Gemini Nano synchronous Call
Gemini Nano image models accept synchronous requests in Gemini-compatible format. Common models on the MoonNexAI pricing page include gemini-3.1-flash-image-preview, gemini-3-pro-image-preview, nano-banana-2 and nano-banana-pro. Use a model ID returned by the console, pricing page or GET /v1/models. For long tasks, see Gemini Nano asynchronous requests.
Recommended entrance
http
POST /v1beta/models/{model}:generateContent
POST /v1beta/models/{modelName}:generateContentExample request
bash
curl https://moonnexai.com/v1beta/models/gemini-3.1-flash-image-preview:generateContent \
-H "Authorization: Bearer <MOONNEXAI_API_KEY>" \
-H "Content-Type: application/json" \
-d '{
"contents": [
{
"role": "user",
"parts": [
{
"text": "Generate a clean product mockup on a white studio table."
}
]
}
]
}'Common Models
| Models | Recommended use |
|---|---|
gemini-3.1-flash-image-preview | Gemini image generation, suitable for speed priority image creation. |
gemini-3-pro-image-preview | Gemini image generation, suitable for mass-priority image creation. |
nano-banana-2 | Gemini Nano Image Generation, suitable for the Nano Banana series. |
nano-banana-pro | Gemini Nano image generation, suitable for a higher quality Nano Banana image creation. |
Results-based processing
Gemini-compatible response usually uses candidates[].content.parts[] to return text or picture content. The business side should save the original request, model name and final picture URL or image content to facilitate retesting and tracking.