[Integrations](https://spiral.ai/integrations) › [Grok](https://spiral.ai/integrations/grok) › [Sa2VA 8B image segmentation](https://spiral.ai/integrations/grok/sa2va-8b-image-segmentation)

# How to Use Sa2VA 8B image segmentation in Grok

Sa2VA 8B returns a text answer and image segmentation masks for a supplied still image. Use it to evaluate image descriptions and object masks with the model that scored 84.4 on MMBench versus 4B's 81.8.

|  |  |
| --- | --- |
| Model | Sa2VA 8B image segmentation |
| Available through | fal |
| Category | Data |
| Price | $0.052 per image. |
| Returns | json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Sa2VA 8B image segmentation in Grok

- Use Sa2VA 8B image segmentation on the supplied NASA Perseverance rover photo. Describe the rover's visible equipment and request masks for the parts discussed.
- Use Sa2VA 8B image segmentation on https://raw.githubusercontent.com/facebookresearch/segment-anything-2/main/notebooks/images/truck.jpg. Describe the truck's position relative to the building and request a mask for each.
- Use Sa2VA 8B image segmentation to describe the truck in https://raw.githubusercontent.com/facebookresearch/segment-anything-2/main/notebooks/images/truck.jpg and request a mask isolating it.
- Use Sa2VA 8B image segmentation to look this up and give me the result as a table.
- Pull the latest numbers from Sa2VA 8B image segmentation and tell me what changed since last week.

## How to set up Sa2VA 8B image segmentation in Grok

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

### Use the Grok connector

1. **Add a custom connector**: In Grok open Settings › Connect Apps, then Add a custom connector. Name it Spiral, paste this URL, leave Headers empty and click Add MCP.

```text
https://api.spiral.ai/mcp
```

2. **Sign in to Spiral and approve**: Grok opens Spiral: sign in, pick the organization and click Authorize. Spiral gives the connection its own API key; Grok never sees it, and you can remove the connection under Settings › Connected apps.

3. **Check that it is connected**: Connect Apps › Custom shows Spiral as Connected. It works in every Grok chat and Grok bot.

### Use the Spiral skill

1. **Send Grok 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 Sa2VA 8B image segmentation**: 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/sa2va/8b/image",
    "input": {
      "prompt": "Could you please give me a brief description of the image? Please respond with interleaved segmentation masks for the corresponding parts of the answer.",
      "image_url": "https://raw.githubusercontent.com/facebookresearch/segment-anything-2/main/notebooks/images/truck.jpg"
    }
  }'
```

Then paste one of the prompts above: Grok finds Sa2VA 8B image segmentation on Spiral, shows the price and runs it.

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

## Sa2VA 8B image segmentation tools and prices

- [Sa2VA 8B Image · Vision](https://spiral.ai/tools/fal/fal-ai/sa2va/8b/image) (fal): $0.052 per image.

## What can you do with Sa2VA 8B image segmentation in Grok?

Turn a supplied photo or clip into a description with masks that show the objects being discussed. A chat app can ask Sa2VA focused visual questions and present the returned text and masks for review.

### Draft visual descriptions

Ask Sa2VA to describe a product photo or demonstration clip, then use the answer as a draft for a media caption.

### Prepare annotation drafts

Request object descriptions with corresponding masks for an image or video dataset. Give annotators the text and masks together for review.

### Catalog product media

Describe visible products, colors, and surroundings in catalog photos and demonstration videos. Use the descriptions to draft searchable asset labels.

### Prepare masks for editing

Name the object an editor needs to isolate and request its segmentation mask. Review the returned image mask or mask video before using it in an editing workflow.

### Review generated media

Ask specific questions about objects and their relationships in generated stills or clips. Compare the answers and masks with the creative brief during review.

### Create visual teaching material

Use licensed illustrations or animation clips to draft object descriptions and visual questions. Request matching masks to highlight the regions discussed in a lesson.

## Overview

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

## Sa2VA 8B image segmentation in other agents

- [Amp](https://spiral.ai/integrations/amp/sa2va-8b-image-segmentation)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/sa2va-8b-image-segmentation)
- [Claude](https://spiral.ai/integrations/claude-desktop/sa2va-8b-image-segmentation)
- [Claude Code](https://spiral.ai/integrations/claude-code/sa2va-8b-image-segmentation)
- [Cline](https://spiral.ai/integrations/cline/sa2va-8b-image-segmentation)
- [Codex](https://spiral.ai/integrations/codex/sa2va-8b-image-segmentation)
- [Cursor](https://spiral.ai/integrations/cursor/sa2va-8b-image-segmentation)
- [Devin](https://spiral.ai/integrations/devin/sa2va-8b-image-segmentation)
- [dots](https://spiral.ai/integrations/dots/sa2va-8b-image-segmentation)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/sa2va-8b-image-segmentation)
- [Gemini](https://spiral.ai/integrations/gemini/sa2va-8b-image-segmentation)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/sa2va-8b-image-segmentation)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/sa2va-8b-image-segmentation)
- [goose](https://spiral.ai/integrations/goose/sa2va-8b-image-segmentation)
- [Grok Build](https://spiral.ai/integrations/grok-build/sa2va-8b-image-segmentation)
- [Hermes](https://spiral.ai/integrations/hermes/sa2va-8b-image-segmentation)
- [Instinct](https://spiral.ai/integrations/instinct/sa2va-8b-image-segmentation)
- [Manus](https://spiral.ai/integrations/manus/sa2va-8b-image-segmentation)
- [Muse](https://spiral.ai/integrations/muse/sa2va-8b-image-segmentation)
- [Muse Code](https://spiral.ai/integrations/muse-code/sa2va-8b-image-segmentation)
- [n8n](https://spiral.ai/integrations/n8n/sa2va-8b-image-segmentation)
- [Notion](https://spiral.ai/integrations/notion/sa2va-8b-image-segmentation)
- [OpenClaw](https://spiral.ai/integrations/openclaw/sa2va-8b-image-segmentation)
- [opencode](https://spiral.ai/integrations/opencode/sa2va-8b-image-segmentation)
- [Perplexity](https://spiral.ai/integrations/perplexity/sa2va-8b-image-segmentation)
- [Raycast](https://spiral.ai/integrations/raycast/sa2va-8b-image-segmentation)
- [VS Code](https://spiral.ai/integrations/vscode/sa2va-8b-image-segmentation)
- [Windsurf](https://spiral.ai/integrations/windsurf/sa2va-8b-image-segmentation)
- [Zapier](https://spiral.ai/integrations/zapier/sa2va-8b-image-segmentation)

## More Grok guides

- [Sa2VA 4B video segmentation](https://spiral.ai/integrations/grok/sa2va-4b-video-segmentation)
- [Sa2VA 8B video segmentation](https://spiral.ai/integrations/grok/sa2va-8b-video-segmentation)
- [Sa2VA 4B image segmentation](https://spiral.ai/integrations/grok/sa2va-4b-image-segmentation)
- [fal NSFW image check](https://spiral.ai/integrations/grok/fal-nsfw-image-check)
- [SAM 3 image embedding](https://spiral.ai/integrations/grok/sam-3-image-embedding)
- [fal image NSFW probability](https://spiral.ai/integrations/grok/fal-image-nsfw-probability)

## Questions about Sa2VA 8B image segmentation in Grok

**Can Grok use Sa2VA 8B image segmentation?**

Yes. Add Spiral to Grok as an MCP server, and Grok can find and run Sa2VA 8B image segmentation like any built-in tool.

**How much does Sa2VA 8B image segmentation cost in Grok?**

$0.052 per image. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Grok plan is separate.

**Do I need a fal account to use Sa2VA 8B image segmentation in Grok?**

No. Spiral runs Sa2VA 8B image segmentation on its own fal account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Sa2VA 8B image segmentation in Grok?**

About two minutes: add a custom connector, then sign in to Spiral and approve, then check that it is connected.

**Does Grok wait while Sa2VA 8B image segmentation runs?**

Sa2VA 8B image segmentation runs in the background. Grok starts the run, checks on it and gives you the json when it's ready.

**What does Sa2VA return besides a description?**

Its documented outputs include generated text and segmentation masks. Image analysis returns image masks; video analysis returns mask video files.

**Can Sa2VA fetch media behind a login?**

Externally hosted media URLs must be publicly accessible. A link that requires a website login falls outside that documented boundary.

**How do the published 4B and 8B results compare?**

ByteDance reports MMBench scores of 81.8 for 4B and 84.4 for 8B. On the MeVIS video segmentation benchmark, it reports 55.9 and 58.9 respectively; these are benchmark scores, not accuracy percentages for your media.

**How should I ask for segmentation masks?**

Explicitly request masks for the objects discussed in the answer. ByteDance's example asks for interleaved segmentation masks corresponding to parts of the description.

**Which scenes need closer review?**

The Sa2VA paper identifies occlusion and long referring descriptions as challenges. It also calls out longer videos with camera motion, so review those results closely before using the masks as annotations.

