# Sorties de modèles IA (Epoch AI, HF, OpenRouter) (`rosmax/ai-model-releases`) Actor

Collecte les sorties récentes de modèles IA depuis Epoch AI (Publication date), Hugging Face (createdAt par orgs), OpenRouter (created). Dédoublonnage par canonical\_model. Filtres sinceDays et organizations.

- **URL**: https://apify.com/rosmax/ai-model-releases.md
- **Developed by:** [Maxime Rosito](https://apify.com/rosmax) (community)
- **Categories:** AI, News
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $1.50 / 1,000 enregistrements

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## Sorties de modèles IA

### Description

Collecte les sorties récentes de modèles d'intelligence artificielle depuis trois sources :

- **Epoch AI** : CSV all\_ai\_models.csv (CC BY) avec Publication date
- **Hugging Face** : createdAt par organisations suivies
- **OpenRouter** : champ `created` (epoch seconds)

### Dédoublonnage

Les modèles sont dédoublonnés par `canonical_model` (nom normalisé). Si un même modèle apparaît dans plusieurs sources, seule la première occurrence est conservée.

### Différenciation : détection des nouvelles sorties

- **Mode changes** : Ne renvoie que les modèles sortis depuis le dernier run
- **Filtres temporels** : `sinceDays` pour limiter aux sorties récentes
- **Filtres organisations** : Surveiller des orgs spécifiques sur HuggingFace

### Exemples

#### Input (mode changes)

```json
{
  "mode": "changes",
  "sources": ["epoch", "huggingface", "openrouter"],
  "sinceDays": 30,
  "organizations": ["meta-llama", "mistralai", "anthropic"],
  "maxItems": 100,
  "historyStoreName": "ai-model-releases-history"
}
```

#### Output (nouvelle sortie)

```json
{
  "record_type": "change",
  "source": "epoch",
  "observed_at": "2026-09-25T06:00:00.000Z",
  "previous_observed_at": "2026-09-24T06:00:00.000Z",
  "change_type": "new_release",
  "release_key": "epoch:llama-3-3-70b",
  "model_name": "Llama 3.3 70B",
  "canonical_model": "llama-3-3-70b",
  "organization": "Meta",
  "release_date": "2026-09-20",
  "parameters": "70B",
  "attribution": "Epoch AI (CC BY)"
}
```

### Planification hebdomadaire

Pour surveiller les nouvelles sorties chaque semaine :

```
Schedules → Add schedule
- Time: Monday 08:00 UTC
- Run input: {"mode":"changes","sources":["epoch","huggingface","openrouter"],"sinceDays":7,"maxItems":100}
```

Le mode `changes` ne renvoie que les nouveaux modèles sortis depuis le dernier run.

### Sources et licences

- **Epoch AI** : https://epoch.ai/data/all\_ai\_models.csv
  - Licence : **CC BY 4.0** (attribution requise)
  - Chaque item inclut automatiquement `attribution: "Epoch AI (CC BY)"`

- **Hugging Face** : API publique (https://huggingface.co/api/models), sans clé

- **OpenRouter** : API publique `/api/v1/models` (https://openrouter.ai/api/v1/models)

### Tarification pay-per-event suggérée

- **Événement `record`** : 0,0001 $ par enregistrement
- **Événement `change-detected`** : 0,001 $ par nouvelle sortie

### Limites

- **Dédoublonnage simple** : Basé uniquement sur le nom canonicalisé, peut rater des variantes
- **Epoch AI** : CSV volumineux (~6-7 MB), peut prendre quelques secondes à télécharger
- **HF par orgs** : Limité à 50 modèles par organisation (API limit)
- **Pas de métadonnées complètes** : Seules les infos de base (nom, org, date) sont normalisées

# Actor input Schema

## `mode` (type: `string`):

snapshot = toutes les sorties récentes ; changes = nouvelles sorties depuis dernier run

## `sources` (type: `array`):

Sources à interroger

## `sinceDays` (type: `integer`):

Ne collecter que les modèles sortis dans les N derniers jours (0 = tous)

## `organizations` (type: `array`):

Liste d'organisations pour filtrer les sorties HF (vide = liste par défaut)

## `maxItems` (type: `integer`):

Limite stricte du nombre d'enregistrements à produire

## `historyStoreName` (type: `string`):

Nom du store pour conserver l'historique entre runs

## `emitBaselineOnFirstRun` (type: `boolean`):

Au premier run en mode changes, émettre tous les items marqués is\_baseline=true

## `snapshotRetention` (type: `integer`):

Nombre de relevés datés à garder dans l'historique (0 = désactivé)

## `webhookUrl` (type: `string`):

URL optionnelle pour recevoir un POST JSON avec le résumé des nouvelles sorties

## Actor input object example

```json
{
  "mode": "changes",
  "sources": [
    "epoch",
    "huggingface",
    "openrouter"
  ],
  "sinceDays": 90,
  "organizations": [
    "meta-llama",
    "mistralai",
    "Qwen",
    "google",
    "deepseek-ai",
    "microsoft",
    "openai",
    "nvidia",
    "black-forest-labs",
    "anthropic"
  ],
  "maxItems": 1000,
  "historyStoreName": "ai-model-releases-history",
  "emitBaselineOnFirstRun": true,
  "snapshotRetention": 7,
  "webhookUrl": ""
}
```

# Actor output Schema

## `results` (type: `string`):

Lien vers les items du dataset (sorties de modèles détectées)

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {};

// Run the Actor and wait for it to finish
const run = await client.actor("rosmax/ai-model-releases").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {}

# Run the Actor and wait for it to finish
run = client.actor("rosmax/ai-model-releases").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{}' |
apify call rosmax/ai-model-releases --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,rosmax/ai-model-releases"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/PWnmJ5EByXCnDN41X/builds/RcJda2VwotDd7XJxJ/openapi.json