Introduction

Moonez.ai exposes two APIs with one API key and one balance:

• Image generation — three Gemini image models, each with text-to-image and image-to-image modes.
• Text generation — Gemini text models billed per token, served over a Google-compatible API you can call with the official google-genai SDK.
• Video generation — Veo (short MP4 videos from a text prompt, async job API) and Gemini Omni (multimodal real-time, audio/video input). Both are managed in the video category.

Base URL

All endpoints are served under:

https://api.moonez.ai/api/v1

How it works

All image generation requests are asynchronous. A successful call returns 202 Accepted with a job_id and a status_url. You then poll GET /jobs/{job_id} until the job reaches a terminal state (done or failed).

Text requests use the Gemini wire format and return the result inline — no jobs, no polling. See the Gemini-compatible API.

1. Create a job

   POST to a generation endpoint with your prompt and parameters. You receive a job_id.

2. Poll for the result

   GET /jobs/{job_id} until status is done or failed.

3. Download the image

   When done, read result.image_url — a presigned URL valid for 1 hour.

Tip

Prefer push over poll? Register a webhook and we'll call you when a job finishes.

Tip

Need text, or a synchronous call that returns the result inline? Use the Gemini-compatible API with Google's official google-genai SDK — same key, no polling.

Models at a glance

Image models

Model	Resolution	Text-to-image	Image-to-image (URLs)
gemini-2.5-flash-image	1K only	POST /nb/text-generations	POST /nb/url-generations
gemini-3.1-flash-image	1K · 2K · 4K	POST /nb2/text-generations	POST /nb2/url-generations
gemini-3-pro-image	1K · 2K · 4K	POST /text-generations	POST /url-generations

Text models (Gemini)

Seven Gemini text models, billed per token, served over a Google-compatible API:

Model	Notes
gemini-3-flash-preview	Preview
gemini-3.1-flash-lite	Latest lite
gemini-3.1-pro-preview	Preview pro
gemini-3.5-flash	Current fast line
gemini-3.5-flash-lite	Current lite
gemini-3.6-flash	Latest flash
gemini-3.7-flash	Latest flash

Video models (Veo & Omni)

Model	Endpoint	Notes
veo-3.1-generate-001	POST /api/gemini/v1beta/interactions	MP4, 1–8 s, billed per second (720p/1080p/4K rates)
gemini-omni-1.1-flash	POST /api/gemini/v1beta/models/{model}:generateContent	Multimodal real-time, billed per 1M tokens (input / text-out / video-out)

See Video generation for the request format and billing details.

Call them with the official Google SDK by pointing base_url at https://api.moonez.ai/api/gemini — see Text models and the Gemini-compatible API.

Next steps

Quickstart

Create your first generation end-to-end with cURL.

Authentication

Get your API key and learn about idempotency.

Models

Compare the three image models.

Text models

Per-token Gemini text over a Google-compatible API.

API Reference

Full request and response schemas.