> For the complete documentation index, see [llms.txt](https://docs.crynux.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.crynux.io/application-development/execute-tasks.md).

# Execute Tasks

Crynux Network executes work as typed Raw Tasks. Each task carries a `task_type` and a `task_args` JSON string that matches the schema for that type. Applications usually submit tasks through [Crynux AS](https://crynux-as.xyz), which prices the job, reserves Credits, and forwards the task to the network.

For more direct control over the application wallet, Relay fees, repeat-task settings, or Bridge-owned Raw / Batch APIs, you can deploy your own [Crynux Bridge](https://docs.crynux.io/application-development/crynux-bridge.md). Self-hosting Bridge is a more advanced option; [Crynux AS](https://crynux-as.xyz) is usually easier for application development.

## Crynux AS Raw Task endpoints

Under `/api/<endpoint_token>/v1`:

| Operation                | Method and path                                        |
| ------------------------ | ------------------------------------------------------ |
| Create one task          | `POST /inference_tasks`                                |
| Create up to 100 tasks   | `POST /inference_tasks/batch`                          |
| Get status               | `GET /inference_tasks/<client_task_id>`                |
| Batch status             | `POST /inference_tasks/batch/status`                   |
| Download LLM JSON        | `GET /inference_tasks/<client_task_id>/llm`            |
| Download image PNG       | `GET /inference_tasks/<client_task_id>/images/<index>` |
| List loaded image models | `GET /models/image`                                    |

Common top-level create fields (outside `task_args`):

* `task_type` — `0` for Image, `1` for LLM
* `task_args` — JSON string of the task schema
* `min_vram` — optional minimum GPU VRAM in GB
* `task_version` — optional task version string
* `queue_timeout` — optional queue wait budget in seconds (Flexible Pricing)

For OpenAI-compatible chat and image endpoints, see [How to Run LLM using Crynux Network](https://docs.crynux.io/application-development/how-to-run-llm-using-crynux-network.md) and [OpenAI-Compatible Image API](https://docs.crynux.io/application-development/openai-compatible-image-api.md). For quantization options shared by both task types, see [Model Quantization](https://docs.crynux.io/application-development/quantization.md).

## Task guides

{% content-ref url="/pages/1DaHVxBpm1NeVj27j6if" %}
[Text-to-Image Task](https://docs.crynux.io/application-development/execute-tasks/text-to-image-task.md)
{% endcontent-ref %}

{% content-ref url="/pages/wbQGyrKGcOdpNuWNNgqU" %}
[Text-to-Text Task](https://docs.crynux.io/application-development/execute-tasks/text-to-text-task.md)
{% endcontent-ref %}

{% content-ref url="/pages/3eDkFf418hrOdNqJhFiB" %}
[Text-to-Music Task](https://docs.crynux.io/application-development/execute-tasks/text-to-music-task.md)
{% endcontent-ref %}

{% content-ref url="/pages/OYloDmjrkkpJYK0nN3h2" %}
[Text-to-Video Task](https://docs.crynux.io/application-development/execute-tasks/text-to-video-task.md)
{% endcontent-ref %}

{% content-ref url="/pages/kF1BIZvTRByilPJEdbWH" %}
[Fine-Tuning Task](https://docs.crynux.io/application-development/execute-tasks/fine-tuning-task.md)
{% endcontent-ref %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.crynux.io/application-development/execute-tasks.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
