AI image, video, audio and 3D generation
Seedream V5.0 Pro
Seedream 5.0 Pro API Preview is ByteDance's advanced image generation model for text-to-image and reference-image generation.
Top models, one balance
Text to image, image to video, image to 3D, text to speech and more, from leading labs, priced per result.

- 01GPT Image 2.6 Flare Text-to-ImageOpenAIImages from text4Kfrom€0.10per image
- 02GPT Image 2.6 Sunburst EditOpenAIImage editing4Kfrom€0.13per image
- 03Nano Banana 2.1 Text-to-ImageGoogleImages from text4Kfrom€0.08per image
- 04GPT Image 2.5 Flare Text-to-ImageOpenAIImages from text4Kfrom€0.05per image
- 05GPT Image 2.5 Sunburst Text-to-ImageOpenAIImages from text4Kfrom€0.05per image
- 06Seedance 2.5 Talking AvatarBytedanceTalking avatarsPortraitsfrom€0.44per clip
- 07Wan 3.0 Prime Text-to-VideoAlibabaVideo from textfrom€0.30per clip
- 08Wan 3.0 Reference-to-VideoAlibabafrom€0.60per clip
- 09Kling V4.0 Image-to-VideoKwaivgiAnimating imagesfrom€0.32per clip
- 10Kling V4.0 Flash Text-to-VideoKwaivgiVideo from textfrom€0.19per clip
- 11Seedream V5.0 Pro EditBytedanceImage editingfrom€0.09per image
- 12Seedream V5.0 Flash EditBytedanceImage editingfrom€0.06per image
Built for
developers
One API for every model. Call it from Node, Python or curl, or script it from the terminal with the Genlaxy CLI.
npm i -g genlaxy1import { writeFile } from "node:fs/promises";2 3const API = "https://genlaxy.ai/api/v1/api/catalog";4const auth = { Authorization: `Bearer ${process.env.GENLAXY_API_KEY}` };5 6// 1. Generate an image7const res = await fetch(`${API}/generations`, {8 method: "POST",9 headers: { ...auth, "Content-Type": "application/json", "Idempotency-Key": crypto.randomUUID() },10 body: JSON.stringify({11 modelId: "luma/uni-v1/text-to-image",12 inputs: { prompt: "Neon city street after rain, cinematic night", size: "16:9" },13 }),14});15let { generation } = await res.json();16 17// 2. Wait for the result18while (generation.status === "queued" || generation.status === "generating") {19 await new Promise((r) => setTimeout(r, 3000));20 ({ generation } = await (await fetch(`${API}/generations/${generation.id}`, { headers: auth })).json());21}22 23// 3. Save the file24const file = await fetch(`${API}/generations/${generation.id}/content`, { headers: auth });25await writeFile("result.jpeg", Buffer.from(await file.arrayBuffer()));genlaxy run google/gemini-omni-flash/text-to-video -p "$PROMPT" --duration 5 -o ./shots/genlaxy run luma/uni-v1/text-to-image -p "..." --json -o ./out/ | jq -r .filegenlaxy skill installNo plans.
Just top up
Add funds from €3 and pay only for what you render. Unused balance stays on your account.
No restriction on commercial use. A render that fails is not charged.
How does pricing work?
You top up a euro balance, from €3, and each render is paid from it. The composer shows the exact price before you press Generate; nothing is charged for a render that fails.
Is there a subscription?
No. There is no monthly fee and no plan to cancel. Your balance stays on your account until you use it.
How do I pay?
With PayPal (which also takes cards) or with crypto (USDC or USDT) on the networks shown at checkout. The balance is credited as soon as the payment is confirmed.
Can I use what I generate?
Yes. We claim no ownership of what you generate and place no restriction on commercial use. Whether an output is protected by copyright depends on the law where you are - the license page explains.
Who is responsible for the output?
Images and clips are produced automatically by AI models. Genlaxy does not control or review what a model generates and is not responsible for it; you decide how to use a result and whether that use is lawful where you are.
Can I turn a still into a clip?
Yes. Any image in your feed or library has an Animate action that uses it as the first frame of a video.
Is there an API?
Yes. Create a key in Settings and call the same models from your own code, paid from the same balance.
Three ways to work
Draft mood boards on a fast image model, then finish the hero frame on a sharper one, from one balance and one tab.
Chain image to video to 3D in one script with the CLI, and read each render's price from the same JSON log.
No subscription to forget. Top up from €3 when a client job comes in and see the exact price before every render.




