GeminiNano Banana 2 Lite
Nano Banana 2 Lite · Generate
Image / Gemini / Nano Banana 2 Lite / Generate
POST
/v1/images/generationsRequest parameters
Authorization
Add an Authorization header whose value is Bearer followed by your API key.
Authorization: Bearer ****************
Header parameters
Content-TypestringOptional
application/json
AcceptstringOptional
application/json
Body parametersapplication/jsonrequired
modelstringRequired
Model ID, fixed to `gemini-3.1-flash-lite-image`
promptstringRequired
Image description
nintegerOptional
Number of images, default `1`
sizestringOptional
Resolution, e.g. `1024x1024`
qualitystringOptional
Quality tier (when supported by the model)
response_formatstringOptional
Return format. `url` only applies to models that support it (e.g. DALL-E); OpenAI gpt-image always returns `b64_json` and ignores this field.
output_formatstringOptional
Output image encoding (png / jpeg / webp); applies to OpenAI gpt-image models.
output_compressionintegerOptional
Compression level 0–100; only takes effect for jpeg / webp.
backgroundstringOptional
Background type (transparent / opaque / auto); transparent requires png or webp.
moderationstringOptional
Moderation strictness (auto / low); upstream still moderates.
userstringOptional
Optional end-user identifier forwarded upstream for abuse detection.
Example
{ "model": "gemini-3.1-flash-lite-image", "prompt": "A golden retriever running in the snow", "n": 1, "size": "1024x1024", "response_format": "b64_json"}Request code samples
curl https://api.hotrouter.ai/v1/images/generations \ -H "Authorization: Bearer $API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "gemini-3.1-flash-lite-image", "prompt": "A golden retriever running in the snow", "n": 1, "size": "1024x1024", "response_format": "b64_json" }'Response
200 · Success
createdintegerOptional
Creation timestamp (seconds)
dataarray[object]Required
Generated images
Example
{ "created": 1730000000, "data": [ { "b64_json": "<base64>" } ]}