[Integrations](https://spiral.ai/integrations) › [Codex](https://spiral.ai/integrations/codex) › [BEN v2](https://spiral.ai/integrations/codex/ben-v2)

# How to Use BEN v2 in Codex

BEN v2 removes backgrounds from existing photos to prepare product cutouts, portraits, and design assets. Its focus includes hair matting and fine edges, though low contrast and compression can still cause halos.

|  |  |
| --- | --- |
| Model | BEN v2 |
| Available through | fal |
| Category | Image |
| Price | $0.0325 per 1,048,576 megapixels. Minimum 1,048,576 pixels. |
| Returns | image |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with BEN v2 in Codex

- Use BEN v2 to remove the backgrounds from the product photos in public/products. Save separate PNG cutouts and build a preview page on white and dark backgrounds for review.
- Use BEN v2 on the staff portraits in this project. Add the cutouts to a draft team page and show enlarged previews of hair and shoulder edges.
- Use BEN v2 on the hero product photo in this project. Create a transparent asset and show it on the landing page's actual background so I can inspect the boundary.
- Use BEN v2 to remove the background from the raster sponsor logo in this project. Show the original and result at full size so I can check lettering and thin strokes.
- Use BEN v2 to compare the original product photo with a tighter crop near square. Keep the whole product visible and build a side-by-side preview of the resulting edges.

## How to set up BEN v2 in Codex

Pick the way that suits you. Each takes about two minutes.

### Use Spiral's MCP server

1. **Add the hosted server**

```bash
codex mcp add spiral --url https://api.spiral.ai/mcp
```

2. **Sign in**: Codex opens the browser: sign in to Spiral and click Authorize. No API key. `codex mcp list` then shows Spiral.

```bash
codex mcp login spiral
```

### Use the Spiral skill

1. **Send Codex this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run BEN v2**: One request; the result comes back by polling or a webhook.

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "fal",
    "model": "fal-ai/ben/v2/image",
    "input": {
      "image_url": "https://storage.googleapis.com/falserverless/gallery/Ben2/arduino-uno-board-electronics-hand-600nw-1869855883.webp"
    }
  }'
```

Then paste one of the prompts above: Codex finds BEN v2 on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/codex

## BEN v2 tools and prices

- [BEN v2 · Background Remover (image)](https://spiral.ai/tools/fal/fal-ai/ben/v2/image) (fal): $0.0325 per 1,048,576 megapixels. Minimum 1,048,576 pixels.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| seed |  | — | Random seed for reproducible generation. |

## What can you do with BEN v2 in Codex?

Prepare transparent product and portrait assets for your project's pages with BEN v2. Have the coding agent add previews that make edge defects easy to inspect before replacing existing assets.

### Product listing cutouts

Remove the background from product photos, then place approved cutouts on a consistent listing background. Inspect thin handles and small label text.

### Portraits for team pages

Prepare portrait cutouts for staff pages and speaker layouts. Review hair and shoulder edges against the page background.

### Fashion catalog layouts

Isolate clothing or photographed models for catalog compositions. Keep the full garment visible in the source and review fine boundaries.

### Advertising compositions

Extract a photographed product for reuse across ad layouts. Keep a transparent master so each composition can use a different background.

### Presentation assets

Turn product and portrait photos into cutouts for slides. Preview the result on the slide color to catch visible halos.

### Logo background removal

Remove a background from a sharp raster logo for placement in a layout. Inspect thin strokes and lettering before approving it.

## Overview

- [fal](https://spiral.ai/providers/fal)
- [All Codex guides](https://spiral.ai/integrations/codex)

## BEN v2 in other agents

- [Amp](https://spiral.ai/integrations/amp/ben-v2)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/ben-v2)
- [Claude](https://spiral.ai/integrations/claude-desktop/ben-v2)
- [Claude Code](https://spiral.ai/integrations/claude-code/ben-v2)
- [Cline](https://spiral.ai/integrations/cline/ben-v2)
- [Cursor](https://spiral.ai/integrations/cursor/ben-v2)
- [Devin](https://spiral.ai/integrations/devin/ben-v2)
- [dots](https://spiral.ai/integrations/dots/ben-v2)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/ben-v2)
- [Gemini](https://spiral.ai/integrations/gemini/ben-v2)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/ben-v2)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/ben-v2)
- [goose](https://spiral.ai/integrations/goose/ben-v2)
- [Grok](https://spiral.ai/integrations/grok/ben-v2)
- [Grok Build](https://spiral.ai/integrations/grok-build/ben-v2)
- [Hermes](https://spiral.ai/integrations/hermes/ben-v2)
- [Instinct](https://spiral.ai/integrations/instinct/ben-v2)
- [Manus](https://spiral.ai/integrations/manus/ben-v2)
- [Muse](https://spiral.ai/integrations/muse/ben-v2)
- [Muse Code](https://spiral.ai/integrations/muse-code/ben-v2)
- [n8n](https://spiral.ai/integrations/n8n/ben-v2)
- [Notion](https://spiral.ai/integrations/notion/ben-v2)
- [OpenClaw](https://spiral.ai/integrations/openclaw/ben-v2)
- [opencode](https://spiral.ai/integrations/opencode/ben-v2)
- [Perplexity](https://spiral.ai/integrations/perplexity/ben-v2)
- [Raycast](https://spiral.ai/integrations/raycast/ben-v2)
- [VS Code](https://spiral.ai/integrations/vscode/ben-v2)
- [Windsurf](https://spiral.ai/integrations/windsurf/ben-v2)
- [Zapier](https://spiral.ai/integrations/zapier/ben-v2)

## More Codex guides

- [Age Progression](https://spiral.ai/integrations/codex/age-progression)
- [Baby Version](https://spiral.ai/integrations/codex/baby-version)
- [Age Modify](https://spiral.ai/integrations/codex/age-modify)
- [Background Change](https://spiral.ai/integrations/codex/background-change)
- [851 Labs Background Remover](https://spiral.ai/integrations/codex/851-labs-background-remover)
- [Boogu Image](https://spiral.ai/integrations/codex/boogu-image)

## Questions about BEN v2 in Codex

**Can Codex use BEN v2?**

Yes. Add Spiral to Codex as an MCP server, and Codex can find and run BEN v2 like any built-in tool.

**How much does BEN v2 cost in Codex?**

$0.0325 per 1,048,576 megapixels. Minimum 1,048,576 pixels. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Codex plan is separate.

**Do I need a fal account to use BEN v2 in Codex?**

No. Spiral runs BEN v2 on its own fal account. You sign in to Spiral once and never paste a key.

**How long does it take to set up BEN v2 in Codex?**

About two minutes: add the hosted server, then sign in.

**Does Codex wait while BEN v2 runs?**

BEN v2 runs in the background. Codex starts the run, checks on it and gives you the image when it's ready.

**What is BEN v2 useful for?**

BEN v2 removes backgrounds from existing photos. Use the cutouts in product listings, portrait layouts, catalogs, and ads.

**Can BEN v2 handle hair and fine edges?**

The maker highlights hair matting and edge refinement as strengths. Inspect loose hair and soft boundaries before using the cutout in a finished design.

**Where can BEN v2 cutouts need cleanup?**

Hair, fur, and transparent objects can retain rough edges, halos, or color fringing. Review those areas closely before approving the result.

**How should I prepare an image for BEN v2?**

Start with a sharp original and a clearly visible subject. Where practical, crop toward a square while keeping the whole subject inside the frame.

**Why can very wide or tall images lose detail?**

The maker explains that background removal uses a fixed internal working size. Extreme proportions can leave fewer effective pixels for the subject, so try a tighter crop before processing.

