# Moondream2

> Small but capable vision-language model (14M+ runs) — ask free-form questions about any image. Efficient VQA for tagging, moderation prep, and alt-text.

- **Provider**: replicate
- **Model ID**: lucataco/moondream2
- **Category**: image_video_caption
- **Credits**: 5 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**): Input image
- `prompt` (string, optional): Input prompt (Default: `Describe this image`)

## Example Request

```json
{
  "model": "lucataco/moondream2",
  "input": {
    "image": "https://replicate.delivery/pbxt/KZKNhDQHqycw8Op7w056J8YTX5Bnb7xVcLiyB4le7oUgT2cY/moondream2.png",
    "prompt": "Describe this image"
  }
}
```

## 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

vqa, vision-language, image-captioning, moondream, efficient

## Documentation

https://replicate.com/lucataco/moondream2