# Morpheus Inference Marketplace

The **Morpheus Inference Marketplace** is where decentralized AI becomes accessible to everyone. It connects people who need compute power with providers who supply it, all coordinated by smart contracts. Instead of a centralized service, requests and responses flow directly between users and providers in a peer-to-peer system.

### Why Decentralized Inference Matters

Decentralized inference matters because it breaks the dependency on centralized providers who control access, pricing, and availability of AI infrastructure. In a decentralized system, anyone can contribute resources and anyone can use them, creating a more open, resilient, and competitive market. This model reduces single points of failure, keeps costs fair through transparent incentives, and ensures that innovation is not limited by the decisions of a few large players. It’s about shifting power from closed platforms to an open network where inference is a shared, community-driven resource.

### Design

At the center of the marketplace are the **Compute Node contracts**, which:

* Register providers and the models they host
* Match consumers with available providers
* Secure connections through encryption and verifiable on-chain logic

To participate, both sides use a **Proxy-Router** — a lightweight software package that connects to the contracts and manages communication. Once a session is established, the consumer sends requests directly to the provider’s model and receives responses without any middleman.

<figure><img src="/files/W4vmixI1ramD6oJJK7Ks" alt=""><figcaption></figcaption></figure>

For people who don’t want to run a node, there’s the [**API Gateway**.](https://openbeta.mor.org/) that is free during Beta testing. This gateway:

* Provides a simple API key for access
* Abstracts away the complexity of contracts and routers
* Powers integrations, lite clients, and apps like the **Morpheus Chat App**

Providers benefit by making their models available and earning rewards. Consumers gain flexible access to inference, with pricing based on session time instead of tokens. A reputation system ensures that reliable providers — with strong uptime, speed, and track record — are matched more often.

For those interested in more technical details, see:

* [Intro to Morpheus Compute Node](https://github.com/MorpheusAIs/Docs/blob/main/!KEYDOCS%20README%20FIRST!/Compute%20Providers/Compute%20Node/Intro%20to%20Morpheus%20Compute%20Node.md)
* [Overview of the Morpheus-Lumerin Environment](https://github.com/Lumerin-protocol/Morpheus-Lumerin-Node/blob/main/docs/00-overview.md)

💬 If you have any questions, feel free to ask them in the dedicated channel on [Discord](https://discord.com/channels/1151741790408429580/1167520834139738289).


---

# Agent Instructions: 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:

```
GET https://gitbook.mor.org/morpheus-inference-marketplace.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.