AI image and video generation API

One API for the best image and video models. Sub-second image generation, async video with polling, per-request pricing — no GPUs to provision and no cold starts.

  1. 1

    Create an API key in the Developer Dashboard and export it:

    Terminal
    export GETIMG_API_KEY="your-api-key"
  2. 2

    Open Claude Code in your project and send it this prompt:

    Prompt
    Integrate the getimg.ai image and video generation API into this project.

1. Read the docs index at https://docs.getimg.ai/llms.txt, then the
   Quickstart, Models and Generate images / Generate videos guides it links.
2. Use the official SDK for this codebase (getimg-ai on npm, getimg on
   PyPI), or plain HTTP if neither fits.
3. Read the API key from the GETIMG_API_KEY environment variable. Never
   hardcode it or commit it.
4. Pick a model by calling the list models endpoint instead of guessing
   an id.

Pay as you go. No subscription, no minimum spend, and every response reports its exact cost.

34+
Production models
7
Model providers
1M+
Generations daily
2
Endpoints to learn

Image generation API

18 text-to-image models behind one synchronous endpoint — Nano Banana, Seedream, Qwen Image, GPT Image and more. From $0.015 per image.

Compare image models

Video generation API

16 video models for text to video and image to video — Kling, Seedance, Wan, Grok Imagine and more. From $0.022 per second.

Compare video models

Latest models

The most recent additions to the catalog. We add the best models available, not everything that launches.

Browse all models
Nano Banana 2.1
image

Nano Banana 2.1

Fast Gemini image generation and editing up to 4K, with up to 14 reference images.

googlefrom $0.04/image
GPT Image 2.5 Flare
image

GPT Image 2.5 Flare

GPT Image 2.5 Flare image generation and editing with automatic quality.

openaifrom $0.06/image
GPT Image 2.5 Sunburst
image

GPT Image 2.5 Sunburst

GPT Image 2.5 Sunburst image generation and editing with automatic quality.

openaifrom $0.06/image

Built for production

One request format across every model, official SDKs, and limits that scale with you.

One request format

Every image model takes the same body and returns the same shape. Switching model is a one-string change.

Image guide

Async video with polling

Submit a job, poll for status, download the result. Long renders never hold a request open.

Video guide

Official SDKs

First-party Node.js and Python clients, or call the endpoints directly over plain HTTP.

Libraries

Limits that scale

Documented rate limits per endpoint, with headroom that grows alongside your usage.

Rate limits

Transparent by design

Every response includes a usage object showing exactly what the request cost. Consistent parameters, clear documentation, predictable bills.

How billing works
Response
POST /v2/images/generations
{
  "model": "...",
  "prompt": "your image description",
  "aspect_ratio": "16:9",
  "output_format": "jpeg"
}

→ 200 OK
{
  "id": "req-01HXY...",
  "status": "completed",
  "data": [{ "url": "https://..." }],
  "usage": { "total_cost": 0.03 }
}

Pay only for what you use

Per-generation pricing with no subscriptions and no idle GPU costs. Images from $0.015. Video from $0.022 per second.

Browse the model catalog

Every model lists its own per-resolution rates.

Frequently asked questions

What can I build with an image and video generation API?

Add generation to any product — on-demand visuals in design, writing or chat tools, automated imagery for listings and campaigns, or fast prototyping of concepts.

You get production models like Seedream 4, Nano Banana 2 and Kling O3 without running your own GPUs.

How do I get an API key?

Create a project in the Developer Dashboard and generate a key. It is only shown once, so store it securely. Full setup steps are in the authentication guide.

Is this image and video generation API free?

No — the API is a paid, pay-as-you-go product. You are billed per request, with no subscription and no minimum spend, and every response reports its exact cost.

Rates vary by model and resolution. See image model pricing and video model pricing.

How do I use the API?

POST a model id and a prompt. Images return synchronously; video returns a job you poll until it completes. Parameters differ per model — aspect ratios, resolutions, reference images and more.

See the quickstart, model guide and API reference.

Start building with the getimg API

Create a key, add credit and make your first call in minutes.

Get your API key

Or start with the quickstart guide.