> ## Documentation Index
> Fetch the complete documentation index at: https://docs.mage.space/llms.txt
> Use this file to discover all available pages before exploring further.

# My generation failed or was blocked

> A failed generation and a refused one are different problems. How to tell which you hit, what happens to your Gems, and whether the refusal came from Mage or the model's lab.

A generation that fails and a generation that is refused are two different problems with two different fixes. Start by reading which one you got.

## Which one happened

| What you saw                                             | What it means                                                                               |
| -------------------------------------------------------- | ------------------------------------------------------------------------------------------- |
| An error, or the job ended with no output                | The generation failed. Something on the infrastructure side went wrong.                     |
| A message saying the prompt or image cannot be generated | The generation was refused. This is about content, and the next question is who refused it. |
| The job finished but the output is blank or corrupted    | Treat it as a failure. Run it again before anything else.                                   |

## If it failed

Gems spent on a generation that fails are refunded. Run it again first; most failures are transient. If it fails twice on the same settings, change one thing at a time: drop the resolution a step, shorten the duration, or remove an attached reference. Then try a different model on the same prompt. A failure that repeats across models is worth reporting: send the prompt, the model, the settings, and roughly when it happened to [mage@mage.space](mailto:mage@mage.space).

## If it was refused

### Mage's rules

The content rules apply on every model and plan, and no amount of rephrasing gets around them. See [what you can and cannot create](/policy/content-rules).

### A lab's filter

GPT Image 2, Grok Image, Grok Video, Nano Banana 2, Veo 3.1 Lite, and Veo 3 are run by their labs, and each lab's content rules apply to your prompts before Mage sees the result. A refusal from one of these comes from that lab's filter, and Mage cannot change or override it. The same prompt may run on a Mage model.

## Refusals that are neither

* An imported custom model that will not load is a compatibility problem, not a content one. See [importing custom models](/features/importing-custom-models).
* A model above your plan's unlimited tier does not leave the picker. It switches from unlimited to Gems and keeps running, which is also what happens after a downgrade.

## What not to do

Do not retry a refused prompt repeatedly with small variations. If you think a refusal was wrong, say so once, with the prompt and the model, at [mage@mage.space](mailto:mage@mage.space).