Image edit

Image

Edit an existing image on the same POST /v1/images endpoint as image generation: pass one or more reference images in input_references (URL or base64 data URL, same two shapes as image input) plus a prompt describing the change. There is no separate upload or multipart endpoint. Edit models are listed under the Image Edit filter on the models catalog; billing, usage.cost and failover work exactly as for generation. Two variants have their own rules: virtual try-on (person photo + garment, its own page) and image upscaling (no prompt, its own page).

import requests

resp = requests.post(
    "https://videorouter.sh/api/v1/images",
    headers={"Authorization": "Bearer llmr_sk_live_..."},
    json={
        "model": "gemini-2.5-flash-image",
        "prompt": "make this scene look like a watercolor painting",
        "input_references": [
            {"type": "image_url", "image_url": {"url": "https://example.com/photo.jpg"}}
        ],
    },
).json()

const res = await fetch("https://videorouter.sh/api/v1/images", {
  method: "POST",
  headers: { Authorization: "Bearer llmr_sk_live_...", "Content-Type": "application/json" },
  body: JSON.stringify({
    model: "gemini-2.5-flash-image",
    prompt: "make this scene look like a watercolor painting",
    input_references: [
      { type: "image_url", image_url: { url: "https://example.com/photo.jpg" } },
    ],
  }),
});
const data = await res.json();

curl https://videorouter.sh/api/v1/images \
  -H "Authorization: Bearer llmr_sk_live_..." \
  -H "content-type: application/json" \
  -d '{
    "model": "gemini-2.5-flash-image",
    "prompt": "make this scene look like a watercolor painting",
    "input_references": [
      {"type": "image_url", "image_url": {"url": "https://example.com/photo.jpg"}}
    ]
  }'

Not yet supported

Mask-based inpainting (restricting an edit to one region) isn't supported — edits apply to the whole image. stream: true is rejected outright, same as generation.