Vision
Image input on models that support it.
Send images with the standard image_url content part, either as an HTTPS URL or a base64 data URL:
curl https://api.vichar.io/v1/chat/completions \
-H "Authorization: Bearer $VICHAR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "vichar-sonnet-5.5",
"messages": [{
"role": "user",
"content": [
{"type": "text", "text": "What is in this image?"},
{"type": "image_url", "image_url": {"url": "https://example.com/photo.png"}}
]
}]
}'Only some models accept image input. To find them, list the catalogue and look for vision support in the model's capability flags, or filter vichar.io/models. The Vichar catalogue is text out; image input only.
How is this guide?