> For the complete documentation index, see [llms.txt](https://docs.trueopen.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.trueopen.ai/providers.md).

# Providers

Supply inference and verification capacity by operating a Cortex Node.

Run a Cortex Node to provide inference and verification capacity. This guide covers connecting compatible model capacity, accepting accountable Task duties, and keeping the node healthy through operation and exit.

You do not need this guide if you only submit Tasks from an application. Start with [Use TrueOpen](/developers.md) instead. If you develop the adapter or model-serving integration used by an operator, use the [model integrator guide](/providers/model-integration.md).

## Is this role for you?

A compute provider is responsible for:

* Maintaining an operator identity, online service key, and ServiceBond
* Supplying hardware and a model runtime compatible with declared Profiles
* Keeping chain, Nexus, model, and evidence-storage connections healthy
* Deciding when to offer capacity and at what local price floor
* Completing Worker or Verifier duties before chain-height deadlines
* Retaining evidence through challenge and cleanup windows
* Monitoring, upgrading, recovering, draining, and exiting the node safely

Running a Cortex Node creates economic responsibility. A missed or invalid accepted duty may affect the provider's bond.

## Operator journey

```mermaid
flowchart LR
    A[Check requirements] --> B[Install Cortex]
    B --> C[Create identity and configure endpoints]
    C --> D[Connect a compatible model]
    D --> E[Declare Profiles and bond]
    E --> F[Join and activate]
    F --> G[Perform Task duties]
    G --> H[Monitor and maintain]
    H --> I[Drain and exit]
```

## Start here

For a participation walkthrough, see [Model and node activation](/providers/model-and-node-activation.md) and [Node lifecycle](/providers/node-lifecycle.md). Adapter developers can use the dedicated [Model integration](/providers/model-integration.md) guide.

1. Review the [requirements](/providers/requirements.md) before acquiring hardware or depositing a bond.
2. Follow the [provider quickstart](/providers/quickstart.md) to understand the complete setup and activation sequence.
3. Configure [Profiles and capabilities](/providers/profiles-and-capabilities.md).
4. Learn when [Worker and Verifier duties](/providers/task-duties.md) become binding.
5. Prepare monitoring, backups, and restart procedures with [Operations and recovery](/providers/operations-and-recovery.md).
6. Review [Security and exit](/providers/security-and-exit.md) before putting funds or sensitive Task data at risk.

{% hint style="info" %}
Release-specific commands, image names, ports, network IDs, minimum bond values, and hardware matrices will be added when public release artifacts are available. The sequence and safety requirements documented here still apply.
{% endhint %}


---

# 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.trueopen.ai/providers.md?ask=<question>&goal=<endgoal>
```

`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.