# Gemini Predictions Scraper: Prediction Market Prices & Odds (`forgedata/gemini-predictions-scraper`) Actor

Scrape every Gemini Predictions market: live prices, odds and implied probabilities for NFL and college games, midterm elections, Fed decisions, crypto and more. Settled results too. No login.

- **URL**: https://apify.com/forgedata/gemini-predictions-scraper.md
- **Developed by:** [Data Forge](https://apify.com/forgedata) (community)
- **Security:** Limited permissions
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $0.01 / 1,000 results

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.
Since this Actor supports Apify Store discounts, the price gets lower the higher subscription plan you have.

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

## Gemini Predictions Scraper: Prediction Market Prices, Odds & Results

Scrape **every prediction market on Gemini Predictions** in one run: NFL and college games, the 2026 midterms, the Fed, Bitcoin and other crypto prices, commodities, weather and more. Get each outcome's **live price, implied probability, bid and ask, volume**, closing time, and for settled markets the **winning side and settlement value**. Export to JSON, CSV or Excel, or call it from the API. **$2 per 1,000 results.** No login, no API key, no browser.

The first and only Gemini Predictions scraper on Apify.

### Why use it

- **All of Gemini Predictions at once.** Gemini's own list stops at 1,000 events, so this actor reads every category and merges them. A full run covers 1,200+ live events.
- **Ready-to-use prices.** Best bid, best ask, last trade, and an implied probability (the bid/ask midpoint) for every outcome, plus Gemini's buy and sell prices for both Yes and No.
- **Results too.** Switch to settled markets to get the winning side, the settlement value and when it resolved. Useful for backtests and calibration studies.
- **Spreadsheet friendly.** One row per outcome by default, or one row per event with outcomes nested.
- **Fast and cheap.** Reads Gemini's public API directly, so a full run takes under a minute.

### What you can use it for

- **Compare venues:** line Gemini prices up against Polymarket, Kalshi or sportsbooks to find price gaps.
- **Trading research:** track how probabilities move into an event, and backtest on settled results.
- **Dashboards and newsletters:** show live odds for elections, games, Fed decisions and crypto prices.
- **AI agents:** give an agent a current read on what markets expect, through the Apify API or MCP server.

### What you get for each outcome

| Field | Example |
|---|---|
| eventTitle / outcome | Which party will win the U.S. Senate? / Republican |
| category / subcategory | Politics / Midterms |
| impliedProbability | 0.62 |
| yesBid / yesAsk / lastPrice | 0.61 / 0.63 / 0.62 |
| buyYes / buyNo / sellYes / sellNo | 0.63 / 0.39 / 0.61 / 0.37 |
| spread | 0.02 |
| eventVolume / eventVolume24h | 182,340 / 12,905 |
| startTime / expiryDate | game start and market close |
| status / marketState | active / open |
| resolutionSide / settlementValue / resolvedAt | yes / 77,813.74 / when it settled |
| strike | for price markets, e.g. above 77,000 |
| rules | full resolution rules (optional) |
| url | the market's page on Gemini |

Prices are in dollars per $1 contract, so 0.62 means the market puts the chance at about 62%.

### How to use it

1. Pick **Categories** (for example Sports, Politics or Crypto), or leave empty for all.
2. Optional: **Search** for a word like `senate`, `bitcoin` or `chiefs`.
3. Choose **Active** for live prices or **Settled** for results.
4. Set **Max results** and run. Download the data or connect it through the API.

Schedule it every few minutes or hours to build a price history.

### Pricing

**$2 per 1,000 results**, with lower prices on Apify's Bronze, Silver and Gold plans. You pay only for rows saved.

### Is it legal?

This actor reads the public market data that Gemini publishes through its open API, which requires no account or key. It collects no personal data. Gemini's market data is Gemini's property and its use is governed by Gemini's Market Data Agreement; you are responsible for using the data within those terms. This actor is not affiliated with or endorsed by Gemini. Prediction market prices are not financial advice.

### More from Data Forge

- [Polymarket vs Kalshi API](https://apify.com/forgedata/prediction-markets-api): the same question matched across Polymarket and Kalshi, with price gaps and sportsbook lines
- [Hyperliquid Outcome Markets Scraper](https://apify.com/forgedata/hyperliquid-outcome-markets): Hyperliquid's on-chain prediction markets

# Actor input Schema

## `categories` (type: `array`):

Which Gemini prediction market categories to scrape. Leave empty for every category.

## `search` (type: `string`):

Optional. Only events matching this text, e.g. senate, bitcoin, chiefs, fed.

## `status` (type: `string`):

Active markets with live prices, or settled markets with the winning side and settlement value.

## `outputLevel` (type: `string`):

Contract: one row per outcome (best for spreadsheets). Event: one row per market with its outcomes nested.

## `minVolume` (type: `integer`):

Skip events that have traded less than this many contracts in total. 0 keeps everything.

## `sortBy` (type: `string`):

Order of results. Total volume puts the most traded markets first.

## `settledWithinDays` (type: `integer`):

For settled markets: only those resolved in the last N days. 0 means no limit.

## `includeRules` (type: `boolean`):

Add each contract's full resolution rule text.

## `maxResults` (type: `integer`):

Maximum rows to save. You pay only for rows saved.

## Actor input object example

```json
{
  "categories": [
    "Sports"
  ],
  "search": "",
  "status": "active",
  "outputLevel": "contracts",
  "minVolume": 0,
  "sortBy": "volume",
  "settledWithinDays": 0,
  "includeRules": false,
  "maxResults": 100
}
```

# Actor output Schema

## `results` (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 = {
    "categories": [
        "Sports"
    ],
    "maxResults": 100
};

// Run the Actor and wait for it to finish
const run = await client.actor("forgedata/gemini-predictions-scraper").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 = {
    "categories": ["Sports"],
    "maxResults": 100,
}

# Run the Actor and wait for it to finish
run = client.actor("forgedata/gemini-predictions-scraper").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 '{
  "categories": [
    "Sports"
  ],
  "maxResults": 100
}' |
apify call forgedata/gemini-predictions-scraper --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,forgedata/gemini-predictions-scraper"
        }
    }
}
```

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/nNgaJ7r11s1cLZzHy/builds/XhnHcbPpYrvfNZMIj/openapi.json