Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.dolphy.chat/llms.txt

Use this file to discover all available pages before exploring further.

​
Endpoint

POST https://dolphy.chat/api/v1/images/edits
Single backend model: seedream-4.5 (NSFW-capable, runs on Novita with Replicate fallback).

​
Request

Unlike OpenAI’s edits API which uses multipart/form-data, ours takes JSON with a base64-encoded image. Easier for backend customers. 
{
  "image": "iVBORw0KGgo...",
  "prompt": "make the sky purple",
  "response_format": "url"
}
FieldTypeNotes
imagestringBase64-encoded source (PNG/JPG/WebP). Up to 25MB raw. Strip the data:image/...;base64, prefix or include it; both work.
promptstringUp to 32000 chars
response_formatenumurl (default) or b64_json

​
Response

{
  "created": 1730000000,
  "data": [{ "url": "https://firebasestorage.googleapis.com/..." }]
}

​
Code

import fs from "fs";
const b64 = fs.readFileSync("./input.jpg").toString("base64");
const r = await fetch("https://dolphy.chat/api/v1/images/edits", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.DOLPHY_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({ image: b64, prompt: "make the sky purple" }),
});
const { data } = await r.json();
console.log(data[0].url);

​
Billing

2 credits per edit. No per-image-size variance.