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

# API reference

> Choose the reference for your model or service.

This is the API reference for **Perceptron Mk1.5**, generated from the live OpenAPI spec.

All endpoints use the base URL `https://api.perceptron.inc` and take your API key in the `Authorization: Bearer $PERCEPTRON_API_KEY` header; see [Authentication](https://docs.perceptron.inc/perceptron-mk1.5/guides/python/auth.md).

## Which reference do you need?

> [card] [Perceptron Mk1.5 (Latest)](https://docs.perceptron.inc/api-reference/chat-completions/create-chat-completion.md)
>
> The live contract, generated from the OpenAPI spec: chat completions, files and models.

> [card] [Perceptron Mk1](https://docs.perceptron.inc/perceptron-mk1/api-reference/index.md)
>
> Mk1's own endpoint pages, including the `vision_config` request field.

> [card] [Detect](https://docs.perceptron.inc/api-reference/detection/detect-objects.md)
>
> Object detections for a single image.

> [card] [Egocentric video annotation](https://docs.perceptron.inc/api-reference/egocentric/submit-an-egocentric-batch.md)
>
> Asynchronous batches of first-person video.

Use the selector at the top of the sidebar to switch between the Mk1.5 and Mk1 references.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.