IMG.LY AI Gateway

Add AI models to your editor. Without another SDK, vendor or invoice.

Image , video , text , and voice — today’s flagship models, kept current for you. Fully managed, ready to drop into any editor or automation built on IMG.LY SDK.

  • Image, video, text & voice models
  • Fully managed, failover handled
  • Built for IMG.LY SDK
Read the docs Get started
  • Photo Editor
  • Video Editor
  • Design Editor
  • Print Editor
  • AI Editor
  • Photo Editor
  • Video Editor
  • Design Editor
  • Print Editor
  • AI Editor
  • Photo Editor
  • Video Editor
  • Design Editor
  • Print Editor
  • AI Editor
AI Gateway
Flux 2 → AI Editor
  • Nano Banana 2
  • Flux 2
  • v4.1 Vector
  • GPT Image 2.5
  • Seedream 5 Pro
  • v4
  • v4.1
  • Seedream 5 Lite
  • GPT Image 2
  • GPT Image 2.5 Sunburst
  • Qwen Image 2
  • Flux 2 Edit
  • Nano Banana Pro Edit
  • Seedream 5 Pro Layerize
  • GPT Image 2.5 Edit
  • seedvr2 Upscale
  • Flux 2 Pro Edit
  • Qwen Image 3 Edit
  • Nano Banana 2 Lite Edit
  • GPT Image 2.5 Sunburst Edit
  • Flux 2 Max Edit
  • Qwen Image 2 Pro Edit
  • Scribe v2
  • h3 Max I2V
  • Veo 3.1 Lite I2V
  • Seedance 2.5 I2V
  • Veo 3.1 Lite
  • v3 Pro
  • Claude Opus 4.6
  • GPT 5.4
  • Gemini 3.1 Pro Preview
  • Nano Banana Pro
  • Flux 2 Pro
  • Z Image Turbo
  • Flux 2 Klein 9b
  • Nano Banana 2 Lite
  • Seedream 4.5
  • Flux Schnell
  • v3
  • Flux 2 Max
  • v4.1 Pro Vector
  • Flux Dev
  • Nano Banana 2 Edit
  • Rmbg 2.0
  • Crisp Upscale
  • Seedream 4.5 Edit
  • v3 Fill
  • Seedream 5 Pro Edit
  • GPT Image 2 Edit
  • Seedream 5 Lite Edit
  • Flux 2 Klein 9b Edit
  • Flux 3 Edit
  • Eleven v3 TTS
  • Veo 3.1 Fast I2V
  • v3 Pro I2V
  • h3 Max Turbo I2V
  • Veo 3.1 Fast
  • h3 Max
  • h3 Max Turbo
  • Claude Sonnet 4.6
  • GPT 5.4 Mini
  • Gemini 3 Flash Preview

Trusted by teams at 600+ creative product companies

IMG.LY powers creative products at HP, Shopify, Reuters, Hootsuite, Shutterfly and hundreds more.

Digitas
Omneky
The Print Bar
Brandwatch
Planoly
HP
Shopify
Reuters
Hootsuite
Semrush
Shutterfly
one.com
Sprout Social
Constant Contact
Spread Group

One plugin. One invoice. Zero rewrites when models change.

Three shortcuts only AI Gateway can deliver, because it ships inside IMG.LY SDK, not next to it.

Same SDK you already use. 
import CreativeEditorSDK from '@cesdk/cesdk-js';
import ImageGeneration from '@imgly/plugin-ai-image-generation-web';
import { GatewayProvider as ImageGatewayProvider } from '@imgly/plugin-ai-image-generation-web/gateway';

const cesdk = await CreativeEditorSDK.create('#editor', { license: 'YOUR_LICENSE' });

cesdk.actions.register('ly.img.ai.getToken', async () => {
  const res = await fetch('/api/ai/token', { method: 'POST' });
  const { token } = await res.json();
  return token;
});

await cesdk.addPlugin(
  ImageGeneration({
    providers: {
      text2image: ImageGatewayProvider('bfl/flux-2', { debug: true }),
    },
  }),
);
IMG.LY editor with a generated variant landing in a layer
I

Built for IMG.LY SDK.

AI Gateway plugs into the same SDK your team already uses, speaks the same scene model, and drops into the same UI flows.

A sprint of integration becomes an afternoon.
II

SDK, AI, and billing in one dashboard.

No second vendor portal, no second invoice.

API keys, usage, and per-project cost tracking sit next to your SDK license — one source of truth for finance and engineering.
III

We manage the model churn.

New flagship models, deprecations, and upstream outages never reach your code.

You stay on one stable API; we keep what’s behind it current, compatible, and routed around trouble.

Built for the teams already building creative products on IMG.LY.

Every use case IMG.LY SDK already powers, now backed by AI models.

Marketing & ad generation.

Generate on-brand creatives at scale inside a template-driven editor.

E-commerce product imagery.

Swap backgrounds, generate lifestyle shots, and keep products consistent.

Web-to-print personalization.

Let end users generate custom visuals, then output print-ready PDFs via CE.SDK.

Social media & short video.

Drop gen-AI effects, captions, and variants into a Reels-style editor.

In-editor AI assist.

Add “generate”, “extend”, and “retouch” buttons to any editor built on IMG.LY SDK.

Creative automation.

Batch-generate thousands of asset variants, headlessly, with models swapped per job.

AI models for images, video, text, and voice.

A curated, always-current set of today’s flagship models. Pick by quality, speed, or cost. Switch whenever you want.

Images

Text to Image
Image to Image
Inpainting
Style Transfer

Video

Text to Video
Image to Video

Text

Prompt Expansion
Copy Variants
Smart Editing
Translation

Voice

Text to Speech
Speech to Text

See it running.

This is the IMG.LY editor with AI Gateway wired in. Type a prompt, pick a model, watch it land in your scene.

Try the live AI editor

Minutes, not sprints.

One endpoint. Consistent request/response across every model. Works from your server, your client, or directly inside IMG.LY SDK.

Step 1: Install the generation plugin 
npm install @imgly/plugin-ai-image-generation-web
Step 2: Register the Gateway provider 
import ImageGeneration from '@imgly/plugin-ai-image-generation-web';
import { GatewayProvider as ImageGatewayProvider } from '@imgly/plugin-ai-image-generation-web/gateway';

cesdk.actions.register('ly.img.ai.getToken', async () => {
  const res = await fetch('/api/ai/token', { method: 'POST' });
  const { token } = await res.json();
  return token;
});

await cesdk.addPlugin(
  ImageGeneration({
    providers: {
      text2image: ImageGatewayProvider('bfl/flux-2', { debug: true }),
    },
  }),
);
Step 1: Set your API key 
export IMGLY_API_KEY="your-key-here"
Step 2: Mint a short-lived token 
curl -X POST https://gateway.img.ly/v1/tokens \
  -H "Authorization: Bearer $IMGLY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"sub":"user-123"}'
Step 1: Install Express 
npm install express
Step 2: Mint tokens for the editor 
app.post('/api/ai/token', async (req, res) => {
  const response = await fetch('https://gateway.img.ly/v1/tokens', {
    method: 'POST',
    headers: {
      Authorization: `Bearer ${process.env.IMGLY_API_KEY}`,
      'Content-Type': 'application/json',
    },
    body: JSON.stringify({ sub: req.user?.id }),
  });
  const { token } = await response.json();
  res.json({ token });
});
Read API Docs
Read API Docs
Read API Docs

Pricing that gets cheaper as we get bigger.

Pay only for what you use. Every model is priced per request, per image, or per second of output, the same units you’d see upstream. The more volume AI Gateway handles across our customer base, the better our upstream terms get, and the better your pricing gets. Live per-model pricing is public.

  • Nano Banana 2Text → Image $0.080 /req
  • Flux 2 ProText → Image $0.033 /req
  • GPT Image 2.5Text → Image $0.035 /req
  • Nano Banana 2 LiteText → Image $0.044 /req
  • v4.1Text → Image $0.035 /req
  • v3Text → Image $0.072 /req
  • GPT Image 2.5 SunburstText → Image $0.031 /req
  • Flux DevText → Image $0.025 /req
  • Nano Banana Pro EditImage → Image $0.159 /req
  • Crisp UpscaleImage → Image $0.0040 /req
  • seedvr2 UpscaleImage → Image $0.0067 /req
  • Seedream 5 Pro EditImage → Image $0.139 /req
  • Nano Banana 2 Lite EditImage → Image $0.050 /req
  • Flux 2 Klein 9b EditImage → Image $0.025 /req
  • Qwen Image 2 Pro EditImage → Image $0.075 /req
  • Veo 3.1 Fast I2VImage → Video $1.49 /req
  • Veo 3.1 Lite I2VImage → Video $0.349 /req
  • Veo 3.1 FastText → Video $1.46 /req
  • v3 ProText → Video $1.34 /req
  • Claude Sonnet 4.6Text → Text $0.00126 /req
  • Gemini 3.1 Pro PreviewText → Text $0.00095 /req
  • Nano Banana ProText → Image $0.180 /req
  • v4.1 VectorText → Image $0.082 /req
  • Flux 2 Klein 9bText → Image $0.0069 /req
  • v4Text → Image $0.013 /req
  • Flux SchnellText → Image $0.0032 /req
  • GPT Image 2Text → Image $0.258 /req
  • v4.1 Pro VectorText → Image $0.307 /req
  • Flux 2 EditImage → Image $0.030 /req
  • Rmbg 2.0Image → Image $0.019 /req
  • GPT Image 2.5 EditImage → Image $0.062 /req
  • v3 FillImage → Image $0.076 /req
  • Qwen Image 3 EditImage → Image $0.058 /req
  • Seedream 5 Lite EditImage → Image $0.042 /req
  • Flux 2 Max EditImage → Image $0.282 /req
  • Eleven v3 TTSText → Speech $0.017 /req
  • h3 Max I2VImage → Video $0.390 /req
  • h3 Max Turbo I2VImage → Video $0.129 /req
  • Veo 3.1 LiteText → Video $0.386 /req
  • h3 Max TurboText → Video $0.120 /req
  • GPT 5.4Text → Text $0.00119 /req
  • Gemini 3 Flash PreviewText → Text $0.00024 /req
  • Flux 2Text → Image $0.015 /req
  • Z Image TurboText → Image $0.0050 /req
  • Seedream 5 ProText → Image $0.101 /req
  • Seedream 4.5Text → Image $0.047 /req
  • Seedream 5 LiteText → Image $0.038 /req
  • Flux 2 MaxText → Image $0.098 /req
  • Qwen Image 2Text → Image $0.042 /req
  • Nano Banana 2 EditImage → Image $0.084 /req
  • Seedream 5 Pro LayerizeImage → Image $0.342 /req
  • Seedream 4.5 EditImage → Image $0.048 /req
  • Flux 2 Pro EditImage → Image $0.075 /req
  • GPT Image 2 EditImage → Image $0.216 /req
  • GPT Image 2.5 Sunburst EditImage → Image $0.033 /req
  • Flux 3 EditImage → Image $0.096 /req
  • Scribe v2Speech → Text $0.019 /req
  • v3 Pro I2VImage → Video $0.722 /req
  • Seedance 2.5 I2VImage → Video $3.50 /req
  • h3 MaxText → Video $0.420 /req
  • Claude Opus 4.6Text → Text $0.00210 /req
  • GPT 5.4 MiniText → Text $0.00036 /req

Average cost per request over the last 30 days. See full per-model pricing →

Get in touch

Add generative AI to your editor today.

Sign up for the IMG.LY dashboard, grab an API key, and start generating with any model on the gateway.

Get started Read the docs

Frequently Asked Questions

AI Gateway is built for IMG.LY SDK customers and is tightly integrated with the editor. You can call it as a standalone API, but the fit is strongest when paired with the SDK. Talk to us if you're evaluating both.

A curated set of image, video, text, and voice models. Today's flagships, refreshed as new ones ship. See the full live list in the dashboard.

We partner with best-in-class inference providers and manage the plumbing — routing, upgrades, deprecations, and failover. You call one stable API.

Usage-based. Priced per request, per image, or per second of output depending on the model, with no hidden fees beyond published rates. Live pricing in the dashboard.

Content is forwarded to the selected upstream provider to serve your request. We do not retain content beyond what's needed for delivery and billing. Data handling details are in our documentation.

SLAs are available on request for enterprise customers. AI Gateway has automatic failover where upstream redundancy exists.

Sign up, grab an API key, and try a model — or open the demo editor to see AI Gateway wired into IMG.LY SDK.