> ## 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.

# Quickstart

> Get started with Perceptron Mk1.5 for image, video, and audio understanding, tracking, and tool calling.

Perceptron Mk1.5 understands images, video, and audio, grounds answers in space and time, and calls functions that your application provides. Use the same chat completions API for questions, transcription, structured extraction, object tracking, and tool-assisted workflows.

<CardGroup cols={2}>
  <Card title="Create an API key" icon="key" href="https://platform.perceptron.inc/">
    Get your key from the Perceptron platform
  </Card>

  <Card title="Join Discord" icon="discord" href="https://discord.gg/fgBeaACQzE">
    Get help and see what others are building
  </Card>
</CardGroup>

## Make your first request

Install the Perceptron Python SDK and set your API key:

```bash theme={null}
pip install "perceptron>=0.4.0"
export PERCEPTRON_API_KEY="your-api-key"
```

<CodeGroup>
  ```python Python theme={null}
  import os

  from perceptron import Client, image

  client = Client(
      api_key=os.environ["PERCEPTRON_API_KEY"],
      provider="perceptron",
  )

  response = client.chat.completions.create(
      model="perceptron-mk1.5",
      messages=[{
          "role": "user",
          "content": [
              image(
                  "https://raw.githubusercontent.com/perceptron-ai-inc/perceptron/"
                  "main/cookbook/_shared/assets/capabilities/qna/studio_scene.webp"
              ),
              {"type": "text", "text": "Describe this coastal scene and the visible objects."},
          ],
      }],
      max_completion_tokens=1024,
  )
  print(response.choices[0].message.content)
  ```

  ```bash curl theme={null}
  curl https://api.perceptron.inc/v1/chat/completions \
    -H "Authorization: Bearer $PERCEPTRON_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "perceptron-mk1.5",
      "messages": [{
        "role": "user",
        "content": [
          {"type": "image_url", "image_url": {"url": "https://raw.githubusercontent.com/perceptron-ai-inc/perceptron/main/cookbook/_shared/assets/capabilities/qna/studio_scene.webp"}},
          {"type": "text", "text": "Describe this coastal scene and the visible objects."}
        ]
      }],
      "max_completion_tokens": 1024
    }'
  ```
</CodeGroup>

Use the SDK’s `image()`, `video()`, and `audio()` helpers for local paths, bytes, URLs, or uploaded file references. Local paths and bytes are encoded inline; use [Files](/perceptron-mk1.5/guides/files) to upload once and reuse a file ID. See [Python setup](/perceptron-mk1.5/guides/python/getting-started) for a complete integration.

## Explore the capabilities

<CardGroup cols={2}>
  <Card title="Image understanding" icon="image" href="/perceptron-mk1.5/capabilities/image-understanding">
    Ask questions, read text, and locate objects.
  </Card>

  <Card title="Video understanding" icon="film" href="/perceptron-mk1.5/capabilities/video-understanding">
    Describe actions and locate events in time.
  </Card>

  <Card title="Video tracking" icon="crosshairs" href="/perceptron-mk1.5/capabilities/video-tracking">
    Follow objects with timestamped geometry inside track tags.
  </Card>

  <Card title="Tool calling" icon="wrench" href="/perceptron-mk1.5/capabilities/tool-calling">
    Connect the model to functions executed by your application.
  </Card>

  <Card title="Audio understanding" icon="waveform-lines" href="/perceptron-mk1.5/capabilities/audio">
    Summarize recordings, ask questions, transcribe speech, and locate events in time.
  </Card>

  <Card title="Reasoning" icon="brain" href="/perceptron-mk1.5/capabilities/thinking">
    Choose reasoning effort and budget for the final answer.
  </Card>

  <Card title="Multiple assets" icon="images" href="/perceptron-mk1.5/guides/multiple-assets">
    Compare media and map annotations with asset\_idx.
  </Card>

  <Card title="Structured outputs" icon="brackets-curly" href="/perceptron-mk1.5/capabilities/structured-outputs">
    Constrain final answers with JSON Schema or regex.
  </Card>
</CardGroup>

See the [model card](/perceptron-mk1.5/models/perceptron-mk1.5) for limits and pricing.

For production integrations, read [Tokenization](/perceptron-mk1.5/guides/tokenization), [Error messages](/perceptron-mk1.5/guides/error-messages), and [Scaling](/perceptron-mk1.5/guides/scaling).