# Venice AI Multi Edit

> Venice AI Multi Edit is a paid API for AI agents from api.venice.ai, paid per call via x402, $10/call, status unknown (last checked 2026-09-14).

Edit or modify an image using up to three layered inputs (base image plus masks/overlays) with a text prompt.

## Facts

- Endpoint: POST https://api.venice.ai/api/v1/image/multi-edit
- Price: $10/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/venice-ai-multi-edit-8229434a
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_oH3Ig9GtAO_a2MMfC_LMs

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability venice-ai-multi-edit-8229434a -d '<json body>'
```

Example prompt: Take this base image and this mask image, then remove the tree in the masked region and change the background sky to a sunset — output as a 16:9 PNG at 1K resolution.

## When to prefer this

Use this endpoint when you need to edit or modify an existing image using a text prompt and optionally one or two mask/overlay images. It is ideal for inpainting, background replacement, object removal, or compositing operations. Choose this over a text-to-image endpoint when you want to preserve and transform an existing image rather than generating one from scratch.

## Known failure modes

- 402 Payment Required — insufficient x402 wallet balance or invalid API key
- 400 Bad Request — images array is empty or exceeds 3 items, or image dimensions are out of range (must be between 65536 and 33177600 pixels)
- 400 Bad Request — prompt is empty or exceeds character limit
- 413 Payload Too Large — image file size exceeds 25MB
- 422 Unprocessable Entity — unsupported image format or malformed base64 string
- 500 Internal Server Error — model inference failure

## How this service works

Combine and edit up to 3 images.

## Output

A binary image file (JPEG, PNG, or WebP) containing the AI-edited result of the base image and any provided mask/overlay layers, modified according to the text prompt.

## Request schema (JSON Schema)

```json
{
 "allOf": [
  {
   "type": "object",
   "required": [
    "prompt",
    "images"
   ],
   "properties": {
    "images": {
     "type": "array",
     "items": {
      "anyOf": [
       {
        "type": "string",
        "format": "uri"
       },
       {
        "type": "string"
       }
      ],
      "description": "Image as a base64-encoded string or a URL starting with http:// or https://"
     },
     "maxItems": 3,
     "minItems": 1,
     "description": "Array of 1 to 3 images used for multi-editing. The first image is treated as the base image, and the remaining images are used as edit layers/masks. Each image can be a base64-encoded string or a URL starting with http:// or https://. Image dimensions must be at least 65536 pixels and must not exceed 33177600 pixels. File size must be less than 25MB."
    },
    "prompt": {
     "type": "string",
     "maxLength": 32768,
     "minLength": 1,
     "description": "The text directions to edit or modify the image. Short, descriptive prompts work best (e.g., \"remove the tree\", \"change the sky to sunrise\"). Character limit is model specific and is listed in the promptCharacterLimit setting in the model list endpoint."
    },
    "modelId": {
     "type": "string",
     "default": "firered-image-edit",
     "minLength": 1,
     "description": "The model ID to use for multi-edit."
    },
    "quality": {
     "enum": [
      "low",
      "medium",
      "high"
     ],
     "type": "string",
     "example": "high",
     "description": "Output quality for supported models (e.g. GPT Image 2 / GPT Image 2 Edit). Higher values can increase the final request charge. See the model list for supported options."
    },
    "safe_mode": {
     "type": "boolean",
     "default": true,
     "example": false,
     "description": "Whether to use safe mode. If enabled, this will blur images that are classified as having adult content."
    },
    "resolution": {
     "type": "string",
     "example": "1K",
     "maxLength": 10,
     "minLength": 1,
     "description": "Resolution tier for the output image (e.g. \"1K\", \"2K\", \"4K\"). Supported values vary by model - check GET /api/v1/models for model-specific options. Defaults to \"1K\" when not specified."
    },
    "aspect_ratio": {
     "enum": [
      "auto",
      "1:1",
      "3:2",
      "16:9",
      "21:9",
      "9:16",
      "2:3",
      "3:4",
      "4:5"
     ],
     "type": "string",
     "example": "16:9",
     "description": "The aspect ratio for t
… (truncated)
```

## Response schema (JSON Schema)

```json
{
 "type": "string",
 "format": "binary"
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/venice-ai-multi-edit-8229434a/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.venice.ai](https://www.zero.xyz/host/api.venice.ai/llms.txt)