playgroundLive API on your own workspace: 50 DecisionNode Flash requests, 20 DecisionNode MoE requests and 10 booster calls free a day
Ask typed questions. Get typed answers.
Paste any text, JSON or image, ask typed questions, and get typed answers with confidence in milliseconds. Every type names its answer: choice (one of your labels), score (a level on your scale), truth (a probability), number (a value on your grid), point (a spot in your image), box (a rectangle around the thing). Then copy the exact request as curl, Python, TypeScript or JSON.
endpoint
POST /v1/decide
models
DecisionNode MoEDecisionNode Flash
output tokens
0, always free
api key
your workspace's, after sign-in
State
Any text or JSON. Read once, shared by every question.
valid JSON, 3 top-level keys. Esc then Tab leaves the editor
reading...
reading...
Specialist readings of the pictures, handed to the model as evidence.priced per picture read
Human Ageage$0.024 a picture
Estimates a person's age from a face in the picture, using the agemin.com (opens in a new tab) age estimation model, ranked #1 by NIST for Child Online Safety (ages 13 to 16) on true positive rate.
Whether a picture was made by an image generator, and which kind, using Trinity, the state-of-the-art AI image detection model from detector24.ai (opens in a new tab).
runs without it if it is late
100 to 6000 ms; left empty, it gets its default.
reads
Face detectionface_detection$0.001 a picture
Finds the faces in a picture: how many it shows and where each one is, with a box and a confidence per face, from Bynn's face detection model.
Face recognitionface_recognitionfrom $0.001 a picture
Matches the faces in a picture against a collection: one of your own, enrolled through the API or the console, or the public celebrities collection. Each match carries a score and the item's reference, with your label or the public figure's name, and never a picture.
OCRocr$0.0015 a picture
The text a picture shows, read by Bynn OCR: all of it by default, or what a prompt asks for, such as a formula in LaTeX, a table in HTML or Markdown, or the fields of a JSON schema. Full support for English and Chinese; other languages need a prompt that names them.
Depth Visionbynn_depthfree
Distance in meters to what's in the picture: the nearest obstacle straight ahead, seven directions from left to right, and a grid of up to 16 by 16 cells. Estimates from one picture, for decisions and planning, never a safety stop.
Segment Visionbynn_segment$0.001 a picture
Finds what you name in words in the picture: each match's outline, box and centre, and with depth on, its distance and size in meters.
4 calls a run, at most $0.060. Only readings that come back are billed; up to 4 boosters a request.
Questions (3)
One typed answer each, from the same pass.
Is this statement true? One calibrated probability from 0.00 to 1.00 that the statement is true. 0.80 means true about 8 times in 10. Your code picks the cut-off: 0.50 for a plain yes or no, higher when acting on a false yes is costly.
returns one number from 0.00 to 1.00: the probability that the statement is true
returns one number from 0.00 to 1.00: the probability that the statement is true
Add
about 105 input tokens, output freeabout $3.68per million runs like thisper 1M runs
Reading the images...
Response
Run to see the API's answer.
Every question comes back in the shape its type defines, with how sure the model is. Output is always 0 tokens: nothing is generated.
Choiceone of your options, a probability for each
Scorethe expected level on your scale
TruthIs this statement true? One calibrated probability from 0.00 to 1.00 that the statement is true. 0.80 means true about 8 times in 10. Your code picks the cut-off: 0.50 for a plain yes or no, higher when acting on a false yes is costly.
Numbera value on your grid, the expected value, and a probability for every value
Pointone spot in an image, x and y, with present and confidence
Boxa rectangle around the thing, its corners, with present and confidence
