Every model,one API key.
Unified Image API turns a prompt into a hosted image over a simple HTTP API — one API key, one balance, and every model billed per credit. Async jobs, exactly-once billing, keys you control.
Per image, at the Scale pack rate. Failed jobs are refunded.
Async jobs with webhooks
Submit a generation, get a job id back instantly, and get notified the moment it finishes — no polling required.
Exactly-once billing
Credits are deducted when a job succeeds. Failed jobs are refunded automatically, every time.
Keys, limits, allowlists
Scope API keys per project with request-per-second limits and CIDR allowlists you control from the dashboard.
Two requests.
One image.
Submit a job, poll for the result. Every response below is real — copy the commands with your key and they run as-is.
Full API reference →01 · Submit the jobt + 0 ms
curl -s -X POST https://api.genmux.tech/v1/generations \ -H "Authorization: Bearer $API_KEY" \ -H "Idempotency-Key: $(uuidgen)" \ -H "Content-Type: application/json" \ -d '{"model":"nanobanana","prompt":"a red fox in snow","resolution":"1K","ratio":"1:1"}'02 · Accepted — you hold the job idt + 41 ms
202 Accepted{ "id": "0d8b6a3e-2f1c-4a5b-9c1d-7e2f3a4b5c6d", "model": "nanobanana", "status": "queued", "cost": 2 }03 · Poll, or wait for the webhookt + 1 s
curl -s https://api.genmux.tech/v1/generations/0d8b6a3e-2f1c-4a5b-9c1d-7e2f3a4b5c6d \ -H "Authorization: Bearer $API_KEY"04 · Done — the image is at the URLt + 52 s
200 OK{ "id": "0d8b6a3e-2f1c-4a5b-9c1d-7e2f3a4b5c6d", "model": "nanobanana", "status": "succeeded", "cost": 2, "images": [{ "url": "https://…/0.png?X-Amz-Expires=900", "width": 1024, "height": 1024 }]}
Models
Every model behind the same request shape and the same key. Prices are credits per image.
Nano Banana API
Xingyang Nano Banana: fast text-to-image and image-to-image at 1K, up to 14 reference images.
from {usd}/image · 2 credits
Pricing, samples and quick start →Nano Banana Pro API
Xingyang Nano Banana Pro: higher fidelity with 1K, 2K and 4K output, up to 14 reference images.
from {usd}/image · 4 credits
Pricing, samples and quick start →Qwen-Image 2.0 API
Qwen-Image 2.0: strong at rendering legible text inside images and at illustration styles, 1K and 2K output.
from {usd}/image · 3 credits
Pricing, samples and quick start →Qwen-Image Max API
Qwen-Image Max: the highest-fidelity Qwen-Image tier for photoreal and text-heavy compositions, 1K and 2K output.
from {usd}/image · 8 credits
Pricing, samples and quick start →Seedream 5.0 API
Seedream 5.0: ByteDance's high-resolution model for photoreal frames and in-image text, 2K and 4K output, takes reference images.
from {usd}/image · 16 credits
Pricing, samples and quick start →Wan 2.7 Image API
Wan 2.7 Image: fast, low-cost text-to-image at 1K and 2K for previews and bulk generation.
from {usd}/image · 2 credits
Pricing, samples and quick start →Simple, credit-based pricing
Buy a credit pack once, spend it as you generate. No subscriptions, no surprise invoices.
How it works
01
Create an API key
Sign up, verify your email, and generate a scoped key from the dashboard.
02
Submit a generation
POST a prompt, a resolution and a ratio to /v1/generations with an Idempotency-Key. Get a job id back in milliseconds.
03
Poll or get webhooked
Poll the job, or configure a webhook, then download the image from the presigned URL.