Skip to main content
Ask Palliora a question, get a real answer back. Copy the script below, run one command, done. This first script is deliberately public: your question and the answer are visible on the testnet ledger, so you can watch every step of a Compute Contract happen. Once it works, Encrypted compute shows the same flow with your question and answer encrypted.
A few seconds later, a real answer prints to your terminal. That’s it, you just ran a question through a Compute Contract on Palliora’s testnet. Guardians run a small, curated set of models: gemma3:1b, deepseek-r1:1.5b, llama3.2:1b and qwen3:0.6b. Any other model submits fine and fails at execution.

What just happened

That one script did three things: connected to Manas (Palliora’s public testnet), created a Compute Contract naming three Guardians, the model and the fee, and read the answer back once it was ready. You didn’t have to run any infrastructure yourself. Because this run is plaintext, anyone looking at the ledger can see the question and the answer. The privacy comes in the next step: Encrypted compute encrypts the input to a Guardian group and returns the answer encrypted to you. If you want to understand the mechanism behind this (what a Compute Contract is, why it takes a few seconds, who gets paid), see How Palliora Works. If you want a version of this script with proper error handling and configuration, the kind you’d actually keep in a project, see Call a model.

If it didn’t work

Check Troubleshooting, most failures here are network behavior you can work around, not bugs in your code.

Next