],
    "max_tokens": 256,
    "stream": true,
    "stream_options": {"include_usage": true}
  }'

Send one bounded image with text.

The Qwen projector is enabled server-side. Use an HTTPS image URL or a `data:image/...` URL. Images are processed in memory for the request and are not retained.

{
  "model": "venym/qwen3.8-27b-obliterated-iq4-dflash2",
  "messages": [{
    "role": "user",
    "content": [
      {"type":"text","text":"Describe this image."},
      {"type":"image_url","image_url":{"url":"data:image/png;base64,..."}}
    ]
  }],
  "max_tokens": 256
}

No training. No conversation archive.

Account and payment records remain necessary to operate paid access. This product promise is specifically about inference content: the text, images, and generated output are not retained by Venym.