# Quickstart

Reach a first live result in under two minutes. No account, no API key: the Model Intelligence public API answers anonymously.

## 1. Check the service is up

```bash exec GET https://upcube.ai/api/mi/v1/health expect:200 schema:mi-health
curl -sS https://upcube.ai/api/mi/v1/health
```

Expected: HTTP 200 with `ok: true` plus seed counters. If you see anything else, stop here and read [Troubleshooting](/docs/resources/troubleshooting) — downstream steps depend on this one.

## 2. List models

```bash exec GET https://upcube.ai/api/mi/v1/models expect:200 schema:mi-models
curl -sS https://upcube.ai/api/mi/v1/models
```

Expected: HTTP 200 with a `models` array and a `total` count. Each entry carries a `slug` you can look up next.

## 3. Look up one model

Pick a `slug` from step 2 and fetch its envelope:

```bash
curl -sS https://upcube.ai/api/mi/v1/models/<slug>
```

Expected: HTTP 200 with the model's full envelope, or HTTP 404 `{"error":"not found"}` for an unknown slug. Removed models answer 410; quarantined models answer 500 with a reason. Full semantics: [Model Intelligence API](/docs/api/model-intelligence).

## 4. Open the apps

- [Ethen Chat](https://chat.upcube.ai) — sign in and start a conversation ([Chat overview](/docs/chat/overview))
- [Model Intelligence](/model-intelligence) — browse the directory this API serves
- [Studio](https://studio.upcube.ai) — private alpha; enrollment required ([Studio overview](/docs/studio/overview))

## Next steps

- [Core concepts](/docs/get-started/concepts)
- [Chat overview](/docs/chat/overview)
- [Model Intelligence API](/docs/api/model-intelligence)
- [Troubleshooting](/docs/resources/troubleshooting)