Generate with one API: images, video, audio

Call Seedream, Wan, Qwen Image, MiniMax Music, and Nano Banana models by their real names through one queue API on Modellane and pay only for what you use.

Featured models

257 models · 17 makers · image, video, and audio

  • Seedream v4.5 — Photorealistic frames, legible text inside the image, and wide aspect ratios.
  • Qwen Image 3.0 Text to Image — Multilingual prompts, Turkish text inside the image, and up to four variations per request.
  • Nano Banana 2 Text to Image — Fast, stylised, figurine-style images; 10 aspect ratios and 4K resolution.
  • Wan-3.0 Text to Video — Single-shot video from text: duration, resolution, aspect ratio, and audio are each chosen separately.
  • Wan-3.0 Image to Video — Sets your uploaded frame in motion as the first frame; duration, resolution, and audio are each chosen separately.
  • MiniMax Music 3.0 — Produces a full-length track, with vocals or instrumental, from a description of genre, mood, and tempo.

Wire it up in code, or generate in the browser.

Both paths share the same catalog and the same balance: connect the API to your product, or try a model right away in the playground.

Build

Call every model by its real name through one queue API; image, video, and audio share the same request shape.

  • One request shape for every model
  • Keys and usage in your dashboard
  • Failed generations are not charged

Start with the API

Create

Pick a model, write your prompt, and see the output on the same page, straight from the browser with no code.

  • Image, video, and audio models
  • See the cost before you run
  • Download outputs within seven days

Try it in the browser

Why Modellane?

You know up front what you call, what you pay, and how long your output stays.

Real model names
Every model is called by its own name, so you always know what runs.
Pay as you go
Each generation is charged by the units it uses; no subscription required, with optional monthly plans.
One queue API
Images, video, and audio share the same request shape.
Outputs kept for 7 days
Download your output within seven days; after that it is deleted.

One API. Every model.

Send the job to the queue by model name, poll its status, and fetch the output. Create your key in the dashboard; the docs give you a working example.

Four stops to get started

From keys to pricing, everything your first request needs is in the docs.

Frequently asked questions

How do I pay?
As you go: each generation's charge comes off your balance. No subscription is required; optional monthly plans add a balance that is spent first.
Which models are available?
Image, video, and audio models; the list and its prices are public.
How long are outputs kept?
Seven days. Download anything you want to keep.
What if a generation fails?
A failed generation is not charged.
Where do I get an API key?
In the dashboard; you can revoke it at any time.