[Integrations](https://spiral.ai/integrations) › [ChatGPT](https://spiral.ai/integrations/chatgpt) › [Wikipedia article text](https://spiral.ai/integrations/chatgpt/wikipedia-article-text)

# How to Use Wikipedia article text in ChatGPT

Fetch a Wikipedia article's current text as wikitext or HTML, with article metadata. Use it to read the full article or inspect categories and redirects that structured article output leaves out.

|  |  |
| --- | --- |
| Model | Wikipedia article text |
| Available through | Alexandria |
| Category | Web |
| Price | Up to $0.001746 per run at the default inputs. $0.001746 per unit of `limit`. |
| Returns | json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Wikipedia article text in ChatGPT

- Use Wikipedia article text to read English Wikipedia's Lithium iron phosphate battery article and summarize the advantages and limitations it describes.
- Use Wikipedia article text to read English Wikipedia's NASA and European Space Agency articles and compare their stated roles using only the retrieved text.
- Use Wikipedia article text to look this up and give me the result as a table.
- Pull the latest numbers from Wikipedia article text and tell me what changed since last week.
- Check Wikipedia article text and summarize what you find in three bullet points.

## How to set up Wikipedia article text in ChatGPT

Pick the way that suits you. Each takes about two minutes.

### Use the ChatGPT connector

1. **Add a custom MCP server**: In ChatGPT open Plugins, then Add › Add custom MCP server. Name it Spiral, paste this URL and keep Authentication on OAuth. Tick I understand and want to continue, then click Create.

```text
https://api.spiral.ai/mcp
```

2. **Click Connect**: ChatGPT asks to connect Spiral. Connect takes you to Spiral in your browser.

3. **Sign in to Spiral and approve**: Sign in, pick the organization ChatGPT should use and click Authorize. Spiral gives the connection its own API key; ChatGPT never sees it, and you can remove the connection under Settings › Connected apps.

### Use the Spiral skill

1. **Send ChatGPT this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run Wikipedia article text**: One request; the result comes back by polling or a webhook.

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "alexandria",
    "model": "wikipedia/articles/lookup",
    "input": {
      "name": "<name>"
    }
  }'
```

Then paste one of the prompts above: ChatGPT finds Wikipedia article text on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/chatgpt

## Wikipedia article text tools and prices

- [Wikipedia · Article](https://spiral.ai/tools/alexandria/wikipedia/articles/lookup) (Alexandria): Up to $0.001746 per run at the default inputs. $0.001746 per unit of `limit`.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| body | wikitext, html, both, none | wikitext | Which article_body format to include when fields is not given: `wikitext` (default, compact), `html` (MediaWiki DOM, often 5-10x larger), `both`, or `none` for metadata and abstract only. |
| limit | 1 to 10 | 1 | Most matching articles to return, 1 to 10. More than one only helps when no project is pinned and the title exists on several wikis. |
| fields |  | — | Return only these fields, in dot notation, for example `name`, `abstract`, `url`, `version.identifier`. Omit for the full record. Wikimedia returns exactly the fields named. |
| project |  | — | Wikimedia project identifier: language code plus project code, for example `enwiki` (English Wikipedia), `frwiki`, `dewiki`, `enwiktionary` or `eswikivoyage`. Defaults to `enwiki` when neither project nor language is given. `reference/projects` lists every identifier. |
| language |  | — | Wikimedia language code, for example `en`, `fr` or `zh-yue`. Returns the article from any project in that language; combine with project to pin one wiki. |

## What can you do with Wikipedia article text in ChatGPT?

Produce a focused brief from the Wikipedia articles you name. A chat app can compare their explanations, summarize selected sections, or organize returned tables into a readable comparison.

### Prepare a research brief

Read the Wikipedia articles for Lithium iron phosphate battery and Sodium-ion battery, then compare the advantages and limitations described in their text. Use parsed sections when extracting passages and full article text when more context is needed.

### Build city background notes

Turn the articles for Chicago and Toronto into separate notes on history, geography, and transportation. Keep each statement tied to the article it came from.

### Research public organizations

Use the NASA and European Space Agency articles to draft an organizational background comparison from the retrieved text. Distinguish what each article states from your own interpretation.

### Create teaching materials

Read the Plate tectonics article and turn its explanations into a lesson outline, vocabulary list, and comprehension questions. Use the article's sections to keep the material organized.

### Build a focused reference collection

Retrieve a chosen list of Wikipedia titles for a reference assistant. Store article passages from the text response or parsed sections from the structured response, with their source articles.

### Report changes to selected articles

Retrieve the International Space Station article each day and compare it with your previously saved response. Summarize changes in the article's wording without presenting them as independently confirmed events.

## Overview

- [Alexandria](https://spiral.ai/providers/alexandria)
- [All ChatGPT guides](https://spiral.ai/integrations/chatgpt)

## Wikipedia article text in other agents

- [Amp](https://spiral.ai/integrations/amp/wikipedia-article-text)
- [Claude](https://spiral.ai/integrations/claude-desktop/wikipedia-article-text)
- [Claude Code](https://spiral.ai/integrations/claude-code/wikipedia-article-text)
- [Cline](https://spiral.ai/integrations/cline/wikipedia-article-text)
- [Codex](https://spiral.ai/integrations/codex/wikipedia-article-text)
- [Cursor](https://spiral.ai/integrations/cursor/wikipedia-article-text)
- [Devin](https://spiral.ai/integrations/devin/wikipedia-article-text)
- [dots](https://spiral.ai/integrations/dots/wikipedia-article-text)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/wikipedia-article-text)
- [Gemini](https://spiral.ai/integrations/gemini/wikipedia-article-text)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/wikipedia-article-text)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/wikipedia-article-text)
- [goose](https://spiral.ai/integrations/goose/wikipedia-article-text)
- [Grok](https://spiral.ai/integrations/grok/wikipedia-article-text)
- [Grok Build](https://spiral.ai/integrations/grok-build/wikipedia-article-text)
- [Hermes](https://spiral.ai/integrations/hermes/wikipedia-article-text)
- [Instinct](https://spiral.ai/integrations/instinct/wikipedia-article-text)
- [Manus](https://spiral.ai/integrations/manus/wikipedia-article-text)
- [Muse](https://spiral.ai/integrations/muse/wikipedia-article-text)
- [Muse Code](https://spiral.ai/integrations/muse-code/wikipedia-article-text)
- [n8n](https://spiral.ai/integrations/n8n/wikipedia-article-text)
- [Notion](https://spiral.ai/integrations/notion/wikipedia-article-text)
- [OpenClaw](https://spiral.ai/integrations/openclaw/wikipedia-article-text)
- [opencode](https://spiral.ai/integrations/opencode/wikipedia-article-text)
- [Perplexity](https://spiral.ai/integrations/perplexity/wikipedia-article-text)
- [Raycast](https://spiral.ai/integrations/raycast/wikipedia-article-text)
- [VS Code](https://spiral.ai/integrations/vscode/wikipedia-article-text)
- [Windsurf](https://spiral.ai/integrations/windsurf/wikipedia-article-text)
- [Zapier](https://spiral.ai/integrations/zapier/wikipedia-article-text)

## More ChatGPT guides

- [Wikimedia project directory](https://spiral.ai/integrations/chatgpt/wikimedia-project-directory)
- [Wikipedia language codes](https://spiral.ai/integrations/chatgpt/wikipedia-language-codes)
- [Wikidata property details](https://spiral.ai/integrations/chatgpt/wikidata-property-details)
- [Wikipedia structured article](https://spiral.ai/integrations/chatgpt/wikipedia-structured-article)
- [Wikidata labels](https://spiral.ai/integrations/chatgpt/wikidata-labels)
- [Alexandria](https://spiral.ai/integrations/chatgpt/alexandria)

## Questions about Wikipedia article text in ChatGPT

**Can ChatGPT use Wikipedia article text?**

Yes. Add Spiral to ChatGPT as an MCP server, and ChatGPT can find and run Wikipedia article text like any built-in tool.

**How much does Wikipedia article text cost in ChatGPT?**

Up to $0.001746 per run at the default inputs. $0.001746 per unit of `limit`. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your ChatGPT plan is separate.

**Do I need an Alexandria account to use Wikipedia article text in ChatGPT?**

No. Spiral runs Wikipedia article text on its own Alexandria account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Wikipedia article text in ChatGPT?**

About two minutes: add a custom MCP server, then click Connect, then sign in to Spiral and approve.

**Does ChatGPT wait while Wikipedia article text runs?**

Wikipedia article text runs in the background. ChatGPT starts the run, checks on it and gives you the json when it's ready.

**Can I search Wikipedia by topic with these lookups?**

Both lookups require an exact article title. A request for a broad topic does not produce a ranked list of related articles.

**How fresh is the article data?**

Wikimedia documents these lookups as returning the current article revision. The revision identifier changes with every edit, so repeated retrievals can establish whether the article has changed.

**Can I retrieve an article as it appeared last year?**

These lookups return the current revision rather than a selectable historical revision. They do not provide a full revision-history download.

**Why can an article title match more than once?**

Article titles are not unique across Wikimedia projects. The same name can match pages on different wikis, so the intended source edition matters.

**Does structured output include everything in the text response?**

Structured Contents separates article content into parsed objects but omits the raw article body, categories, templates, and redirects. Use Wikipedia article text when those are necessary.

