Fittins AI API

The Fittins AI API is the same premium AI fashion generation service as fittins.ai, for your own store, catalogue system or agency tools. Send up to 3 product photos and a model, and get back a studio-quality on-model photo, up to 8K, from the Turbo, Default, Premium or Ultra tier. Results use your plan's credits and also appear in My Generations.

Base URL: https://api.fittins.ai/v1
Plans: Pro, Business, Enterprise
Pricing: The same credits as the website: a Default 1K photo is 40 credits
Format: JSON over HTTPS; files as PNG

Quickstart

1
Create a key
In Profile → API keys on fittins.ai. The key is shown once; keep it on your server.
2
Pick a model
GET /v1/models lists our model library and your custom models.
3
Create a photo
POST /v1/images with your product photo URL. It answers 202 with a generation id.
4
Get the result
Poll GET /v1/generations/{id} every few seconds. When it succeeded, download output.url.

curl https://api.fittins.ai/v1/images \
  -H "Authorization: Bearer $FITTINS_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: tshirt-red-m-front-v1" \
  -d '{
  "product_images": [
    {
      "url": "https://cdn.mystore.com/p/tshirt-red-front.jpg"
    }
  ],
  "model_id": "mdl_lib_DM5rQvl3KtlR7nqumd6I",
  "prompt": "full body, plain light grey background, soft studio light, front view",
  "aspect_ratio": "3:4",
  "tier": "default",
  "quality": "2k",
  "metadata": {
    "sku": "TSHIRT-RED-M"
  }
}'

202 Accepted

{
  "id": "gen_7Hq2Mz9TkQ4x1bVnR8sL",
  "object": "generation",
  "type": "image",
  "status": "queued",
  "created_at": "2026-11-04T17:02:11.000Z",
  "started_at": null,
  "completed_at": null,
  "input": {
    "model_id": "mdl_lib_DM5rQvl3KtlR7nqumd6I",
    "product_images": [
      {
        "url": "https://cdn.mystore.com/p/tshirt-red-front.jpg"
      }
    ],
    "location_id": null,
    "prompt": "full body, plain light grey background, soft studio light, front view",
    "aspect_ratio": "3:4",
    "tier": "default",
    "quality": "2k"
  },
  "output": null,
  "credits": {
    "estimated": 50,
    "charged": 0
  },
  "project_id": null,
  "metadata": {
    "sku": "TSHIRT-RED-M"
  },
  "error": null,
  "livemode": true
}

// Poll until the photo is ready (usually about a minute).
async function waitFor(id) {
  for (;;) {
    const res = await fetch(`https://api.fittins.ai/v1/generations/${id}`, {
      headers: { Authorization: `Bearer ${process.env.FITTINS_API_KEY}` },
    });
    const g = await res.json();
    if (g.status === "succeeded" || g.status === "failed") return g;
    await new Promise((r) => setTimeout(r, 4000));
  }
}

const g = await waitFor(generation.id);
if (g.status === "succeeded") console.log(g.output.url); // full-quality PNG, link valid 24 hours
else console.error(g.error.code, g.error.message);

Basics

Field names	snake_case; times in UTC, ISO 8601 (2026-11-04T17:02:11.000Z)
Ids	gen_ generation · upl_ upload · file_ file · mdl_lib_ / mdl_own_ model · loc_lib_ / loc_own_ location
Lists	{ "object": "list", "data": […], "has_more": true, "next_cursor": "…" }; ?limit=1..100 (default 20) and ?cursor=
Versions	The major version is in the path (/v1). New fields and endpoints are added without notice; anything that would break your code gets a new version, announced 90 days ahead.
Request id	Every response has an X-Request-Id header. Quote it to support.

What responses never include

Our expanded prompts and the AI analysis of your photos: you get back your own prompt as input.prompt.
Preview and thumbnail versions: output is the full-quality PNG only.
Storage addresses: files come through /v1/files, by id, with signed links.
Which AI provider ran a step, and internal error codes: errors use the public codes below.

Questions? Email support@fittins.ai with the X-Request-Id of the request.Next: Authentication →