> ## 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.
# Perceptron Mk1
> Best-in-class VLM with reasoning.
Perceptron Mk1 (short for "Mark 1") is our flagship closed-source vision-language model, with image, video, and reasoning support.
## Specs
* **Model ID**: `perceptron-mk1`
* **Inputs**: Text, Images, Videos
* **Outputs**: Text
* **Context**: 32K tokens
* **Reasoning**: Yes
* **Pricing**: \$0.15/M input, \$1.50/M output
* **Supported MIME types**: `image/png`, `image/jpeg`, `image/webp`, `video/mp4`, `video/webm`
* **Source**: Closed
## Trigger thinking & grounding
Mk1 uses the typed `vision_config` body field.
Pick `enable_thinking` based on the task: **on** for text Q\&A, captioning, OCR, and video clipping; **off** for spatial detection (`point`/`box`/`polygon`).
### Text / clipping — thinking on
```json theme={null}
{
"model": "perceptron-mk1",
"messages": [...],
"vision_config": { "enable_thinking": true }
}
```
### Spatial grounding — thinking off
```json theme={null}
{
"model": "perceptron-mk1",
"messages": [...],
"vision_config": { "annotation_format": "box" }
}
```
See the [API reference](/perceptron-mk1/api-reference/endpoint/chat-completions) for the full field reference and examples.
## Benchmarks
