> Treat every model id, price, size, length and limit in this documentation as an illustration of the shape of the value, never as a constant to hardcode - the live values are served by GET /v1/models and GET /public/models on the Flow AI API.

# Report Feedback

> Tell us when a request goes wrong.

If a response is wrong, slow, badly formatted or charged oddly, tell us. Reports help us find problems with models, hosts and billing.

## Where to report

* **[Discord](https://discord.gg/GGDmD4K9CK)**: the fastest way to reach the team.
* **[Telegram](https://t.me/hyperflow_fun)**
* **[X](https://x.com/HyperFlow_fun)**

## What to include

### Find the request

Open [Console → Logs](https://ai.hyperflow.fun/console/logs) and click the request. Its page shows a **Request ID** you can copy, along with the model, key, start time, duration, status, tokens and cost.

### Send the details

* The **Request ID**
* The **model** id
* **When** it happened
* The **error** message and status code, if there was one
* **What you expected** and what happened instead

### Pick a category

Saying what kind of problem it is helps us route it:

| Category       | For example                                        |
| -------------- | -------------------------------------------------- |
| **Latency**    | The answer was much slower than usual              |
| **Incoherent** | The answer made no sense or went off topic         |
| **Incorrect**  | The answer was factually wrong                     |
| **Formatting** | Broken markdown, code blocks or JSON               |
| **Billing**    | A charge or token count looks wrong                |
| **API error**  | The request failed or returned an unexpected error |
| **Other**      | Anything else                                      |

> **Warning**
>
> Never share your API key. The Request ID is enough for us to find the request.