Perceptron Mk1
Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It accepts image and video inputs paired with natural language queries, and produces detailed visual understanding responses, either structured or natural language. It excels at video understanding tasks like video QA, summarization, and event detection. On image inputs, it advances point-by-example grounding from multimodal prompts, OCR and document parsing on messy real-world inputs, open vocabulary object detection and counting, and hand pose estimation. Reasoning can be enabled per request to trade latency for deeper analysis on harder tasks. Structured annotations are emitted inline with text only when explicitly requested via the annotation_format parameter (pass "point", "box", or "polygon" for spatial localization on images, or "clip" (start/end timestamps) for temporal segments in video). Without annotation_format, the model returns natural-language text only.
- Input / output price
- $0.15 / $1.50 per 1M
- Context
- 33K tokens
- Released
- May 12, 2026
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
One provider serves this model, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
OpenRouter openrouter/perceptron-mk1 | $0.15/M | $1.50/M |
Is a provider down? OpenRouter status
Pricing
USD per 1M tokens on OpenRouter, after gateway discounts.
- Input
- $0.15 per 1M
- Output
- $1.50 per 1M
Cost by volume
Total cost from 0 to 1T tokens.
Throughput and latency
30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.
Output speed
Higher is better2.9tokens/sacross providers
Response latency
Lower is better0.6sacross providers
Benchmarks
8 published scores from 1 source, each linked to where it was published.
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| ERQAperceptron.inc | 62.5% | perceptron.inc | May 12, 2026 |
| TOMATOperceptron.inc | 42.9% | perceptron.inc | May 12, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| NExT-QAperceptron.inc | 85.8% | perceptron.inc | May 12, 2026 |
| EmbSpatialBenchperceptron.inc | 85.1% | perceptron.inc | May 12, 2026 |
| Perception Testperceptron.inc | 80.8% | perceptron.inc | May 12, 2026 |
| EgoSchemaperceptron.inc | 80.6% | perceptron.inc | May 12, 2026 |
| TempCompassperceptron.inc | 77.2% | perceptron.inc | May 12, 2026 |
| MVBenchperceptron.inc | 74% | perceptron.inc | May 12, 2026 |
Apps
Use Perceptron Mk1 in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
Perceptron Mk1 FAQ
Short answers, built from the data on this page.
Perceptron Mk1 is a model from Perceptron, released on May 12, 2026. Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It accepts image and video inputs paired with natural language queries, and produces detailed visual understanding responses, either structured or natural language. It excels at video understanding tasks like video QA, summarization, and event detection. On image inputs, it advances point-by-example grounding from multimodal prompts, OCR and document parsing on messy real-world inputs, open vocabulary object detection and counting, and hand pose estimation. Reasoning can be enabled per request to trade latency for deeper analysis on harder tasks. Structured annotations are emitted inline with text only when explicitly requested via the annotation_format parameter (pass "point", "box", or "polygon" for spatial localization on images, or "clip" (start/end timestamps) for temporal segments in video). Without annotation_format, the model returns natural-language text only.
On the Respan gateway, Perceptron Mk1 costs $0.15 per 1M input tokens and $1.50 per 1M output tokens on OpenRouter, after gateway discounts.
Perceptron Mk1 is served by OpenRouter.
Perceptron Mk1 accepts up to 33K tokens of context.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "perceptron-mk1". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
Perceptron Mk1 has 8 published benchmark scores, including ERQA 62.5% and NExT-QA 85.8%. Each score links to where it was published; the data is collected by Respan.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.