# Experiential Labs

Experiential Labs est une passerelle d’IA open source qui fournit aux équipes un point de terminaison et une clé API uniques pour les modèles hébergés, les clés appartenant aux clients et les modèles locaux ou personnalisés. Elle ajoute aussi le routage, la gestion des budgets, le contrôle d’accès, l’attribution et des fonctions d’intelligence facultatives pour le trafic des agents.

- Findings24: <https://findings24.com/fr/tools/experiential-labs>
- Site web: <https://www.experientiallabs.ai>
- Tarifs: Freemium
- Catégories: Outils Dev IA

## Qu'est-ce que Experiential Labs ?

Experiential Labs is an open source AI gateway for routing model traffic through one OpenAI-compatible endpoint. It lets teams point agents and applications at a single API while using hosted providers, their own provider keys, or local and custom models behind the same interface.

The product is designed to centralize key management, usage controls, and attribution across model calls. Its core gateway is free and open source to self-host, while the hosted service adds managed routing, org controls, and an intelligence layer that can suggest cheaper or faster routes, improve cache hit rate, and support a model trained on a team’s traffic.

## Que peut faire Experiential Labs ?

### OpenAI-compatible gateway endpoint

Exposes a single \`/v1\` endpoint with streaming support so existing clients can connect without changing their basic API shape.

### Provider routing and failover

Routes requests across hosted providers, cloud hosts, pooled accounts, customer keys, and local models, with failover on capacity or provider errors.

### Budgets and model allowlists

Enforces hard caps, model allowlists, and request-level policies at the gateway so limits apply on every call.

### Usage tracking and attribution

Provides logs and dashboards for spend, requests, token counts, TTFT, and usage broken down by agent, person, model, or day.

### BYOK and local models

Supports bringing your own provider keys and, on higher plans, routing to local and custom models through the same endpoint.

### Intelligence layer

Offers per-prompt model optimization, caching suggestions, prompt compression guidance, and an opt-in model trained on the team’s traffic.

## Cas d'utilisation

### Centralizing model access for a team

Teams that use multiple model providers can give agents and developers one endpoint, one login, and one place to manage keys and policies.

### Keeping spend under control

Admins can set caps, route by budget, and inspect usage by key, person, agent, or day to understand where costs are coming from.

### Improving agent routing

Product and engineering teams can use the intelligence layer to route simple prompts to cheaper models and harder prompts to stronger ones.

### Supporting self-hosted or local inference

Organizations that want to run the gateway on their own infrastructure can self-host the open source core and route to local models behind the same API.

### Auditing request behavior

Teams that need recordkeeping can review request logs with route, token, fallback, and cost data for individual calls.

## Questions fréquentes

### How does pricing work?

Pricing is credit-based. Routed tokens spend credits at the provider’s list price with no markup, and intelligence features also consume credits. The site offers a Free plan, a Pro plan, and Enterprise with custom committed credits.

### Can I bring my own provider keys?

Yes. The site says BYOK is supported, and routed traffic can use your own provider keys first.

### Can I self-host the gateway?

Yes. The core gateway is open source and can be run on your own infrastructure.

### Does the gateway support access controls?

Yes. The site mentions budgets, allowlists, RBAC, org-wide policies, and API key management.

### What does the intelligence layer do?

It can suggest optimal model routing, identify caching opportunities, and support an opt-in model trained on your traffic.

## Informations rapides

- **Category**: Developer Tool
- **Product type**: Open source AI gateway
- **Primary users**: Teams and agents routing calls across multiple model providers
- **Deployment**: Hosted service or self-hosted on your infrastructure
- **API style**: OpenAI-compatible \`/v1\` endpoint
- **Source domain**: experientiallabs.ai