# Perceptron Docs

- [Quickstart](https://docs.perceptron.inc/perceptron-mk1.5/index.md): Get started with Perceptron Mk1.5 for image, video, and audio understanding, tracking, and tool calling.
- [Release notes](https://docs.perceptron.inc/perceptron-mk1.5/changelog.md): Perceptron Mk1.5 API integration changes.
- [Image understanding](https://docs.perceptron.inc/perceptron-mk1.5/capabilities/image-understanding.md): Ask visual questions, extract text, and ground objects in images.
- [Detect](https://docs.perceptron.inc/capabilities/detect.md): Return grounded object detections for a single image from text categories, annotated exemplars, or exhaustive detection.
- [Image Q&A](https://docs.perceptron.inc/perceptron-mk1.5/capabilities/image-qa.md): Ask questions about an image and ground answers in visible regions.
- [Image captioning](https://docs.perceptron.inc/perceptron-mk1.5/capabilities/image-captioning.md): Generate concise descriptions, detailed captions, and captions with spatial grounding.
- [Object detection](https://docs.perceptron.inc/perceptron-mk1.5/capabilities/object-detection.md): Locate named object categories, count visible instances, and render grounded detections.
- [OCR](https://docs.perceptron.inc/perceptron-mk1.5/capabilities/ocr.md): Extract product names, prices, and document text as structured data or grounded spans.
- [In-context learning (image)](https://docs.perceptron.inc/perceptron-mk1.5/capabilities/in-context-learning-image.md): Use labeled visual examples to guide detection in a new image.
- [Video understanding](https://docs.perceptron.inc/perceptron-mk1.5/capabilities/video-understanding.md): Understand video frames and soundtracks, and identify moments or event intervals.
- [Video Q&A](https://docs.perceptron.inc/perceptron-mk1.5/capabilities/video-qa.md): Ask about goals, actions, and outcomes observed in a video.
- [Video clipping](https://docs.perceptron.inc/perceptron-mk1.5/capabilities/video-clipping.md): Locate an event as a moment or an interval with temporal annotations.
- [In-context learning (video)](https://docs.perceptron.inc/perceptron-mk1.5/capabilities/in-context-learning-video.md): Show a reference image and find matching visual evidence in a video.
- [Video tracking](https://docs.perceptron.inc/perceptron-mk1.5/capabilities/video-tracking.md): Follow objects through video with timestamped points, boxes, and track tags.
- [Audio understanding](https://docs.perceptron.inc/perceptron-mk1.5/capabilities/audio.md): Understand speech and sounds, choose audio inputs, and manage usage and limits.
- [Audio Q&A](https://docs.perceptron.inc/perceptron-mk1.5/capabilities/audio-qa.md): Ask focused questions about speech and audible events in a recording.
- [Audio transcription](https://docs.perceptron.inc/perceptron-mk1.5/capabilities/audio-transcription.md): Request spoken text with explicit instructions for language, unclear words, and speaker labels.
- [Audio clipping](https://docs.perceptron.inc/perceptron-mk1.5/capabilities/audio-clipping.md): Locate audible events and speech as moments or intervals in a recording.
- [Tools](https://docs.perceptron.inc/perceptron-mk1.5/capabilities/tool-calling.md): Connect Perceptron Mk1.5 to your application's data and functions.
- [Reasoning](https://docs.perceptron.inc/perceptron-mk1.5/capabilities/thinking.md): Configure reasoning effort and handle reasoning separately from the final answer.
- [Structured outputs](https://docs.perceptron.inc/perceptron-mk1.5/capabilities/structured-outputs.md): Choose native annotations, constrained final answers, or function arguments for your application.
- [Get started with Python](https://docs.perceptron.inc/perceptron-mk1.5/guides/python/getting-started.md): Set up a Python environment and send a complete Mk1.5 image request.
- [Authentication](https://docs.perceptron.inc/perceptron-mk1.5/guides/python/auth.md): Configure a Perceptron API key for Python and HTTP requests.
- [Request basics](https://docs.perceptron.inc/perceptron-mk1.5/guides/python/request-basics.md): Build reusable multimodal requests, preserve conversation history, and choose an output format.
- [Rendering annotations](https://docs.perceptron.inc/perceptron-mk1.5/guides/rendering-annotations.md): Parse image boxes with the SDK, resolve their asset selectors, and draw them on the original image.
- [Coordinate system](https://docs.perceptron.inc/perceptron-mk1.5/concepts/coordinates.md): Convert normalized annotations to image pixels and preserve their asset and crop context.
- [Python FAQs](https://docs.perceptron.inc/perceptron-mk1.5/guides/python/faqs.md): Common questions about Python requests, media, annotations, and async execution.
- [Annotation format](https://docs.perceptron.inc/perceptron-mk1.5/concepts/annotations.md): Read spatial and temporal grounding, including tracks and asset selectors.
- [Multiple assets](https://docs.perceptron.inc/perceptron-mk1.5/guides/multiple-assets.md): Ground answers across media and conversation history with asset_idx.
- [Function calling](https://docs.perceptron.inc/perceptron-mk1.5/guides/tool-calling.md): Execute model-requested functions and continue the conversation, with complete Python and streaming examples.
- [Files](https://docs.perceptron.inc/perceptron-mk1.5/guides/files.md): Upload media once and reuse it across requests.
- [Multilook](https://docs.perceptron.inc/perceptron-mk1.5/guides/multilook.md): Ask independent questions over shared media in one request.
- [MCP](https://docs.perceptron.inc/perceptron-mk1.5/guides/mcp.md): Connect an MCP client to Mk1.5 image, video, audio, and reasoning tools.
- [Error messages](https://docs.perceptron.inc/perceptron-mk1.5/guides/error-messages.md): Diagnose API failures, retry transient requests, and handle incomplete results.
- [Batch processing](https://docs.perceptron.inc/perceptron-mk1.5/guides/batch.md): Process independent images with bounded concurrency and a result for each item.
- [Scaling](https://docs.perceptron.inc/perceptron-mk1.5/guides/scaling.md): Control request volume, latency, and cost as your Mk1.5 workload grows.
- [Tokenization guide](https://docs.perceptron.inc/perceptron-mk1.5/guides/tokenization.md): Budget text, images, video, audio, reasoning, and tool conversations using reported token usage.
- [Prompting reference](https://docs.perceptron.inc/perceptron-mk1.5/best-practices/prompting-reference.md): Choose clear instructions, reasoning controls, and output formats for Mk1.5 tasks.
- [Security](https://docs.perceptron.inc/perceptron-mk1.5/best-practices/security.md): Protect credentials, media, and application actions in a Mk1.5 integration.
- [Building a tool agent](https://docs.perceptron.inc/perceptron-mk1.5/guides/tool-agents.md): Combine function calls, bounded execution, and image results into a useful application workflow.
- [High Fidelity Object Tracking](https://docs.perceptron.inc/perceptron-mk1.5/guides/high-fidelity-object-tracking.md): Turn model waypoints into detailed video tracks with optical flow and appearance tracking.
- [Models overview](https://docs.perceptron.inc/perceptron-mk1.5/models/index.md): Choose a model and discover its API capabilities.
- [Perceptron Mk1.5](https://docs.perceptron.inc/perceptron-mk1.5/models/perceptron-mk1.5.md): Image, video, and audio understanding with visual grounding, reasoning, and function calling.
- [Create chat completion](https://docs.perceptron.inc/perceptron-mk1.5/api-reference/chat-completions/create-chat-completion.md): Generate a response for a text or multimodal conversation, using the OpenAI chat completions request and response format.
- [Create multilook chat completions](https://docs.perceptron.inc/perceptron-mk1.5/api-reference/chat-completions/create-multilook-chat-completions.md): Run several independent prompts over one shared, prefilled context.
- [Detect objects](https://docs.perceptron.inc/perceptron-mk1.5/api-reference/detection/detect-objects.md): Return grounded object detections for a single image from text categories, annotated exemplars, or exhaustive detection.
- [List files](https://docs.perceptron.inc/perceptron-mk1.5/api-reference/files/list-files.md): Returns a paginated list of files belonging to the caller's organization. Cursor pagination via `after`; see the `limit` and `order` parameters for defaults.
- [Upload a file](https://docs.perceptron.inc/perceptron-mk1.5/api-reference/files/upload-a-file.md): Accepts a single file via multipart upload alongside a `purpose` field that declares how the file will be used. Subject to per-file and per-organization storage limits.
- [Retrieve a file](https://docs.perceptron.inc/perceptron-mk1.5/api-reference/files/retrieve-a-file.md): Returns metadata for a single file (size, content type, purpose, etc.). Use the `/v1/files/{file_id}/content` endpoint to download the bytes.
- [Delete a file](https://docs.perceptron.inc/perceptron-mk1.5/api-reference/files/delete-a-file.md): Permanently deletes a file. Once deleted, the file can no longer be retrieved, downloaded, or referenced in requests. Returns 404 if no file with the given id exists.
- [Download a file's contents](https://docs.perceptron.inc/perceptron-mk1.5/api-reference/files/download-a-files-contents.md): Returns the raw bytes with the file's stored `Content-Type` header.
- [List available models](https://docs.perceptron.inc/perceptron-mk1.5/api-reference/models/list-available-models.md): Returns a list of models available in the API. Use the `extended` query parameter to get additional metadata about each model's capabilities and supported features.
- [Retrieve a model](https://docs.perceptron.inc/perceptron-mk1.5/api-reference/models/retrieve-a-model.md): Returns a specific model by its ID. Use the `extended` query parameter to get additional metadata about the model's capabilities and supported features.
- [Quickstart](https://docs.perceptron.inc/perceptron-mk1/index.md): Perceptron Mk1 — vision-language model that sees and reasons across images and video.
- [Changelog](https://docs.perceptron.inc/perceptron-mk1/changelog.md): Changelog
- [Image Q&A](https://docs.perceptron.inc/perceptron-mk1/capabilities/image-qa.md): Ask grounded questions about any scene.
- [Image Captioning](https://docs.perceptron.inc/perceptron-mk1/capabilities/image-captioning.md): Generate concise or detailed descriptions for any scene.
- [Object detection](https://docs.perceptron.inc/perceptron-mk1/capabilities/object-detection.md): Prompt Perceptron Mk1 to return grounded detections with normalized geometry.
- [OCR](https://docs.perceptron.inc/perceptron-mk1/capabilities/ocr.md): Extract structured text with grounded prompts.
- [In-context learning (Image)](https://docs.perceptron.inc/perceptron-mk1/capabilities/in-context-learning-image.md): Teach Perceptron Mk1 a new visual concept with one or many annotated examples.
- [Video Q&A](https://docs.perceptron.inc/perceptron-mk1/capabilities/video-qa.md): Ask grounded questions about a short video and get reasoned natural-language answers.
- [Video Clipping](https://docs.perceptron.inc/perceptron-mk1/capabilities/video-clipping.md): Find the moment an event occurs in a video and return start/end timestamps.
- [In-context learning (Video)](https://docs.perceptron.inc/perceptron-mk1/capabilities/in-context-learning-video.md): Show Perceptron Mk1 an example image or clip, then ask it to do the same task on a fresh video.
- [Thinking](https://docs.perceptron.inc/perceptron-mk1/capabilities/thinking.md): Use reasoning traces to inspect how the model reached an answer.
- [Structured outputs](https://docs.perceptron.inc/perceptron-mk1/capabilities/structured-outputs.md): Constrain model replies to Pydantic, JSON schemas or regex for reliable parsing.
- [Get started](https://docs.perceptron.inc/perceptron-mk1/guides/python-sdk/getting-started.md): Install the Perceptron Python SDK, configure credentials, and send your first request.
- [Authentication](https://docs.perceptron.inc/perceptron-mk1/guides/python-sdk/auth.md): Learn how to configure credentials and authenticate with the Perceptron SDK.
- [Pointing basics](https://docs.perceptron.inc/perceptron-mk1/guides/python-sdk/pointing-basics.md): Understand Perceptron point, box, polygon, collection, and clip types and when to choose each for your application.
- [Perceive basics](https://docs.perceptron.inc/perceptron-mk1/guides/python-sdk/perceive-basics.md): Learn the Perceptron Perceive decorator, core nodes, and the patterns for authoring your first multimodal prompt.
- [Coordinate system](https://docs.perceptron.inc/perceptron-mk1/concepts/coordinates.md): Why normalized coordinates matter
- [Python SDK FAQs](https://docs.perceptron.inc/perceptron-mk1/guides/python-sdk/faqs.md): Answers to the most common questions about Perceptron’s Python client.
- [Files](https://docs.perceptron.inc/perceptron-mk1/guides/files.md): Upload media once and reference it across requests
- [Multilook](https://docs.perceptron.inc/perceptron-mk1/guides/multilook.md): Ask many independent questions about one image or video in a single call and pay for the shared context once.
- [MCP](https://docs.perceptron.inc/perceptron-mk1/guides/mcp.md): AI agents can interact with Perceptron's vision capabilities through our MCP server.
- [Error messages](https://docs.perceptron.inc/perceptron-mk1/guides/error-messages.md): Diagnose and resolve common Perceptron API errors
- [Batch processing](https://docs.perceptron.inc/perceptron-mk1/guides/batch.md): Process thousands of images with async workflows
- [Scaling guide](https://docs.perceptron.inc/perceptron-mk1/guides/scaling.md): Meet throughput and latency goals with Perceptron Mk1
- [Tokenization guide](https://docs.perceptron.inc/perceptron-mk1/guides/tokenization.md)
- [Prompting reference](https://docs.perceptron.inc/perceptron-mk1/best-practices/prompting-reference.md): Copy-paste prompts and code for each SDK primitive.
- [Security](https://docs.perceptron.inc/perceptron-mk1/best-practices/security.md): Protect keys, data, and edge deployments
- [Models](https://docs.perceptron.inc/perceptron-mk1/models/index.md): Vision-language models from Perceptron.
- [Perceptron Mk1](https://docs.perceptron.inc/perceptron-mk1/models/perceptron-mk1.md): Best-in-class VLM with reasoning.
- [Chat Completions](https://docs.perceptron.inc/perceptron-mk1/api-reference/endpoint/chat-completions.md): Generate a response for a text or multimodal conversation, using the OpenAI chat completions request and response format.
- [Multilook Chat Completions](https://docs.perceptron.inc/perceptron-mk1/api-reference/endpoint/multilook-chat-completions.md): Run several independent prompts over one shared, prefilled context.
- [Detect](https://docs.perceptron.inc/perceptron-mk1/api-reference/endpoint/detect.md): Return grounded object detections for a single image from text categories, annotated exemplars, or exhaustive detection.
- [List Models](https://docs.perceptron.inc/perceptron-mk1/api-reference/endpoint/list-models.md): Returns a list of models available in the API. Use the `extended` query parameter to get additional metadata about each model's capabilities and supported features.
- [Retrieve Model](https://docs.perceptron.inc/perceptron-mk1/api-reference/endpoint/retrieve-model.md): Returns a specific model by its ID. Use the `extended` query parameter to get additional metadata about the model's capabilities and supported features.
- [Upload File](https://docs.perceptron.inc/perceptron-mk1/api-reference/endpoint/upload-file.md): Accepts a single file via multipart upload alongside a `purpose` field that declares how the file will be used. Subject to per-file and per-organization storage limits.
- [List Files](https://docs.perceptron.inc/perceptron-mk1/api-reference/endpoint/list-files.md): Returns a paginated list of files belonging to the caller's organization. Cursor pagination via `after`; see the `limit` and `order` parameters for defaults.
- [Retrieve File](https://docs.perceptron.inc/perceptron-mk1/api-reference/endpoint/retrieve-file.md): Returns metadata for a single file (size, content type, purpose, etc.). Use the `/v1/files/{file_id}/content` endpoint to download the bytes.
- [Retrieve File Content](https://docs.perceptron.inc/perceptron-mk1/api-reference/endpoint/retrieve-file-content.md): Returns the raw bytes with the file's stored `Content-Type` header.
- [Delete File](https://docs.perceptron.inc/perceptron-mk1/api-reference/endpoint/delete-file.md): Permanently deletes a file. Once deleted, the file can no longer be retrieved, downloaded, or referenced in requests. Returns 404 if no file with the given id exists.

## OpenAPI Specs

- [openapi](/api-reference/openapi.json)


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