# CLIP Features

> CLIP ViT-L/14 embeddings for text AND images (163M+ runs) — put both in the same vector space for cross-modal search, dedup, and zero-shot classification.

- **Provider**: replicate
- **Model ID**: andreasjansson/clip-features
- **Category**: embeddings
- **Credits**: 1 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

- `inputs` (string, optional): Newline-separated inputs. Can either be strings of text or image URIs starting with http[s]:// (Default: `a
b`)

## Example Request

```json
{
  "model": "andreasjansson/clip-features",
  "input": {
    "inputs": "a photo of a dog\na cat\ntwo cats with remote controls\nhttps://replicate.com/api/models/cjwbw/clip-vit-large-patch14/files/36b04aec-efe2-4dea-9c9d-a5faca68b2b2/000000039769.jpg"
  }
}
```

## 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

embeddings, clip, image-embedding, cross-modal, similarity-search

## Documentation

https://replicate.com/andreasjansson/clip-features