# Florence-2 Large

> Microsoft's Florence-2 all-in-one vision model — captioning, object detection, phrase grounding, OCR, and segmentation in a single API via task selection.

- **Provider**: replicate
- **Model ID**: lucataco/florence-2-large
- **Category**: object_detection_segmentation
- **Credits**: 2 per request
- **Pricing Type**: fixed

## API Endpoint

Base URL: https://api.core.today/v1

### Create Prediction
POST /predictions

### Get Status
GET /predictions/{job_id}

### Cancel
DELETE /predictions/{job_id}

## Authentication

Header: `X-API-Key: YOUR_API_KEY`

## Input Parameters

- `image` (string, **required**): Grayscale input image
- `task_input` (string, optional): Input task (Default: `Caption`; Options: `Caption`, `Detailed Caption`, `More Detailed Caption`, `Caption to Phrase Grounding`, `Object Detection`, `Dense Region Caption`, `Region Proposal`, `OCR`, `OCR with Region`)
- `text_input` (string, optional): Text Input(Optional)

## Example Request

```json
{
  "model": "lucataco/florence-2-large",
  "input": {
    "image": "https://replicate.delivery/pbxt/L9zDhV2KiVnudUyRiNjt9P18LZ98Hrqq5GGdx9szmBCAyEhP/car.jpg",
    "task_input": "Object Detection"
  }
}
```

## Response Format

```json
{
  "job_id": "abc123",
  "status": "pending",
  "provider": "replicate",
  "model": "black-forest-labs/flux-schnell",
  "created_at": "2026-01-01T00:00:00Z",
  "result": null,
  "error": null
}
```

Status values: `pending`, `processing`, `completed`, `failed`, `cancelled`

## Usage Flow

1. POST /predictions with model and input → receive job_id
2. Poll GET /predictions/{job_id} until status is `completed` or `failed`
3. Result contains output URL(s) or data

## Output Type

json

## Tags

vision, object-detection, captioning, ocr, florence, microsoft

## Documentation

https://replicate.com/lucataco/florence-2-large