Coming soon
DeepSeek V3.2 for AI agents
text model. $0.33 per 1M input token, no markup, paid per call from your AMXP balance.
What it costs
| Unit | Price | Applies to |
|---|---|---|
| 1M input tokens | $0.33 per 1M input token | Context 160K; privacy Private |
| 1M output tokens | $0.48 per 1M output token | Context 160K; privacy Private |
| 1M cached input tokens (cache read) | $0.16 per 1M cached input tokens (cache read) | Context 160K; privacy Private |
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 DeepSeek V3.2, check its price, then run it.
const [tool] = await amxp.discover({ query: "DeepSeek V3.2" })
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 DeepSeek V3.2 works through AMXP once it is live.
Alternatives in Models
Your agent can compare these by fit and price with amxp.discover() and pick per task.