Meet the Somnia Agents #2: LLM Inference. LLM Inference is one of the three base Somnia Agents. It allows smart contracts to run a deterministic LLM and receive a consensus-validated answer directly in their callback. The same prompt produces the same output across every validator, turning AI reasoning into an onchain primitive rather than an offchain dependency. Let’s explore how it works and when to use it.

Use LLM Inference when you need reasoning over information you already have. Examples include: - Classification and content moderation - Summarising onchain text - AI-arbitrated escrow and dispute resolution - Prediction market resolution - Structured extraction from provided content Outputs can also be constrained using allowedValues, allowing responses to be limited to a predefined set such as RELEASE, REFUND, or SPLIT. This makes consensus straightforward and onchain integration significantly easier. 2/3

Meet the Somnia Agents #1: LLM Parse Website. LLM Parse Website is one of the three base Somnia Agents. It allows smart contracts to fetch information from live websites and convert it into structured onchain data through validator consensus. This makes it possible to build applications that react to information on the web without relying on centralized backends or traditional oracle infrastructure. Let’s explore how it works and when to use it.

To get started, you’ll need three things: - The agent ID - The platform contract - The execution cost LLM Parse Website uses the same agent ID on both testnet and mainnet. Agent ID: 12875401142070969085 Cost: 0.10 STT/SOMI per validator 5/6