Reach AI Demand
Serve inference for people, applications, and autonomous agents through one network.
For Compute Providers
Bring your hardware to Katara’s decentralized inference network. Serve supported models to people, applications, and agents, and get paid for eligible work.
Earn with Katara Cortex
Put your Apple silicon Mac or supported GPU to work. Run approved AI models with Katara Cortex and get paid instantly in USDC, settled on Avalanche blockchain.
You bring the compute and set your prices. Katara Cortex connects you with demand from people, applications, and agents, and handles routing, verification, and payment.
Serve inference for people, applications, and autonomous agents through one network.
Choose what to charge for input and output tokens. Compete for requests on your terms.
Find approved models that fit your machine’s chip, memory, and supported runtime.
Inside the Network
Katara Cortex combines approved model bundles, provider validation, and clear usage records so you can understand what serves your requests and what you’re paying for.
Pinned model weights, tokenizers, and runtimes define what each provider must run.
Providers are tested with known prompts and checked against the bundle’s requirements.
Request records report token usage and the cost in USDC, so you can see what you paid for.
Getting Started
Use the hardware checker to identify supported models for your chip, memory, and operating system.
Follow the provider guide to install the node, connect your wallet, and configure your machine.
Load approved model bundles and set your prices. Routing depends on validation, available capacity, and demand.
Earn USDC for eligible inference. Review the current settlement rules and provider responsibilities before joining.
Compatibility does not guarantee work or earnings. Review the current provider responsibilities in the terms before joining.
Follow the setup instructions and check the current requirements for your machine.