# MOSS Image (`moss_image`)

> MOSS Image text-to-image: Chinese and English text rendering and layout control (natural language, tag sequences or JSON layouts), 512-2048 px per side, up to 4 images per request.

- Capability: Images (tool `image`) — Text to image
- Price: from $0.01 per run (1 credit = $0.01). Exact price for a request: POST https://api.varg.ai/v2/estimate
- Typical time: ~20 s
- JSON Schema: https://api.varg.ai/v2/tools/image?model=moss_image (public, no key)
- Try it: https://varg.ai/dashboard/tools/playground?model=moss_image

## Call it

REST: `POST https://api.varg.ai/v2/tools/image/call` with `Authorization: Bearer $VARG_API_KEY` (create a key at https://varg.ai/dashboard/api).
It answers `202` with a job right away. Poll `GET /v2/jobs/{id}` until `status` is `completed`, then read `output.outputs[0].url` — or pass `options.webhook_url` and get the finished job POSTed to you.

```bash
curl -X POST https://api.varg.ai/v2/tools/image/call \
  -H "Authorization: Bearer $VARG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "moss_image",
  "prompt": "A wide view of a refrigerator beside a kitchen counter with a fruit bowl. A small sticky note on the refrigerator door is handwritten in Chinese:\n\"记得买牛奶和鸡蛋！\n牛奶两盒，鸡蛋一打。\""
}'
```

MCP: the varg server `https://mcp.varg.ai/mcp` (OAuth sign-in, no key) runs it with `call_tool`:

```json
{
  "tool": "image",
  "input": {
    "model": "moss_image",
    "prompt": "A wide view of a refrigerator beside a kitchen counter with a fruit bowl. A small sticky note on the refrigerator door is handwritten in Chinese:\n\"记得买牛奶和鸡蛋！\n牛奶两盒，鸡蛋一打。\""
  },
  "wait": true
}
```

## Inputs

| field | type | required | default | allowed | description |
|---|---|---|---|---|---|
| `model` | string | yes | — | `moss_image` or a route key below | Which model runs the job. |
| `prompt` | string | no | — | — | — |
| `files` | array of { url } | no | — | — | — |
| `aspect_ratio` | string | no | — | e.g. 16:9 \| 9:16 \| 1:1 \| 4:3 \| 3:4 \| 21:9 \| auto | — |

Media inputs are URLs. Upload a local file first with `POST /v2/files` and pass the returned URL.

## Provider options

Optional, per provider, under `provider_options.<provider>`. Only the options of the provider that runs the job apply — pin a route to choose it.

### provider_options.fal

| field | type | required | default | allowed | description |
|---|---|---|---|---|---|
| `prompt` | string | no | — | — | Text prompt for image generation. Supports natural language, tag sequences, and JSON layouts. |
| `negative_prompt` | string | no | — | — | Negative prompt. When empty, guidance uses transformer layer skipping for the negative branch. |
| `seed` | integer | no | — | -9007199254740991–9007199254740991 | — |
| `sync_mode` | boolean | no | — | — | Return images as data URIs instead of storing them in request history. |
| `image_size` | string | no | — | square_hd \| square \| portrait_4_3 \| portrait_16_9 \| landscape_4_3 \| landscape_16_9 | — |
| `num_images` | integer | no | — | 1–4 | Number of images to generate. |
| `output_format` | string | no | — | jpeg \| png \| webp | — |
| `guidance_scale` | number | no | — | 0–10 | Classifier-free guidance scale. |
| `num_inference_steps` | integer | no | — | 1–100 | Number of denoising steps. |
| `enable_safety_checker` | boolean | no | — | — | Enable output content moderation. Disabling it requires account authorization; unauthorized requests are always checked, and images flagged as unsafe are returned as black images. |
| `enable_prompt_expansion` | boolean | no | — | — | Plan a structured layout from your prompt before generation. Preserves requested visible text and uses the selected image dimensions. If enhancement is unavailable, uses the original prompt. |

## Routes

`"model": "moss_image"` picks a route automatically (priority order, then the inputs you send). To pin one, pass its key as `model`.

| model key | provider | modality | price from | typical time |
|---|---|---|---|---|
| `fal:fal-ai/moss-image` | fal | text-to-image | $0.01 | ~20 s |

---

Catalog version 2026-11-11T12:59:09.901887+00:00. All models: https://varg.ai/models/llms.txt