> ## 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
> Perceptron Mk1 — vision-language model that sees and reasons across images and video.
Perceptron Mk1 is a vision-language model that understands images and video. Ask it questions, detect objects, read text, get captions, or clip events — all through a simple API.
## Try Perceptron Mk1 in 30 seconds
Get your key from the Perceptron platform
Get help and see what others are building
Step through this example interactively
Step through this example interactively
Or pick your preferred method:
```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": "perceptron-mk1",
"messages": [
{
"role": "user",
"content": [
{"type": "video_url", "video_url": {"url": "https://raw.githubusercontent.com/perceptron-ai-inc/perceptron/main/cookbook/_shared/assets/tutorials/isaac_frame_by_frame/surf.mp4"}},
{"type": "text", "text": "What happens in this video?"}
]
}
],
"vision_config": { "enable_thinking": true }
}'
```
```python Python SDK theme={null}
from perceptron import configure, question, video
configure(
provider="perceptron",
model="perceptron-mk1",
api_key="YOUR_API_KEY", # Get yours at platform.perceptron.inc
)
result = question(
video("https://raw.githubusercontent.com/perceptron-ai-inc/perceptron/main/cookbook/_shared/assets/tutorials/isaac_frame_by_frame/surf.mp4"),
"What happens in this video?",
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="perceptron-mk1",
messages=[
{
"role": "user",
"content": [
{"type": "video_url", "video_url": {"url": "https://raw.githubusercontent.com/perceptron-ai-inc/perceptron/main/cookbook/_shared/assets/tutorials/isaac_frame_by_frame/surf.mp4"}},
{"type": "text", "text": "What happens in this video?"}
],
}
],
extra_body={"vision_config": {"enable_thinking": True}},
)
print(response.choices[0].message.content)
```
**Using Python?** Install with `pip install perceptron` or `pip install openai`
**Supported image formats:** JPEG, PNG, WebP — pass a URL or local file path.
**Supported video formats:** MP4, WebM — pass a URL or local file path.
Outputs are deterministic by default (`temperature` defaults to `0.0`). See [API Reference](/perceptron-mk1/api-reference/endpoint/chat-completions) for all parameters.
## Explore our developer guides
Ask questions about images and get grounded answers
Ask questions about video and get answers grounded in time
Locate targets with precise bounding boxes
Find events in video and return start/end timestamps
Extract text from images and documents
Generate descriptions of images
Adapt Perceptron Mk1 to image tasks with a handful of examples
Adapt Perceptron Mk1 to video tasks with a handful of examples
***
## [Models overview](/perceptron-mk1/models)
| Model | Best for | Speed | Latest update |
| ---------------------- | ------------------------------------------------------- | -------- | ------------- |
| `perceptron-mk1` | Image & Video, reasoning enabled | Standard | 2026-05-12 |
| `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 |
| `isaac-0.1` | Images (legacy support) | Fast | 2025-09-17 |
### Perceptron Mk1
Best-in-class closed-source VLM with reasoning — accepts image and video inputs. ("Mk1" is short for "Mark 1".)
* **Model ID**: `perceptron-mk1`
* **Context**: 32K tokens
* **Reasoning**: Yes
* **Pricing**: \$0.15/M input, \$1.50/M output
* Closed source
### 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)
### isaac-0.1
Original 2B VLM, still supported for existing integrations.
* **Model ID**: `isaac-0.1`
* **Context**: 8K tokens
* **Reasoning**: No
* **Pricing**: \$0.15/M input, \$1.25/M output
* [Open weights on Hugging Face](https://huggingface.co/PerceptronAI/Isaac-0.1)
## Benchmarks
Perceptron Mk1 benchmark results:
