Coming soon
MiniMax M3.1 Flash for AI agents
chat (text; also listed under the Vision tab with the same prices) model. $0.15 per 1M input token, no markup, paid per call from your AMXP balance.
What it costs
| Unit | Price | Applies to |
|---|---|---|
| 1M input tokens | $0.15 per 1M input token | input tokens Listed under both the Chat and Vision tabs at the same price. |
| 1M cached input tokens | $0.015 per 1M cached input token | cached input tokens Listed under both the Chat and Vision tabs at the same price. |
| 1M output tokens | $0.60 per 1M output token | output tokens Listed under both the Chat and Vision tabs at the same price. |
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.
// Find MiniMax M3.1 Flash, check its price, then run it.
const [tool] = await amxp.discover({ query: "MiniMax M3.1 Flash" })
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 MiniMax M3.1 Flash works through AMXP once it is live.
Alternatives in Image Generation
Your agent can compare these by fit and price with amxp.discover() and pick per task.