Live
FLUX.1 [schnell] for AI agents
Fast, cheap images from a prompt: a 1 MP image for a third of a cent. The default for drafts, thumbnails and iteration. $0.0030 per megapixel, no markup, paid per call from your AMXP balance.
What it costs
| Unit | Price | Applies to |
|---|---|---|
| megapixel | $0.0030 per megapixel | Per megapixel of output, times the number of images. A 1024×768 image is 0.79 MP. |
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 flux-schnell/text-to-image. Output: image, typically 2–8 s. $0.0030 per megapixel; Per megapixel of output, times the number of images. A 1024×768 image is 0.79 MP.
| Name | Type | Description |
|---|---|---|
prompt required | string | What the image shows. Subject, style, lighting, composition. |
image_size | square_hd · square · portrait_4_3 · portrait_16_9 · landscape_4_3 · landscape_16_9 (default landscape_4_3) | Output size. square_hd is 1024×1024 (1.05 MP); landscape_16_9 is 1024×576 (0.59 MP). |
num_images | integer (default 1) | How many images. Each is billed. |
num_inference_steps | integer (default 4) | |
seed | integer | Fix for repeatable results. |
output_format | jpeg · png (default jpeg) | File format. |
How to call it
Callable now from the API, the MCP server and the console.
// FLUX.1 [schnell]: check the price, then run it.
const spec = await amxp.inspect("flux-schnell/text-to-image") // parameters and price per megapixel
const result = await amxp.execute("flux-schnell/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.