Endpoints

Asks one configured model server what it serves. There is no built-in list and no fallback: what a server offers is knowable only by asking it, so an empty answer is the honest report that we could not.

curl "$SANDBOX/endpoints/a1b2c3d4/models" \
  -H "x-intentic-control: $INTENTIC_TOKEN"

import { sandbox } from "@intentic/sandbox-client";

const result = await sandbox.endpoints.models({
  "id": "a1b2c3d4"
});

The allowance, what has been used, when it resets, and which model actually answered the last message. Not being available is the ordinary answer rather than a failure: most sandboxes run against a platform that offers no trial at all.

curl "$SANDBOX/endpoints/trial/status" \
  -H "x-intentic-control: $INTENTIC_TOKEN"

import { sandbox } from "@intentic/sandbox-client";

const result = await sandbox.endpoints.trial();

The memory this sandbox may use, whether a GPU reached it, and every curated model priced two ways: whether it fits on one device's free memory and so runs at full speed, and whether it can load at all. The two the connect view offers, one that downloads in a minute and the best this machine runs at full speed, come from the first; a start is refused only on the second.

curl "$SANDBOX/endpoints/local-model/fit" \
  -H "x-intentic-control: $INTENTIC_TOKEN"

import { sandbox } from "@intentic/sandbox-client";

const result = await sandbox.endpoints.localModelFit();

Downloads the curated instant model into the workspace cache so that adding it later costs nothing. Stopping leaves the part file, so a later start resumes from where this one stopped rather than beginning again.

curl -X POST "$SANDBOX/endpoints/local-model/prefetch" \
  -H "x-intentic-control: $INTENTIC_TOKEN" \
  -H "content-type: application/json" \
  -d '{"action":"start"}'

import { sandbox } from "@intentic/sandbox-client";

const result = await sandbox.endpoints.localModelPrefetch({
  "action": "start"
});