Image GenerationActive
moondream3-preview / caption
caption
Moondream3 is a cutting-edge vision-language model that delivers advanced visual reasoning with built-in object detection, pointing, and OCR capabilities—bringing fast, cost-effective, and scalable inference to real-world applications.
Image to TextBf16
Model ID
caption
Provider
moondream3-preview
Updated
1770899032
wiro playground—moondream3-preview/caption
Updated 1770899032
The Moondream 3 "Caption" model is a core capability within the Moondream 3 vision-language model (VLM) for generating natural language descriptions of images. It automatically analyzes the visual content and provides a coherent, detailed narrative, with options to produce varying lengths of captions, from short, concise summaries to long, elaborate descriptions that capture style, attributes, pose, and contextual interpretation.
API quick start
Run caption with a single API call.
POST https://api.wiro.ai/v1/Run/moondream3-preview/caption
{
"inputImage": "https://your-cdn.com/input.png",
"length": "normal",
"temperature": 0.7,
"top_p": 0.95
}