Analyze an image | EmpirioLabs AI Docs

Vision-only endpoint for image-understanding models (Janus Pro, Amazon Nova Canvas variation/describe modes). For chat-style vision (Qwen-VL, Mistral Vision, etc.) use POST /v1/chat/completions with an image_url content part instead.

Authentication

AuthorizationBearer

Pass your EmpirioLabs API key as a bearer token. The Anthropic-style x-api-key header is also accepted on every endpoint.

Request

This endpoint expects an object.

modelstringRequired

image_urlstringRequired

URL or base64 of the image to analyze.

questionstringRequired

What you want to know about the image.

analysis_temperaturedoubleOptional

analysis_top_pdoubleOptional

analysis_seedintegerOptional

Response

Analysis result.

answerstringOptional

usageobjectOptional

$	curl -X POST https://api.empiriolabs.ai/v1/images/analysis \
>	-H "Authorization: Bearer <token>" \
>	-H "Content-Type: application/json" \
>	-d '{
>	"model": "janus-pro-deepseek",
>	"image_url": "https://images.empiriolabs.ai/sample/nature-forest-001.jpg",
>	"question": "What types of trees are visible in this image?"
>	}'

1	{
2	"answer": "The image shows a dense forest primarily composed of pine and fir trees, with some deciduous trees scattered throughout.",
3	"usage": {
4	"prompt_tokens": 45,
5	"completion_tokens": 78,
6	"total_tokens": 123
7	}
8	}