Coming soon

GPT Image 2.5 Sunburst for AI agents

image edit model. $0.08 per edit, no markup, paid per call from your AMXP balance.

What it costs

UnitPriceApplies to
edit$0.08 per edit1K output resolution; includes the first input image
edit$0.15 per edit2K output resolution; includes the first input image
edit$0.24 per edit4K output resolution; includes the first input image
additional input image$0.00966 per additional input imageCharged for each input image beyond the first, on top of the per-edit price
edit$0.04 per editQuality low, 1K output resolution; includes the first input image
edit$0.04 per editQuality low, 2K output resolution; includes the first input image
edit$0.05 per editQuality low, 4K output resolution; includes the first input image
edit$0.04 per editQuality medium, 1K output resolution; includes the first input image
edit$0.06 per editQuality medium, 2K output resolution; includes the first input image
edit$0.08 per editQuality medium, 4K output resolution; includes the first input image
edit$0.08 per editQuality high, 1K output resolution; includes the first input image
edit$0.15 per editQuality high, 2K output resolution; includes the first input image
edit$0.24 per editQuality high, 4K output resolution; includes the first input 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.

How to call it

The same three calls work for every tool. Your agent does this on its own once AMXP is installed.

agent.ts
// Find GPT Image 2.5 Sunburst, check its price, then run it.
const [tool] = await amxp.discover({ query: "GPT Image 2.5 Sunburst" })
const spec   = await amxp.inspect(tool.id)      // parameters, price per call
const result = await amxp.execute(tool.id, { /* params from spec */ })

Connector in progress. This page describes how GPT Image 2.5 Sunburst works through AMXP once it is live.

Alternatives in Image Enhancement

Your agent can compare these by fit and price with amxp.discover() and pick per task.