> 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/model-integration.md).

# Model Integration

Connect a model runtime to Cortex for inference and verification.

This guide is for developers who implement or maintain the adapter between Cortex and model compute. It is not an operator installation guide and does not cover bonding, earnings, or day-to-day node operation.

The integration boundary has three goals:

* Present stable health, capability, inference, and verification operations to Cortex
* Bind every result to the exact Task, Profile, duty, and runtime requested by Cortex
* Keep protocol signing and chain access outside the model runtime

## Integration path

Read [Cortex architecture](/providers/model-integration/cortex-architecture.md) for the control plane and runtime trust boundaries.

```mermaid
flowchart LR
    A[Choose a registered Profile] --> B[Implement adapter operations]
    B --> C[Publish capability manifest]
    C --> D[Bind runtime and artifacts]
    D --> E[Test inference and verification]
    E --> F[Run conformance tests]
    F --> G[Hand off to a compute provider]
```

Start with the [model adapter interface](/providers/model-integration/adapter-interface.md), define the [Profile and capability manifest](/providers/model-integration/profile-manifest.md), then run [conformance testing](/providers/model-integration/conformance-testing.md). Operators consuming the integration should follow [Providers](/providers.md).

## Responsibility boundary

The adapter produces raw result and evidence material. Cortex validates the bindings, constructs protocol material, persists responsibility state, and signs. The model runtime must not hold the provider's service key, submit chain transactions, or decide final settlement.


---

# 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/model-integration.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.