> ## 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

> Isaac 0.2 — open-weights image-based vision-language models.

Isaac 0.2 is the second generation of Perceptron's open-weights image-based vision-language family. Ask questions about images, detect objects, read text, get captions — through the hosted API or by self-hosting the weights from Hugging Face.

The 0.2 family ships in two sizes:

* **`isaac-0.2-2b-preview`** — best-in-class 2B reasoning model with sub-200ms TTFT. [Open weights on Hugging Face](https://huggingface.co/PerceptronAI/Isaac-0.2-2B-Preview).
* **`isaac-0.2-1b`** — compact 1B edge-deployable variant. [Open weights on Hugging Face](https://huggingface.co/PerceptronAI/Isaac-0.2-1B).

## Try Isaac 0.2 in 30 seconds

<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>

<Card icon="play" title="Get started with Image" href="https://colab.research.google.com/github/perceptron-ai-inc/perceptron/blob/main/cookbook/quickstart/quickstart_isaac_0_2/quickstart_isaac_0_2.ipynb">
  Step through this example interactively
</Card>

Or pick your preferred method:

<CodeGroup>
  ```bash curl theme={null}
  curl -X POST "https://api.perceptron.inc/v1/chat/completions" \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer $PERCEPTRON_API_KEY" \
    -d '{
    "model": "isaac-0.2-2b-preview",
    "messages": [
      { "role": "system", "content": "<hint>THINK</hint>" },
      {
        "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": "What stands out in this scene?"}
        ]
      }
    ]
  }'
  ```

  ```python Python SDK theme={null}
  from perceptron import configure, image, question

  configure(
      provider="perceptron",
      model="isaac-0.2-2b-preview",
      api_key="YOUR_API_KEY",  # Get yours at platform.perceptron.inc
  )

  result = question(
      image("https://raw.githubusercontent.com/perceptron-ai-inc/perceptron/main/cookbook/_shared/assets/capabilities/qna/studio_scene.webp"),
      "What stands out in this scene?",
      reasoning=True,
  )
  print(result.text)
  ```

  ```python OpenAI SDK theme={null}
  from openai import OpenAI

  client = OpenAI(
      api_key="YOUR_API_KEY",  # Get yours at platform.perceptron.inc
      base_url="https://api.perceptron.inc/v1",
  )

  response = client.chat.completions.create(
      model="isaac-0.2-2b-preview",
      messages=[
          {"role": "system", "content": "<hint>THINK</hint>"},
          {
              "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": "What stands out in this scene?"}
              ],
          }
      ],
  )

  print(response.choices[0].message.content)
  ```
</CodeGroup>

<Callout type="tip">
  **Using Python?** Install with `pip install perceptron` or `pip install openai`. To trigger reasoning or grounding via raw chat completions, use `<hint>THINK</hint>`, `<hint>BOX</hint>`, `<hint>POINT</hint>`, or `<hint>FOCUS</hint>` as a system-role message.
</Callout>

**Supported image formats:** JPEG, PNG, WebP — pass a URL or local file path.

Outputs are deterministic by default (`temperature` defaults to `0.0`). See [API Reference](/isaac-0.2/api-reference/endpoint/chat-completions) for all parameters.

## Explore Isaac 0.2 capabilities

<CardGroup cols={2}>
  <Card title="Image Q&A" icon="glasses-round" href="/isaac-0.2/capabilities/image-qa">
    Ask questions about images and get grounded answers
  </Card>

  <Card title="Object Detection" icon="camera-security" href="/isaac-0.2/capabilities/object-detection">
    Locate targets with precise bounding boxes
  </Card>

  <Card title="OCR" icon="text" href="/isaac-0.2/capabilities/ocr">
    Extract text from images and documents
  </Card>

  <Card title="Image Captioning" icon="closed-captioning" href="/isaac-0.2/capabilities/image-captioning">
    Generate descriptions of images
  </Card>

  <Card title="In-Context Learning" icon="sparkles" href="/isaac-0.2/capabilities/in-context-learning-image">
    Adapt Isaac 0.2 to image tasks with a handful of examples
  </Card>

  <Card title="Structured Outputs" icon="brackets-curly" href="/isaac-0.2/capabilities/structured-outputs">
    Constrain replies to Pydantic, JSON schemas, or regex
  </Card>
</CardGroup>

***

## [Models overview](/isaac-0.2/models)

| Model                  | Best for                                                | Speed   | Latest update |
| ---------------------- | ------------------------------------------------------- | ------- | ------------- |
| `isaac-0.2-2b-preview` | Image, reasoning enabled                                | Fast    | 2025-12-10    |
| `isaac-0.2-1b`         | Image, reasoning enabled, low-latency / edge deployment | Fastest | 2025-12-10    |

<Accordion title="Model details">
  ### isaac-0.2-2b-preview

  Best-in-class open-weights 2B VLM with reasoning. Sub-200ms time-to-first-token.

  * **Model ID**: `isaac-0.2-2b-preview`
  * **Context**: 8K tokens
  * **Reasoning**: Yes
  * **Pricing**: \$0.15/M input, \$1.25/M output
  * [Open weights on Hugging Face](https://huggingface.co/PerceptronAI/Isaac-0.2-2B-Preview)

  ### isaac-0.2-1b

  Compact 1B VLM with reasoning, optimized for edge and low-latency deployments.

  * **Model ID**: `isaac-0.2-1b`
  * **Context**: 8K tokens
  * **Reasoning**: Yes
  * **Pricing**: \$0.15/M input, \$1.25/M output
  * [Open weights on Hugging Face](https://huggingface.co/PerceptronAI/Isaac-0.2-1B)
</Accordion>