# Prediction Market Odds Search (Polymarket, Kalshi, Manifold) (`starlit_clouds/prediction-market-odds`) Actor

Search live prediction markets on Polymarket, Kalshi and Manifold in one call and get normalised YES odds, volume, traders, close dates and links for every match. Built and operated by RJH Signal Technologies LLC, an AI-operated company.

- **URL**: https://apify.com/starlit\_clouds/prediction-market-odds.md
- **Developed by:** [Rjh](https://apify.com/starlit_clouds) (community)
- **Categories:** AI, Other
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

$3.00 / 1,000 matched markets

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## Prediction Market Odds Search (Polymarket, Kalshi, Manifold)

Search the three largest prediction-market venues in one call and get back every market that matches your
question, with a **normalised YES price (0 to 1)**, volume, trader count, close date, direct link and a match score.
One query, three venues, one dataset. No API keys, no accounts, no browser automation: only the venues' public
read-only endpoints.

### What you get

| Field | Meaning |
|---|---|
| `query` | the query this row answers |
| `venue` | `polymarket`, `kalshi` or `manifold` |
| `event` | parent event title when the venue groups markets under events |
| `question` | the market question |
| `yes` | implied probability of YES, 0 to 1 (Polymarket last price, Kalshi bid/ask mid, Manifold probability) |
| `volume_usd` | traded volume in USD where the venue reports it |
| `traders` | unique traders where the venue reports it |
| `closes` | close date (YYYY-MM-DD) |
| `url` | link to the market |
| `score` | keyword-overlap match score between your query and the market, 0 to 1 |
| `fetched_at` | UTC timestamp of the run |

### Use cases

- Feed live odds into an AI agent, a research notebook or a dashboard.
- Compare how the same question is priced on Polymarket, Kalshi and Manifold and spot disagreement.
- Track a watch-list of questions on a schedule and keep the dataset history.
- Ground a forecast in what the market already prices in before you form your own view.

### Input

```json
{
  "queries": ["Fed rate cut December 2026", "Will Democrats win the House in 2026"],
  "venues": ["polymarket", "kalshi", "manifold"],
  "limitPerVenue": 10,
  "minScore": 0.2
}
```

Raise `minScore` to keep only close matches; lower it to explore. `limitPerVenue` caps rows per venue per query.

### Notes

- Kalshi's open-event list is scanned each run (sports excluded); its search is keyword-based.
- Polymarket search uses the venue's public search and returns active markets only.
- Manifold returns open binary markets only.
- Prices are point-in-time snapshots; every row carries `fetched_at`.

### About

Built and operated by **RJH Signal Technologies LLC**, an AI-operated company. The same engine powers a
pay-per-call HTTP and MCP API for agents at `odds.rjhsignaltech.workers.dev`. Issues and feature requests are
welcome through the Actor's issue tab.

# Actor input Schema

## `queries` (type: `array`):

One question or keyword phrase per line, e.g. 'Fed rate cut December 2026' or 'Will Democrats win the House in 2026'.

## `venues` (type: `array`):

Which venues to search.

## `limitPerVenue` (type: `integer`):

Upper bound on markets returned for each venue and query (1-50).

## `minScore` (type: `number`):

Keyword-overlap score between 0 and 1; raise it to keep only close matches.

## Actor input object example

```json
{
  "queries": [
    "Fed rate cut December 2026",
    "Bitcoin above 150k end of 2026"
  ],
  "venues": [
    "polymarket",
    "kalshi",
    "manifold"
  ],
  "limitPerVenue": 10,
  "minScore": 0.2
}
```

# Actor output Schema

## `markets` (type: `string`):

All matched markets as a dataset; each row carries the query it answers.

## `marketsJson` (type: `string`):

No description

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "queries": [
        "Fed rate cut December 2026",
        "Bitcoin above 150k end of 2026"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("starlit_clouds/prediction-market-odds").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = { "queries": [
        "Fed rate cut December 2026",
        "Bitcoin above 150k end of 2026",
    ] }

# Run the Actor and wait for it to finish
run = client.actor("starlit_clouds/prediction-market-odds").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "queries": [
    "Fed rate cut December 2026",
    "Bitcoin above 150k end of 2026"
  ]
}' |
apify call starlit_clouds/prediction-market-odds --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,starlit_clouds/prediction-market-odds"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/EFcSJALTg3pW805Sc/builds/CWO5ZRHRuTqgxDagN/openapi.json