# Perceptron Docs

## Docs

- [Chat Completions](https://docs.perceptron.inc/api-reference/endpoint/chat-completions.md)
- [List Models](https://docs.perceptron.inc/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/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.
- [Prompting reference](https://docs.perceptron.inc/best-practices/prompting-reference.md): Copy-paste prompts and code for each SDK primitive.
- [Prompting tips](https://docs.perceptron.inc/best-practices/prompting-tips.md): Techniques to improve accuracy, reduce verbosity, and get better results.
- [Security](https://docs.perceptron.inc/best-practices/security.md): Protect keys, data, and edge deployments
- [Captioning](https://docs.perceptron.inc/capabilities/captioning.md): Generate concise or detailed descriptions for any scene.
- [Focus](https://docs.perceptron.inc/capabilities/focus.md): Let Isaac zoom into image regions via tool calls for fine-grained answers.
- [In-context learning](https://docs.perceptron.inc/capabilities/in-context-learning.md): Teach Isaac a new visual concept with one or many annotated examples.
- [Object detection](https://docs.perceptron.inc/capabilities/object-detection.md): Prompt Isaac to return grounded detections with normalized geometry.
- [OCR](https://docs.perceptron.inc/capabilities/ocr.md): Extract structured text with grounded prompts.
- [Structured outputs](https://docs.perceptron.inc/capabilities/structured-outputs.md): Constrain model replies to Pydantic, JSON schemas or regex for reliable parsing.
- [Thinking](https://docs.perceptron.inc/capabilities/thinking.md): Use reasoning traces to inspect how the model reached an answer.
- [Visual Q&A](https://docs.perceptron.inc/capabilities/visual-qa.md): Ask grounded questions about any scene.
- [Changelog](https://docs.perceptron.inc/changelog.md): Changelog
- [Coordinate system](https://docs.perceptron.inc/concepts/coordinates.md): Why normalized coordinates matter
- [Batch processing](https://docs.perceptron.inc/guides/batch.md): Process thousands of images with async workflows
- [Error messages](https://docs.perceptron.inc/guides/error-messages.md): Diagnose and resolve common Perceptron API errors
- [Tokenization guide](https://docs.perceptron.inc/guides/image-tokens.md)
- [MCP](https://docs.perceptron.inc/guides/mcp.md): AI agents can interact with Perceptron's vision capabilities through our MCP server.
- [Authentication](https://docs.perceptron.inc/guides/python-sdk/auth.md): Learn how to configure credentials and authenticate with the Perceptron SDK.
- [Python SDK FAQs](https://docs.perceptron.inc/guides/python-sdk/faqs.md): Answers to the most common questions about Perceptron’s Python client.
- [Get started](https://docs.perceptron.inc/guides/python-sdk/getting-started.md): Install the Perceptron Python SDK, configure credentials, and send your first request.
- [Perceive basics](https://docs.perceptron.inc/guides/python-sdk/perceive-basics.md): Learn the Perceptron Perceive decorator, core nodes, and the patterns for authoring your first multimodal prompt.
- [Pointing basics](https://docs.perceptron.inc/guides/python-sdk/pointing-basics.md): Understand Perceptron point, box, polygon, and collection types and when to choose each for your application.
- [Scaling guide](https://docs.perceptron.inc/guides/scaling.md): Meet throughput and latency goals with Isaac
- [Frame-by-frame tutorial](https://docs.perceptron.inc/guides/tutorials/frame-by-frame.md)
- [Quickstart](https://docs.perceptron.inc/index.md): Vision-language models that see, reason, and act.

## OpenAPI Specs

- [openapi](https://docs.perceptron.inc/api-reference/openapi.json)