Make image
make_imageOne picture from a description in one call, the still twin of make_video: wires the image model, prepares the render and answers like estimate_run_cost: the price, whether the balance covers it, and a quoteId. It does NOT start the render: tell the person the price, and once they accept, call run_pipeline with the returned pipelineId and quoteId (no inputs), then poll get_run; the picture is outputs.image. Pass referenceImageUrls to change or restyle pictures the account already has ("make this render photo real", "same scene at night"): the model works from them and keeps their composition. A local file goes into the library first with create_upload_url and import_media. Needs the pipelines:write scope; the run needs pipelines:run.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"prompt": "<prompt>"
},
"name": "make_image"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| name | No | What to call the render. | |
| model | No | An image model, only when the person asked for one by name. Defaults to Nano Banana (google/gemini-2.5-flash-image). | |
| prompt | Yes | What the picture shows, or for a reference, what to change about it. | |
| aspectRatio | No | The picture's shape. Omit it to let the model choose (a square, or the shape of the reference). | |
| maxPriceUsd | No | The most the person will pay for this picture, if they said. | |
| referenceImageUrls | No | Up to 4 pictures in the account's library (from import_media, list_assets or a run's outputs), copied exactly, for the model to work from. |