Catch the next
model release.

Returns official releases dated today or in the previous six UTC days. No key, install, or pagination. Select a provider to add a real server-side query filter.

Loading recent releases…

const response = await fetch('https://www.aidatahub.io/api/latest-models');
if (!response.ok) throw new Error(`Latest models: HTTP ${response.status}`);
const { models, status } = await response.json();
if (status !== 'ok') console.warn('A source check is delayed.');
console.log(models);

These examples call /api/latest-models directly. ?provider=anthropic and the other provider IDs in the selector filter at the API. Provider IDs are case-insensitive. Unknown filters return HTTP 400.

Waiting for the feed.

02 / Follow what’s new

Alerts without the noise.

For a no-code option, add our RSS feed to your reader or an RSS-triggered automation. It contains newly detected official releases, excluding initial history and catalog listings.

For reliable alerts, use the full history feed and download the tiny JavaScript client. Poll every 15 minutes. Save the first set of IDs without sending alerts. On later checks, process unseen official releases whose baseline is false.

import { FEED_URL, findNewReleases } from './model-releases-client-v1.mjs';

// Your app supplies durable storage and notification delivery.
const savedIds = await loadSeenIds(); // null on first run; otherwise string[]
const response = await fetch(FEED_URL, { signal: AbortSignal.timeout(15000) });
if (!response.ok) throw new Error('Feed request failed');
const { releases, seenIds } = findNewReleases(await response.json(), savedIds);
for (const release of releases) {
  await sendAlert(release); // deduplicate by release.id at your destination
}
await saveSeenIds(seenIds); // save only AFTER successful delivery

This integration outline requires your own loadSeenIds, sendAlert, and saveSeenIds functions. Persist IDs across restarts. A failed delivery must not advance the checkpoint; retries can repeat earlier deliveries, so the destination should also deduplicate by ID. A date cutoff or limited result set can miss delayed releases.

Send the last response’s ETag as If-None-Match on later requests. A 304 has no body: keep your previous data. On errors, retain your checkpoint and retry with backoff. The tiny client uses normal HTTP caching; custom conditional requests belong in your integration.

The simple endpoint returns generatedAt, from, through, provider, status, count, and models. An empty models array means no recognized releases in that period. status: "degraded" means a source check failed; inspect the full feed for details. Check that generatedAt is recent before treating an empty result as complete.

Full history feed

Use /api/model-releases.json for older releases, OpenRouter listings, source health, and alert IDs. It returns the entire archive; query parameters do not filter it.

The response has schemaVersion: 1, generatedAt, initializedAt, pollIntervalSeconds, coverage, sources, and events. Optional links point to these docs, the schema, client, and RSS. Unknown additive fields should be ignored.

Events are ordered by release or listing date, newest first. They are not ordered by detection time. The feed contains the collected archive; it does not paginate.

JavaScript client options

getModelReleases({ provider, type, limit, since, signal }) fetches the feed and returns events, count, total, generatedAt, sources, and stale. HTTP errors and unsupported feeds throw. selectReleases(feed, options) filters an already loaded feed.

• provider: exact name, case-insensitive. Omit for all.
• type: release (default), listing, or all.
• limit: integer 1–1,000; default 10. total counts all matches before this limit.
• since: exclusive cutoff on publishedAt; ISO date or timestamp with timezone. Omit for all dates.
• signal: optional AbortSignal. Default timeout: 15 seconds.

04 / Know the limits

Evidence, with a heartbeat.

Provider marks identify the source organizations. AIDataHub is independent and is not endorsed by these providers.