Perceptron Mk1.5
4320°
Run this model
Offers / Ads
Perceptron | 36,864 token context | $0.15/M input, $1.50/M output. Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answers with text plus optional structured annotations: points, boxes, polygons, tracks, and clips. It supports graded reasoning through the standard reasoning controls, function tool calling, and structured outputs via JSON Schema. Structured annotations are emitted inline with text only when requested via the annotation_format parameter ("point", "box", or "polygon" for spatial localization on images, "clip" for temporal segments in video). Video soundtracks are analyzed only when explicitly enabled per request.
Guides for this model
Open weights vs open source vs API-only: what you are actually allowed to do
How to choose an AI model in October 2026: the closed source news, then the open weights worth downloading
The 10 cheapest ChatGPT alternatives in 2026: free local models, free tiers and flat-rate plans
Captain's notes
Notes from 2026-10-13
Perceptron Mk1.5 is Perceptron's reasoning model built for physical agents: it takes text, image, video, and audio as input and can return not just text but structured spatial and temporal annotations — bounding boxes, polygons, point localizations, and video clip segments. That output format is the differentiator; most multimodal models stop at text. It suits robotics pipelines, computer vision workflows, and any system that needs a model to reason about where something is, not just what it is.
Known for
- Returns structured spatial annotations: points, boxes, and polygons on images
- Temporal clip annotations for video, useful in agent and pipeline contexts
- Accepts text, image, video, and audio in a single request
- Function tool calling and JSON Schema structured outputs supported
- Graded reasoning depth via standard reasoning controls
Watch out for
- Closed weights, API-only — you cannot run this locally or inspect the model
- Video audio analysis is off by default; you must enable it per request explicitly
- Context window is 36,864 tokens, which is modest for long video or document work
Prompts to try
Locate objects in image
Attach an image of a cluttered desk. Return bounding boxes for every electronic device visible, with a one-word label for each. Use annotation_format: box.
Video segment extraction
I'm attaching a short video of a manufacturing line. Identify every interval where a human hand enters the frame and return those as clip annotations with start and end times and a brief description of what the hand is doing.
Agent action planning
You are controlling a mobile robot in a warehouse. The attached image is the robot's current camera view. Identify the nearest navigable path to the red shelf, describe any obstacles, and return a polygon annotation outlining the recommended travel corridor.
Compare with
- Perceptron Mk1API-only model32,768 token context · $0.15/M input, $1.50/M output
- DeepSeek V4.1 FlashOpen-weights model1,048,576 token context · $0.04/M input, $0.68/M output
- GLM 5.3 FlashOpen-weights model1,048,576 token context · $0.02/M input, $0.72/M output
- MiMo-V2.6-FlashOpen-weights model1,050,000 token context · $0.14/M input, $0.28/M output
More text models from perceptron
Questions people ask
- Can I run Perceptron Mk1.5 locally?
- No — the weights are not public and there is no Hugging Face repository. It is API-only.
- What does it cost and how long is the context?
- Pricing is $0.15 per million input tokens and $1.50 per million output tokens, with a context window of 36,864 tokens.
- How is this different from a standard multimodal model?
- Most multimodal models return text descriptions of what they see; Mk1.5 can also emit structured spatial annotations — points, boxes, polygons — and temporal clip markers for video, making it directly usable in agent and computer-vision pipelines without a separate parsing step.
Captain's verdictIf you need a model that tells you where something is — not just what it is — and can slot into an agent pipeline, Mk1.5 is purpose-built for that.
Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.
Ranking badge
Updated Oct 22, 2026
Made this model? Show this badge on your page.
Paste it into your Hugging Face card or Civitai description.
How this score adds up
This model has no popularity data from any source yet, so it carries a stand-in number below 7,000° that keeps the lists complete. It never ranks above a model with data. The breakdown appears here as soon as a source reports it.
Glossary: the terms used here
- Heat score
- One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
- Floor
- The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
- Download-equivalents
- Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
- Log scale
- Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
- Likes
- Thumbs up and likes from every source, worth half a download each on the log scale.
- Adoption rate
- How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
- Measured and estimated
- Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
- Seeder
- Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
- AI Horde
- A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
- Generation sites
- Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
- OpenRouter tokens
- A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
- Full model (checkpoint)
- The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
- LoRA and embedding
- Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
- Family and weights
- The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
- Age
- Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
- Family boost
- A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
- Stand-in score
- A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
- New! (grace period)
- A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
- Trend
- How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
- Typical model
- The middle of the catalog: half the models with a figure grew faster over the period, half slower.
Perceptron Mk1.5 is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.
Browse by Model Family
Text / LLM Models
434
Anima Models
528
Chroma Models
19
Fibo Models
2
Flux Models
1,496
Flux 2 / Klein Models
1,239
Flux 3 Models
3
Moss Models
3
Iris Models
1
MiniMax H3 Models
364
Hunyuan Models
204
Ideogram Models
20
Krea2 Models
717
Qwen Models
20
Qwen2 Models
47
Ltx2 Models
153