# API playground

> Try every Virlo API endpoint and see real replies drawn as videos, creators, sounds and charts. No API key needed.

Source: https://dev.virlo.ai/docs/playground
Markdown: https://dev.virlo.ai/docs/playground.md
Section: How the API works

## About the Virlo API (applies to every page)

- Base URL: `https://api.virlo.ai/v1`. Every request needs the header `Authorization: Bearer YOUR_API_KEY` (keys start with `virlo_tkn_`).
- Responses are JSON inside a `data` field, except the `/v1/webhooks` endpoints, which return the object or array directly. Field names are snake_case.
- Prices are in US dollars from a prepaid balance. 1 credit = $0.01. The `X-Cost` response header on each successful response is the exact charge. Errors are free.
- Slow jobs return an ID. Check its status every 15 seconds (or whatever `retry_after_seconds` says) until `finalized` is `true`.
- All docs pages: https://dev.virlo.ai/llms.txt. Every page in one file: https://dev.virlo.ai/llms-full.txt. MCP server for AI assistants: https://dev.virlo.ai/api/mcp/mcp.

---

See what the API returns before you write code.

**At a glance**

- **What it does:** Runs any endpoint and draws the reply: video grids, creator cards, sounds, hooks, audience splits and growth charts.
- **You send:** Pick a question or an endpoint. The fields come filled in, so **Send request** works right away.
- **You get back:** Replies recorded from the real API, the raw JSON, and the same request as cURL, JavaScript or Python.
- **Cost:** Free here, no key needed. Each endpoint shows its live price, and the [Billing page](https://dev.virlo.ai/docs/credits#prices) lists them all.

## How it works

- Start with a question, or pick any endpoint from the list. The list is read from the API's own spec, so it always matches what the API offers.
- Results lead to the next call. From a video, ask why it popped or look up its creator. From a sound, open the videos using it. From an agent, read its videos, trends and hooks.
- **Result** draws the reply, **JSON** shows it raw, and **Code** gives you the request to paste into your app.
- Agents and deep-dive lookups run in the background. The playground shows how waiting works: it checks the status endpoint until the job is done.

## Try it

The interactive playground runs in the browser: <https://dev.virlo.ai/docs/playground>. Every endpoint it shows is documented on the other pages.

## Run it on your own data

> **Note:** Sign in and open the [dashboard playground](https://dev.virlo.ai/dashboard/playground). It sends real requests with your team's API key, fills ids from your own agents and tracked creators, and shows what each call cost. Paid endpoints spend your balance.

---

More in How the API works:

- [How results load](https://dev.virlo.ai/docs/async-data.md)
- [Pagination](https://dev.virlo.ai/docs/pagination.md)
- [Rate limits](https://dev.virlo.ai/docs/rate-limits.md)
- [Webhooks](https://dev.virlo.ai/docs/webhooks.md)
- [Errors](https://dev.virlo.ai/docs/errors.md)
- [Workflow recipes](https://dev.virlo.ai/docs/recipes.md)