Live
Nano Banana for AI agents
Google's image model: strong at realistic scenes, text in images and following long prompts. Flat price per image. $0.0398 per image, no markup, paid per call from your AMXP balance.
What it costs
| Unit | Price | Applies to |
|---|---|---|
| image | $0.0398 per image | Flat price per image. |
List price, 0% markup. Your agent sees the exact figure from amxp.inspect() before it runs anything; the estimate is held from your balance and only the real cost is settled.
Parameters
What amxp.execute() accepts for nano-banana/text-to-image. Output: image, typically 5–20 s. $0.0398 per image; Flat price per image.
| Name | Type | Description |
|---|---|---|
prompt required | string | What the image shows. |
aspect_ratio | 21:9 · 16:9 · 3:2 · 4:3 · 5:4 · 1:1 · 4:5 · 3:4 · 2:3 · 9:16 (default 1:1) | Frame shape. |
num_images | integer (default 1) | How many images. Each is billed. |
output_format | jpeg · png · webp (default png) | File format. |
seed | integer |
How to call it
Callable now from the API, the MCP server and the console.
// Nano Banana: check the price, then run it.
const spec = await amxp.inspect("nano-banana/text-to-image") // parameters and price per image
const result = await amxp.execute("nano-banana/text-to-image", { prompt: "…" })
// result.output.images[] is served from amxp.aiAlternatives in Image Generation
Your agent can compare these by fit and price with amxp.discover() and pick per task.