---
title: "PentestLLM API status: hourly probe and model health"
canonical: https://pentestllm.ai/status
generated: 2026-11-11T18:03:07.438Z
source: https://pentestllm.ai/status
base_url: https://api.pentestllm.ai/v1
---

Listed models, last hour

- Answering: 37 served real requests with no failure pattern
- Degraded: 5
- Down: 0
- No traffic: 0 no customer request in the window; the daily check still runs

Retry test, daily

- OpenAI format: Failed Nov 11, 2026, 6:30 AM UTC, 290 ms

Once a day the gateway sends one real request the way a request is retried after a failure.

curl

```
curl https://api.pentestllm.ai/v1/status
```

## Affected models, last 60 minutes

| Model | State | Served | Failed |
| --- | --- | --- | --- |
| [GLM-5.3 Flash Apex Abliterated](https://pentestllm.ai/models/glm-5.3-flash-apex-abliterated) `glm-5.3-flash-apex-abliterated` | Degraded | 29 | 38 |
| [Abliterated Model Large](https://pentestllm.ai/models/abliterated-model-large) `abliterated-model-large` | Degraded | 1 | 11 |
| [DeepSeek V4.1 Flash 1017 Heretic](https://pentestllm.ai/models/deepseek-v4.1-flash-1017-heretic-uncensored) `deepseek-v4.1-flash-1017-heretic-uncensored` | Degraded | 5 | 3 |

A request to a degraded model is retried on the next route before you see an error; a down model answers 503.

## What is checked

**API** checks that the gateway can build its model catalog, the same list `GET /v1/catalog` returns, every hour at seven minutes past, UTC. It passes when the list has models in it. The bar above reads the last 30 days of those hours.

**Listed models** carry an `availability` field in the catalog from real traffic in the last hour: ok, degraded, down, or unknown when nobody called the model. The table of affected models comes from the same hour. Checks are not billed to any account.

Whether each model still answers like the build it is named after is a different check: the [daily real-model check](https://pentestllm.ai/proof) sends a fixed prompt to every model each day.

## What each state means

- Operational: In the latest hour, requests were answered.
- Degraded: In the latest hour, at least one request in five failed.
- Down: In the latest hour, requests failed and none were answered.
- No data yet: No requests and no checks for this service in the last 30 days.

## During an incident

- A request that fails with a 5xx or 429 on one route is retried on another. Your price stays the same.
- Every response, including errors, carries an `x-uplink-request-id` header. Keep it; it is how we find your request.
- A 429 with a `retry-after` header says how many seconds to wait before trying again.
- If a request fails and this page shows the API operational, [send us the request id](https://pentestllm.ai/contact).

The same data is public JSON at `https://api.pentestllm.ai/v1/status`: no key, readable from any origin, cached for 60 seconds. Point your own monitoring at it.