Model catalog
Moonez.ai supports 25 models: five image models, nine text models, three Veo video models, five music models, two embedding models, and Gemini Omni. The latest additions are Nano Banana 2 Lite, Gemini 3.8 Flash, and Gemini 4 Argon.
Use the exact API IDs below. Access depends on your key’s permissions, your account’s pricing, and provider availability. A model in this catalog is not a guarantee that every provider supports every parameter.
Image models
Section titled “Image models”All five models use POST /api/v1/generations for native asynchronous jobs and
generateContent for Gemini-compatible requests.
Both text-to-image generation and editing with input images are available.
| Model | API ID | Native output sizes | Reference |
|---|---|---|---|
| Nano Banana 2 Lite | gemini-3.1-flash-lite-image | 1K only | Generate · Edit |
| Nano Banana 2.1 | gemini-nano-banana-2.1 | 1K · 2K · 4K | Generate · Edit |
| Nano Banana Pro | gemini-3-pro-image | 1K · 2K · 4K | Generate · Edit |
| Nano Banana 2 | gemini-3.1-flash-image | 1K · 2K · 4K | Generate · Edit |
| Nano Banana | gemini-2.5-flash-image | 1K only | Generate · Edit |
Nano Banana 2 Lite is a separate model, not an alias for Nano Banana 2. It has its own API-key permission and 1K rate. Do not request 2K or 4K with it. Image generation is billed by model and output size; see Resolutions and Aspect ratios.
Text models
Section titled “Text models”These models use the Gemini-compatible generateContent,
streamGenerateContent, and countTokens methods. They also support text
prompts through the native jobs API. Billing uses input and output tokens,
with an independent rate for each model.
| Model | API ID |
|---|---|
| Gemini 4 Argon | gemini-4-argon |
| Gemini 3.8 Flash | gemini-3.8-flash |
| Gemini 3.7 Flash | gemini-3.7-flash |
| Gemini 3.6 Flash | gemini-3.6-flash |
| Gemini 3.5 Flash | gemini-3.5-flash |
| Gemini 3.5 Flash Lite | gemini-3.5-flash-lite |
| Gemini 3.1 Pro Preview | gemini-3.1-pro-preview |
| Gemini 3.1 Flash Lite | gemini-3.1-flash-lite |
| Gemini 3 Flash Preview | gemini-3-flash-preview |
See Text models for cURL examples, including Gemini 4 Argon and Gemini 3.8 Flash, and SDK quickstart for Python. Method and parameter support ultimately depend on the selected provider.
Video models
Section titled “Video models”| Model | API ID |
|---|---|
| Veo 3.1 | veo-3.1-generate-001 |
| Veo 3.1 Fast | veo-3.1-fast-generate-001 |
| Veo 3.1 Lite | veo-3.1-lite-generate-001 |
Veo creates asynchronous video jobs through
POST /api/gemini/v1beta/interactions or POST /api/v1/generations.
It does not use generateContent or appear in Gemini models.list.
Use the video generation reference
for duration, resolution, polling, and per-second billing.
Multimodal model
Section titled “Multimodal model”| Model | API ID |
|---|---|
| Gemini Omni 1.1 Flash | gemini-omni-1.1-flash |
Gemini Omni is available through the Gemini-compatible generateContent
interface and uses token-based billing. Its input and output capabilities
depend on the active provider. It appears under video/multimedia controls in
the dashboard, but it is not a Veo model. Do not use the Veo request body
or assume that a WebSocket Live API is available.
Music models
Section titled “Music models”| Model | API ID | Interface |
|---|---|---|
| Lyria 2 | lyria-002 | predict (Vertex service account) |
| Lyria 3 Clip | lyria-3-clip-preview | interactions (JSON or SSE) |
| Lyria 3 Pro | lyria-3-pro-preview | interactions (JSON or SSE) |
| Lyria 3.5 | lyria-3.5 | interactions (JSON or SSE) |
| Lyria RealTime | lyria-realtime-exp | WebSocket BidiGenerateMusic |
Music requires the separate MUSIC permission and a configured account price.
Ordinary Lyria is billed per completed track; RealTime per second of delivered
audio. No audio means no charge. Music does not use streamGenerateContent;
see the music and live streaming guide.
Embedding models
Section titled “Embedding models”| Model | API ID | Interface |
|---|---|---|
| Gemini Embedding 2 | gemini-embedding-2 | embedContent, batchEmbedContents |
| Gemini Embedding 2 Preview | gemini-embedding-2-preview | embedContent, batchEmbedContents |
Embeddings require the EMBEDDING permission. Both synchronous methods use Google standard input-token rates by modality; output vectors are not billed. See the embeddings guide for requests and billing details.
IDs, aliases, and discovery
Section titled “IDs, aliases, and discovery”The following preview aliases are accepted in addition to their canonical IDs:
| Accepted alias | Canonical ID |
|---|---|
gemini-2.5-flash-image-preview | gemini-2.5-flash-image |
gemini-3.1-flash-image-preview | gemini-3.1-flash-image |
gemini-3-pro-image-preview | gemini-3-pro-image |
Use gemini-3.1-flash-lite-image and gemini-nano-banana-2.1 without adding a
-preview suffix. The preview suffixes in the text-model table are already
part of those models’ canonical IDs.
GET /api/gemini/v1beta/models returns the image, text, music, embedding, and Omni models permitted
by your key. Veo is excluded because it uses a different generation interface.
The retired text IDs gemini-2.5-pro, gemini-2.5-flash, and
gemini-2.5-flash-lite may appear in historical jobs but are not active models.