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

# Settling a Market Manually

Legacy guidance for manually settling markets created before Automated Settlement.

{% hint style="success" %}
**Automated markets do not require creator action after close.** Delphi runs the settlement workflow automatically. See [How Automated Settlement Works](/how-ai-settlement-works.md).
{% endhint %}

## Settling a Market Manually

This guide applies only to markets created before Automated Settlement became available. These markets display a *Legacy* label.

### Legacy Manual Markets

You cannot create a new manual-settlement market. Instead, all new markets utilize the Automated Settlement process.

{% hint style="warning" %}
Only follow this guide when settling an existing **Legacy** market. For every other market, Delphi settles automatically after trading closes.
{% endhint %}

### Settle a Legacy Market

Legacy markets require creator action after close. You have 24 hours to settle the market.

To settle a market manually:

1. Open the closed market and select *Settle Market*.
2. Copy the locked settlement prompt.
3. Run it through the market's configured judge model.
4. Paste the output, select the matching outcome, and confirm.
   1. For cloud-hosted models, run the prompt directly. These models can access the market's specified sources.
   2. For verifiable local models, retrieve the specified source data first. Append it to the settlement prompt, then run the prompt in [Gensyn's REE](https://docs.gensyn.ai/tech). Paste the resulting [settlement receipt](https://docs.gensyn.ai/tech/ree/receipts) as the model output.

{% hint style="warning" %}
The receipt verifies the computation from its recorded inputs. It does not verify that the source data was correct.
{% endhint %}

### Claiming Fees and Payouts

After you settle a Legacy market, select **Claim Now** on the market page to claim your creator fee earnings and any winning shares you hold.

The *Claimable* tab in [Activity](/activity.md) lists unredeemed winning shares.

### What if None of Your Outcomes Apply?

Do not force an incorrect outcome. Let the deadline pass if no listed outcome applies.

The market resolves to *No Outcome*. Positions pay at the final market prices, which may differ from their original cost.

### What Happens If You Miss the Deadline

If you do not settle a Legacy market within 24 hours, it resolves to *No Outcome*.

* Your initial liquidity is forfeited.
* Positions pay at final market prices.
* Proceeds may be higher or lower than the original cost.

{% hint style="info" %}
This is not a traditional refund. Participants can claim the value of their remaining positions from **Payouts** in [Activity](/activity.md).
{% 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.delphi.fyi/settling-a-market.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.