P
LLMperceptron

Perceptron: 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...

Anyone in the Space can @-mention Perceptron: Perceptron Mk1 with the team's shared context — pooled credits, one chat, one memory.

All models

Starter is free forever — 1 Space, 100 credits/month, 1 MCP. No card.

Verdict

Perceptron Mk1 is a multimodal model that handles text, images, and video at an aggressive price point — $0.15 input makes it one of the cheapest options for high-volume workloads. The 32K context window is adequate for most tasks but constrains long-document work. Without public benchmarks, you're buying on price and modality support rather than proven performance. Reach for this when cost matters more than leaderboard rankings and you need basic vision or video understanding baked in.

Best for

  • High-volume multimodal processing on budget
  • Video frame analysis at scale
  • Cost-sensitive image captioning
  • Prototyping vision features before scaling
  • Batch jobs where latency isn't critical

Strengths

The standout is pricing: $0.15 per million input tokens undercuts most competitors by 3-5x, making this viable for batch jobs that would bankrupt you elsewhere. Native video support is rare at this price tier — most budget models stop at images. The 32K context window handles typical documents, code files, and multi-image prompts without chunking. Multimodal capability means you can throw screenshots, diagrams, or video clips at it without switching models mid-workflow.

Trade-offs

No public benchmarks means you're flying blind on accuracy relative to Claude, GPT-4o, or Gemini. The 32K context ceiling blocks serious long-document analysis — you'll hit limits around page 20 of a dense PDF. Output pricing at $1.50/Mtok is 10x the input rate, so verbose responses get expensive fast. Early-stage models often lag on reasoning depth and instruction-following compared to established players. Expect to iterate on prompts more than you would with a top-tier model.

Specifications

Provider
perceptron
Category
llm
Context length
32,768 tokens
Max output
8,192 tokens
Modalities
text, image, video
License
proprietary
Released
2026-05-12

Pricing

Input
$0.15/Mtok
Output
$1.50/Mtok
Model ID
perceptron/perceptron-mk1

Per-token prices show what the model costs upstream. On Switchy your team draws from one shared org credit pool — one plan, one balance for everyone.

Team cost calculator

Estimated monthly spend
$9.77
17.6M tokens / month
5 seats · 80 msgs/day

Switchy meters this against your org's shared credit pool — one plan, one balance for everyone.

Providers

Provider-level routing data is not available yet for this model.

Performance

Performance snapshots are collected daily. Check back after the next ingestion run.

Benchmarks

Public benchmark scores are not available yet for this model. Check back after the next ingestion run.

Works well with

Top MCPs

Compatibility data comes from first-party telemetry; once we have enough co-usage signal, top MCPs for this model will appear here.

How Switchy teams use it

Not enough Spaces have used this model yet to share anonymised team stats. We wait for at least 50 distinct Spaces per week before publishing any aggregate.

Starter prompts

Extract Invoice Line Items

Extract all line items from this invoice image into a JSON array. Each item should include description, quantity, unit price, and total. Return only valid JSON with no explanation.
Open in a Space →

Summarize Video Meeting

Watch this meeting recording and list the key decisions made and action items assigned. Format as bullet points with owner names where mentioned.
Open in a Space →

Caption Product Photos

Write a 2-sentence product description for this image. First sentence describes what's shown, second highlights a key feature or benefit. Keep it under 40 words total.
Open in a Space →

Compare Screenshot Versions

Compare these two screenshots and list every visual difference you notice. Focus on layout changes, color shifts, and text edits. Be specific about locations.
Open in a Space →

Classify Support Tickets

Read this support ticket and assign it to one category: Billing, Technical, Account, or Feature Request. Reply with only the category name and a 1-sentence reason.
Open in a Space →
Data last verified 1 hour ago.Sources aggregated hourly to weekly. See docs/architecture/model-directory.md.