Models on-chain (AIConfig)

lightnode-sdk

ln.getModels() / ln.estimateFee() read it directly. The custom lcai_listSupportedModels RPC method returns the live whitelist.

npm Source

The official LightChain model registry is the AIConfig contract. The read-only LightNode client wraps it - ln.getModels() is what built the table below right now:

network

Whitelisted on mainnet via ln.getModels()

Reading AIConfig…

AIConfig (model registry) addresses

Mainnet (chain 9200): 0x24D11533…8Ce77D
Testnet (chain 8200): 0xeCF4Ca5B…31b67e

For the live whitelist, you can also call the chain's custom lcai_listSupportedModels RPC method directly.

Try it now: use the "Run a CLI command" widget above, pick lightnode models, hit Run.

More from lightnode-sdk

Bridge SDK

Top up a server wallet, let users pay in ETH, or move earnings back. Typed wrapper around the LightChain Hyperlane Warp Route - quote, approve, transfer LCAI both directions. Pair it with a Uniswap swap for a complete ETH-to-native-LCAI flow.

DAO SDK

Read + vote on LCAI Governor proposals on Ethereum. Real OZ Governor v5 wrapper. Cast votes, propose, queue, execute.

Multi-turn Conversation

new Conversation({ network, privateKey }).send('hi') keeps history client-side and runs one encrypted inference per turn. Optional system prompt + maxHistoryTurns cap.

Worker preflight + watch

workerPreflight submits ONE real test inference + returns verdict. workerWatch streams state-change events (registered, went-stale, jobs-completed) for any worker, no key required.

Dispute / refund queries

ln.getJobStatus(jobId) classifies a job (submitted / in-flight / completed / stalled / disputed / resolved) and exposes a refundable flag.

Back to all modules Build hub