> For the complete documentation index, see [llms.txt](https://docs.cestus.network/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.cestus.network/readme.md). # Introduction ### What is Cestus Cestus is a permissionless inference network. GPU operators worldwide contribute hardware, serve open-weight models, and earn from every token their machines produce. Developers access the full range of open AI through a single endpoint. No closed weights. No centralized content policy. No single company controls the infrastructure. **One API. Every open model. Live on the network.** ### Why it matters AI inference today works like a utility where a small number of operators own the grid. OpenAI keeps the models. AWS keeps the margin. The open-weight ecosystem has produced models that rival their proprietary counterparts on most tasks, yet accessing them at production scale still means building your own infrastructure or accepting someone else's terms. Cestus closes that gap. Not by competing with centralized providers or raw compute marketplaces, but by being something neither has delivered: a complete, permissionless inference platform where open models are served through a polished developer API and consumer-facing interfaces, with no closed weights and no single company controlling the infrastructure. ### What you get * **Unified multi-modal pipeline.** Text inference, image generation, video generation, and music generation all run on the same swarm, routed by the same algorithm, billed through the same token economy. * **OpenAI-compatible API.** Change the base URL and model name. Everything else stays the same. * **Consumer interfaces.** A chat UI, image generation interface, video generation interface, and music generation interface - all powered by the same swarm as the API. * **Wallet-native auth.** Sign in with your Web3 wallet. No passwords. No centralized identity. * **Per-token billing.** Pay only for what you use. No idle capacity billed to your account. ### The honesty rule Cestus is a permissionless network of independent operators. That means: * **Model availability is dynamic.** The catalogue grows as operators join and load new models. Query `/v1/models` at runtime rather than hardcoding identifiers. * **No platform-level content policy.** The network serves any registered open-weight model. Content filtering is a property of the model weights, not the protocol. ### Where to go next * **Developers:** [Developer Quickstart](/getting-started/quickstart.md) * **End users:** [Sandbox Quickstart](/getting-started/publish-your-docs.md) * **GPU operators:** [Node Operator Quickstart](/getting-started/node-operator-quickstart.md) * **Researchers:** [Whitepaper](https://files.cestus.network/whitepaper.pdf) --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.cestus.network/readme.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.