MicrosoftFastHigh

Florence-2 Large

Microsoft's Florence-2 all-in-one vision model — captioning, object detection, phrase grounding, OCR, and segmentation in a single API. Pick a task, optionally add text input, done.

2 credits

per call

One model, many tasks (task_input selection)

Caption / Detailed Caption / Object Detection

OCR and OCR with region boxes

Phrase grounding and segmentation

3 credits per call

Run it right now

Test this model instantly in the Console Playground — no code required

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

llms.txtllms.txt ↗

Quick Start

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "lucataco/florence-2-large",
  "input": {
    "image": "https://example.com/document.jpg",
    "task_input": "OCR with Region"
  }
}'

Parameters

Parameter	Type	Required	Default	Description
`image`	string	Yes	-	Input image
`task_input`	string	No	Caption	Vision task to run (caption, detection, OCR, grounding, segmentation...) CaptionDetailed CaptionMore Detailed CaptionCaption to Phrase GroundingObject DetectionDense Region CaptionRegion ProposalOCROCR with Region
`text_input`	string	No	-	Text for tasks that need it (grounding phrases, region coords)

How to Provide File Input

There are 3 ways to provide files for the image parameter:

Recommended

Direct Upload (Multipart)

Attach files directly to POST /v1/predictions/upload. No separate upload step needed.

curl -X POST "https://api.core.today/v1/predictions/upload" \
  -H "X-API-Key: cdt_your_api_key" \
  -F "model=lucataco/florence-2-large" \
  -F 'input={"prompt":"your prompt here"}' \
  -F "file:image=@your_file.png"

Image URL

Pass a publicly accessible URL directly. You can also use file_url from the Storage API.

{
  "model": "lucataco/florence-2-large",
  "input": {
    "prompt": "your prompt here",
    "image": "https://example.com/image.jpg"
  }
}

See the File Upload docs for more upload methods including Presigned URLs.

Common Parameters

Common parameters used when calling POST /v1/predictions.

Parameter	Type	Required	Default	Description
`model`	string	Yes	-	Model identifier
`input`	object	Yes	-	Object containing the model-specific parameters from the table above
`output_folder`	string	No	-	Folder path for output files (max 256 chars, '..' not allowed)
`webhook_url`	string	No	-	Webhook URL to call on completion
`is_public`	boolean	No	false	If true, output files are also available via permanent public URLs

Examples

OCR with Regions

Extract text with positional boxes

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "lucataco/florence-2-large",
  "input": {
    "image": "https://example.com/document.jpg",
    "task_input": "OCR with Region"
  }
}'

Detailed Caption

Get a rich multi-sentence caption

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "lucataco/florence-2-large",
  "input": {
    "image": "https://example.com/scene.jpg",
    "task_input": "More Detailed Caption"
  }
}'