AdGPT

Free LLM tokens - one native ad per response

Chat
Advertisers
Send a message to start chatting
Responses include one contextually relevant ad
Plan a weekend trip to Hawaii
Best way to learn Python?
Quick healthy dinner ideas
Recommend noise-cancelling headphones

Alpha Airlines

travelbid: 82

Book flights worldwide. 20% off with code FLY20 at alphaairlines.com.

TechGear Pro

technologybid: 77

Studio-quality headphones, 20% off today. techgearpro.com.

CodeMaster

educationbid: 71

Learn to code fast - first lesson free. codemaster.io.

Beta Resort

travelbid: 65

Luxury beachfront stays from $99/night. betaresort.com.

VitaBoost

healthbid: 45

Daily vitamins with free shipping on first order. vitaboost.com.

FreshBite

foodbid: 38

Meal kits delivered - first box free. freshbite.com.

How it works

Implements the generative auction from Zhao et al., "LLM-Auction: Generative Auction towards LLM-Native Advertising" (2025). The full candidate ad set with bids is passed to llama-3.1-8b via Groq. The model selects the most relevant ad and integrates it natively into its response in a single inference call. A first-price payment rule applies. The green debug line shows the auction outcome.

API Usage

The API is OpenAI-compatible. Just point your client at /api/chat with standard messages:

curl -X POST https://your-host/api/chat \
  -H "Content-Type: application/json" \
  -d '{"messages": [{"role": "user", "content": "Plan a trip to Hawaii"}]}'

Response includes the LLM reply with a natively integrated ad, plus an auction object showing which advertiser won and their payment. Works as a drop-in replacement for any OpenAI-style chat endpoint - free tokens, ad-supported.

request logs