kavel #

Generate and edit images from Dart and Flutter with no API key, no account and no card.

dart pub add kavel     # or: flutter pub add kavel

import 'package:kavel/kavel.dart';

final kavel = Kavel();
final img = await kavel.generate(
  'matte black ceramic mug on pale oak, soft window light from the left, shallow depth of field',
  aspectRatio: '16:9',
);
print(img.url); // https://cdn.kavel.ai/uploads/kie/image/....webp

final edited = await kavel.edit(img.url, 'place the mug on a white marble surface');

Every other image package wants a key from OpenAI, fal or Replicate before it runs once — and a key shipped inside a Flutter app is a key anyone can pull out of the binary. This one talks to the free tier of Kavel: a client id the package invents rather than an account you register, so there is no secret to ship.

Why it is shaped this way #

• One dependency, http. Works in Flutter on every platform and in plain Dart CLIs.
• An edit lane. edit takes a photo you already have and one sentence describing the change.
• A typed exception. KavelException.kind is an enum — quota means wait or sign in, rejected means reword, signIn means the request is off the free shelf.
• It keeps polling through a dropped connection — a phone switching from Wi-Fi to cellular mid-job does not throw away a generation that is about to run.

Limits, measured against the running service #

• The free grant is 15 credits. An image costs 5, an edit costs 15. The package mints a new client id per call, so a loop is not capped at three.
• 30 credits per IP per day sits on top — about six images from one machine — and surfaces as a quota exception.
• Free output is 1K and watermarked; img.watermarked tells you instead of leaving you to guess.
• Free runs queue 25–80 seconds before the model is called, which is why the default deadline is six minutes.
• Video does not run anonymously — the cheapest clip costs more than the grant. The AI video generator has a browser lane for that.

Signing in removes the watermark and opens the full shelf: Nano Banana 2 for up to 14 reference photos, GPT Image 2 for 4K output, Qwen Image 3 when the picture has to contain correctly spelled text, and Seedream 5.0 Pro for photoreal people. Pricing has every tier.

Past the free tier: an API key #

When the free allowance runs out, the error tells you where to go next. Create a key at kavel.ai/settings/apikeys — the same account you use on the site — and pass it (or set KAVEL_API_KEY):

final kavel = Kavel(apiKey: Platform.environment['KAVEL_API_KEY'], model: 'gpt-image-2');

With a key every call runs on your account, exactly as it would on the site: your credits and plan, no per-IP ceiling, no watermark on a paid plan, and any image model your plan includes. KavelErrorKind.auth means the key is wrong; quota with a key means the account is out of credits. Keep keys on your server — a key compiled into an app can be extracted.

Prompts that work #

Name the light, the material and the composition — that moves the result more than adjectives do. For edits, say what changes and the model keeps the rest; it is the same Nano Banana 2 Lite lane behind the AI hairstyle changer and the AI outfit generator. The free AI image generator runs the same engines in a browser, and the showcase has finished output.

Tests #

dart test

Offline, with MockClient: argument validation, client id uniqueness, the quota wall (an HTTP 200 recognised only by a field), the sign-in refusal, and polling through a dropped connection.

More languages and recipes: kavel.readthedocs.io.

MIT