Coming soon
Gemini Embedding 2 Preview for AI agents
embedding model. $0.25 per 1M input token, no markup, paid per call from your AMXP balance.
What it costs
| Unit | Price | Applies to |
|---|---|---|
| 1M input tokens | $0.25 per 1M input token | Privacy Anonymized |
| 1M output tokens | $0.25 per 1M output token | Privacy Anonymized |
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 Gemini Embedding 2 Preview, check its price, then run it.
const [tool] = await amxp.discover({ query: "Gemini Embedding 2 Preview" })
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 Gemini Embedding 2 Preview works through AMXP once it is live.
Alternatives in Embeddings
Your agent can compare these by fit and price with amxp.discover() and pick per task.