01
Production-ready · v1 API
Moonez.ai — API in. AI out.
Build faster with AI. Scale with API.
Generate high-quality images at scale with one API. Built for teams that need results.
Moonez.ai — AI generation infrastructure for business
27.4 s
Generation time
99.9%
Uptime
HMAC + TLS
Security
< 5 minutes
Quick start
Four steps from request to image
Your customer buys a generation inside your product — UI, bot, marketplace. You set the price.
02
API
A single POST to /v1/generations. Idempotent, async.
03
Gemini
Load-balance across Gemini models, retry, validate.
04
Webhook
HMAC-signed webhook and a presigned S3 URL.
NanoBanana Pro · 1024×1024
Why Moonez.ai for AI-API integration
01
Affordable AI-API pricing
Prepaid model with no hidden markups. You pay only for successful generations; the price depends on model and resolution.
02
Reliable data security
TLS on every channel, HMAC signature on every webhook, presigned URLs with a limited TTL.
03
Fast and scalable
Async stack on FastAPI + ARQ. Thousands of jobs in parallel, 99.9% uptime SLA.
04
Simple integration
One REST endpoint, clear error codes, ready-to-go Python and Node examples. From sign-up to first generation in under five minutes.
05
Transparent billing
Every transaction is recorded as its own row. Live balance, full reserve/charge history, CSV export.
06
One API, many models
Switch between Pro, Flash and Lite models without rewriting client code. A/B experiments, fallback strategies, cost-aware routing.
What we run
Premium
NanoBanana Pro
gemini-3-pro-image
Top quality and detail. For final production assets, marketing and client-facing work.
Balanced
NanoBanana 2
gemini-3.1-flash-image
A balanced option: high quality at a fraction of Pro pricing. Great for everyday tasks and iteration.
Fast
NanoBanana
gemini-2.5-flash-image
The fastest and most affordable model. For prototypes, previews and bulk pipelines.
Video
Gemini Omni
gemini-omni-1.1-flash
Real-time multimodal reasoning: audio and video input with instant responses. Billed per token, works over the same Google-compatible API.
Video
Veo
veo-3.1-generate-001
Cinematic video generation from a text prompt. Async job API, MP4 delivery, duration up to 8 seconds.
Video
Veo Fast
veo-3.1-fast-generate-001
Faster turnaround video generation with the same async job API and per-second billing.
Video
Veo Lite
veo-3.1-lite-generate-001
Lightweight and cost-efficient video generation for high-volume use cases.
Text
Gemini text models
The full Gemini text lineup over a Google-compatible API, billed per token. Same key, same balance, sync and streaming.
- gemini-3-flash-preview
- gemini-3.1-flash-lite
- gemini-3.1-pro-preview
- gemini-3.5-flash
- gemini-3.5-flash-lite
- gemini-3.6-flash
- gemini-3.7-flash
Frequently asked questions
How quickly can I get started?
After signing up you immediately get an API key and a test balance. The first successful generation usually happens within five minutes.
How do payments and balances work?
Prepaid: you top up your balance, the amount is reserved when a job is created, and charged on success. On failure the reserve is returned automatically.
Which payment methods are supported?
Crypto via 0xProcessing (USDT, BTC, ETH and others), bank transfer for teams, custom terms for enterprise.
What happens if the model fails?
We automatically retry up to 10 times with exponential backoff. If every attempt fails — the job is marked as failed, the reserve is returned, and a webhook is delivered with the error status.
Where are generated images stored?
On S3-compatible storage. You receive a presigned URL with a limited TTL — do not cache it; request a fresh one via GET /v1/jobs/{id}.
Can I use my own Gemini API keys?
Yes — for larger customers we run a private key pool with guaranteed throughput.
Why teams choose Moonez.ai
- One REST API for every current Gemini model
- Prepaid balance, transparent transactions, no billing surprises
- 99.9% uptime, async infrastructure, retries out of the box
- HMAC-signed webhooks and presigned URLs with TTL
- Live support and clear documentation in English