What is a decision model, and how is it different from a chat model?

A chat model writes its answer token by token, so a short answer takes half a second to several seconds and rarely answers the same way twice. DecisionNode reads your input once and answers your typed questions in one pass: a choice, a score or a Truth probability, each with how sure the model is. It generates no text, so it answers in milliseconds.

What are the question types?

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). Choice picks one option from the list you send and returns a probability for each. Score places the input on your ordered scale, for example routine to critical, and returns the expected level. Truth (truth in the API) asks whether a statement is true: DecisionNode returns one calibrated probability from 0.00 to 1.00 that it is, so 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. Number (number in the API) asks: How many, or what value? One value on a grid you set (min, max and an optional step), with a calibrated probability for every value: the most probable value, the expected value and the confidence. A count of cars in a photo, overdue invoices in a statement, a year, a rating out of ten.

How does pricing work, and why is output free?

You pay per million input tokens from a prepaid balance: $0.042 on DecisionNode-1.0, $0.021 on DecisionNode-1.0 Flash. The model writes no text, so every response reports output_tokens: 0 and output never costs anything. No seats, no minimums.

Which model should I pick, DecisionNode-1.0 or DecisionNode-1.0 Flash?

DecisionNode-1.0 Flash when speed and volume come first: about 5 ms on a short request, at $0.021 per million input tokens. DecisionNode-1.0 for the hard calls, where accuracy matters most. Many builds run both: Flash first, and any answer under your confidence threshold is re-checked on DecisionNode-1.0 before your code acts.

Yes. Send images next to your text in the same request. The model reads printed and handwritten text, amounts, dates, objects and layout, and answers through the same question types.

When should I use a session? (coming soon)

More than 10 decisions a second? Use a session. It is built for loops: survey, inspection and delivery drones, simulators and games, machine monitoring, long-running agents. You open it once with the instructions, the fixed state and the questions, then stream frames (text, JSON or an image) over one WebSocket and get a typed decision back for each frame. Your context stays loaded for the whole session, so each frame costs only its own tokens, and a client that falls behind gets the newest frame answered, never a backlog, with the skipped frames reported. A session is a decision layer that feeds your controller: the vehicle's own control loop keeps flying it.

Yes. The same request to the same model version returns the same answer, every time. There is no sampling, so your tests hold and every logged decision can be replayed.

Get an API key, paste one curl and branch on the typed answer. The quickstart takes under five minutes, and the playground runs any request in your browser first.

What data do you keep?

Requests are processed to return your answers and to run the service. We do not train our models on your data without your written consent. Inputs and answers are deleted 30 days after each request by default, and zero retention is available on request. The Privacy Policy and the Data Processing Addendum have the details; questions go to privacy@bynn.com.

api all systems normal

Get API key

decision model + inference api

Typed decisions in milliseconds.

Text, JSON or images in. A choice, a score or a Truth probability out, calibrated, in 5 ms on our own GPUs.

Get API key

Open playground

$0.042 per million input tokens

output is free / no sales call

live

DecisionNode-1.0 Flash

choice

decisionnode-flash-latest

...

“Charged twice and no reply yet.”

Where should this ticket go?

billing...
bug...
account...

auto-refund?acts at 0.80

refund...

confidence...

acts at 0.70deciding

Billing, refund sent

billing + refund

Routed to its queue

otherwise

1,284 actions taken

61 re-checked first

last decisions / on our own GPUsp50 5 ms

09:41:02sort parcelreturns 0.836 ms
09:41:01check chargefraud 0.12 false4 ms
09:40:58moderate postseverity 0.414 ms

New ticketwebhook

api all systems normal

Get API key

decision model + inference api

Typed decisions in milliseconds.

Text, JSON or images in. A choice, a score or a Truth probability out, calibrated, in 5 ms on our own GPUs.

Get API key

Open playground

$0.042 per million input tokens

output is free / no sales call

live

DecisionNode-1.0 Flash

choice

decisionnode-flash-latest

...

“Charged twice and no reply yet.”

Where should this ticket go?

billing...
bug...
account...

auto-refund?acts at 0.80

refund...

confidence...

acts at 0.70deciding

Billing, refund sent

billing + refund

Routed to its queue

otherwise

1,284 actions taken

61 re-checked first

last decisions / on our own GPUsp50 5 ms

09:41:02sort parcelreturns 0.836 ms
09:41:01check chargefraud 0.12 false4 ms
09:40:58moderate postseverity 0.414 ms

New ticketwebhook

one HTTPS call from anything you already run

any http client / POST /v1/decide

typescriptts/jsdn.decide()
pythonpythondn.decide()
gogodn.Decide()
rubyrubydn.decide
/v1/decideDecisionNode
curlcurl-X POST
mcpmcptools/call
webhookswebhookson event
agentsagentsbefore acting

same order, two engines

Sixteen answers before the first word.

The same order and the same sixteen checks. DecisionNode answers them all in one pass while a chat LLM is still writing.

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.

DecisionNode-1.0 Flash

POST /v1/decide, one call

request200 OK16 questions, one callmodel decisionnode-1.0-flash
fraud_risktruthTasked0.04 false
address_validtruthTasked0.97 true
gift_ordertruthTasked0.93 true
ship_lanechoiceCaskedstandard 0.88
carrierchoiceCaskedcourier 0.81
priorityscoreSasked1.8 of 3
fragile_itemstruthTasked0.91 true
needs_signaturetruthTasked0.22 false
customs_formtruthTasked0.03 false
promo_abusetruthTasked0.71 true
duplicate_ordertruthTasked0.06 false
stock_reservedtruthTasked0.99 true
packagingchoiceCaskedpadded 0.76
delivery_riskscoreSasked0.6 of 4
split_shipmenttruthTasked0.12 false
next_actionchoiceCaskedship 0.84
usagepending410 tokens in, 0 out

a chat LLM

chat completion, "reply in JSON"

time to all 16 answers: 25 ms against 3.40 s
cost of this order: 0.00086¢ against 0.42¢
price ratio: about 480× cheaper

DecisionNode-⁠1.0 Flash against Claude Sonnet 5.5, the median of the 8 general LLMs on our benchmarks page. Time: DecisionNode-⁠1.0 Flash's 19 ms end-to-end median plus 6 ms for the extra questions; Claude Sonnet 5.5's first token at 630 ms, then 126 output tokens at 22 ms each. Cost is tokens times list price: 410 input tokens at $0.021 per 1M, output free, against 756 input tokens at $3 and 126 output tokens at $15 per 1M. Mock timings. Preliminary results, October 2026.

See every model compared

Race: sixteen checks on one order, DecisionNode-1.0 Flash against a chat LLM
check	DecisionNode-1.0 Flash, typed answer	a chat LLM, text answer
Is this order fraud? (truth)	0.04 false	"fraud_risk": "low"
Is the address deliverable? (truth)	0.97 true	"address_valid": "yes"
Is this a gift? (truth)	0.93 true	"gift_order": "true"
Which ship lane? (choice)	standard 0.88	"ship_lane": "standard shipping"
Which carrier? (choice)	courier 0.81	"carrier": "courier"
How urgent, 0 to 3? (score)	1.8 of 3	"priority": "medium-high"
Any fragile items? (truth)	0.91 true	"fragile_items": "yes, the lamp"
Needs a signature? (truth)	0.22 false	"needs_signature": "probably not"
Needs a customs form? (truth)	0.03 false	"customs_form": "no"
Is the promo code abused? (truth)	0.71 true	"promo_abuse": "possibly"
Is this a duplicate order? (truth)	0.06 false	"duplicate_order": "no"
Is the stock reserved? (truth)	0.99 true	"stock_reserved": "yes"
Which packaging? (choice)	padded 0.76	"packaging": "padded box"
Delivery risk, 0 to 4? (score)	0.6 of 4	"delivery_risk": "low"
Split into two parcels? (truth)	0.12 false	"split_shipment": "false"
Ship, hold, route or flag? (choice)	ship 0.84	"next_action": "ship it"

time to all 16 answers: 25 ms against 3.40 s
cost of this order: 0.00086¢ against 0.42¢
price ratio: about 480× cheaper

the decision model

A model built to decide.

Hand-written rules break on the first message nobody planned for. Chat models word the same answer differently every time. DecisionNode returns a typed answer and how sure it is, the same way every time.

How a decision runs

in
State and questions
text, JSON or images
call
One request
POST /v1/decide
model
Our model on our GPUs
one pass, no text generated
out
Typed answers
a choice, a score or a truth
branch
Your code branches
confidence < 0.70

Four ways to ask

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). One message, four questions:

state“Customer: I was charged twice and nobody has replied for 3 days.”

question

"route": {
  "type": "choice",
  "criteria": {
    "billing": "money",
    "bug": "broken",
    "account": "login"
  }
}

answer

"route": {
  "type": "choice",
  "choice": "billing",
  "confidence": 0.81,
  "probabilities": {
    "account": 0.05,
    "billing": 0.87,
    "bug": 0.08
  }
}

question

"urgency": {
  "type": "score",
  "criteria": [
    "routine", "today",
    "urgent", "critical"
  ]
}

answer

"urgency": {
  "type": "score",
  "score": 2.31,
  "confidence": 0.47,
  "probabilities": {
    "0": 0.01, "1": 0.09,
    "2": 0.48, "3": 0.42
  }
}

question

"refund": {
  "type": "truth",
  "instructions":
    "Refund this automatically?",
  "criteria": {
    "true":
      "Charged twice for the same order",
    "false":
      "Any other billing issue"
  }
}

answer

"refund": {
  "type": "truth",
  "truth": 0.94
}

question

"days_waiting": {
  "type": "number",
  "instructions":
    "Days without a reply?",
  "min": 0,
  "max": 30
}

answer

"days_waiting": {
  "type": "number",
  "number": 3,
  "expected": 3.06,
  "confidence": 0.88,
  "probabilities": {
    "2": 0.04, "3": 0.88,
    "4": 0.06, "5": 0.02
  }
}

returns choice, probabilities, confidenceTry it in the playground

One request answers every question

Send the state once with every question you have. It is read in one pass and shared, so ten questions cost about the same as one.

POST /v1/decide

stateread once0.0 ms62 tokens
routechoicebilling
urgencyscore2.31 urgent
refundtruth0.94 true

zoomin parallelroute+0.4 msurgency+0.5 msrefund+0.3 ms

62 input tokens, 0 output1 pass, no text generated

Confidence you can act on

Every answer says how sure the model is, and the numbers are calibrated. Set a line once: above it your code acts instantly. Below it, the full model checks the same request again, or your code takes the safe path. Nobody waits.

ticket 4471routeact at

DecisionNode-1.0 Flashbilling, 4.8 msbelow line
re-checkDecisionNode-1.0billing, +8.1 msabove line
actedmoved to billing, reply sent12.9 ms

>if (flash.confidence >= 0.70) act()>else if (full.confidence >= 0.70) act()>else safePath()

Text and images in one call

Attach a photo to the same request. The model reads printed text, amounts and layout, and answers with the same question types.

Photo of a till receipt from Kaffebar Norr in Stockholm, total 188,00 kr with 12% moms — which currency is on this receipt?choice, image + text

which currency is on this receipt?choice, image + text

[ a model company and an inference company ][ model company, inference company ]

We build the decision modeland the machine it runs on.

one tick, one decision

now

inference

Fast because we own the path.

Our own decision model on our own inference stack and GPUs. No third-party API between your request and the answer.

Every hop is ours

One pass, no text generation, nothing in between. DecisionNode-⁠1.0 Flash answers a short request in about 5 ms.

the path of one request

requestyour app
read oncetext, images
questionsat once
decideour stack

no sampling: same answer every time

One fleet, two models

Both models run on our own GPUs behind one API. Switch with the model field; nothing else changes.

share of traffic, last hour

DecisionNode-1.0
decisionnode-latest
p50
9 ms
per 1M in
$0.042
share
61%
DecisionNode-1.0 Flash
decisionnode-flash-latest
p50
5 ms
per 1M in
$0.021
share
39%

same request, same answer

Done before an LLM writes a word

A chat LLM writes its answer token by token and needs half a second to four seconds. DecisionNode reads the input once and answers in one pass, fast enough for every request, every payment, every robot frame.

End to end from one client, network included, one short decision. The chat LLM band spans 8 general LLMs on the same decision. Preliminary results, October 2026.

time to a typed answer, end to end, log scale

DecisionNode-1.0 Flash
5 ms on our side
DecisionNode-1.0
9 ms on our side
a chat LLM
8 LLMs 540 to 4,060 ms

Time to a short typed answer, end to end from one client, on a log scale: DecisionNode-1.0 Flash 19 ms, DecisionNode-1.0 24 ms, general LLMs 540 to 4,060 ms.
model	time to answer	note
DecisionNode-1.0 Flash	19 ms	5 ms on our side
DecisionNode-1.0	24 ms	9 ms on our side
a chat LLM	1,290 ms	8 general LLMs, 540 to 4,060 ms

28× to 214× faster on Flash

Paste your own request and watch the clock.

How we measured Open playground

sessions

A decision for every frame.

Open one session, send the fixed part once, then stream frames over a WebSocket. Every frame comes back as a typed decision, a decision layer that feeds your controller.

POST /v1/sessionscoming soonsession opening

sent once instructions, mission brief, geofence, 2 questions, window 8, model decisionnode-latest

each frame bills only its own tokens

Survey drone, line inspection

/v1/sessions/ses_7f3a/stream

frames in0

frametelemetry JSON; text and images work too

window 8leaves context

contextsent once

Typed decisions

decisions out0

waiting for the first frame

More than 10 decisions a second? Use a session.

Same models, same typed and calibrated answers, the same safety check on every frame. The context is billed once when the session opens; each frame, its own tokens.

Read the sessions docs

A survey drone streams telemetry frames into one session; every frame is answered with a flight mode and an abort probability
frame	telemetry	mode: Which flight mode now?	abort: Should the mission be aborted now?
1	battery 0.64, wind 4.2 m/s, 155 m from home	continue 0.93, confidence 0.91 (continue 0.93, hold 0.04, return 0.02, land 0.01)	0.02 false
2	battery 0.63, wind 4.6 m/s, 225 m from home	continue 0.93, confidence 0.91 (continue 0.93, hold 0.04, return 0.02, land 0.01)	0.02 false
3	battery 0.61, wind 5.1 m/s, 295 m from home	continue 0.92, confidence 0.89 (continue 0.92, hold 0.05, return 0.02, land 0.01)	0.02 false
4	battery 0.60, wind 5.8 m/s, 365 m from home	continue 0.91, confidence 0.88 (continue 0.91, hold 0.05, return 0.03, land 0.01)	0.03 false
5	battery 0.58, wind 6.6 m/s, 435 m from home	continue 0.88, confidence 0.84 (continue 0.88, hold 0.07, return 0.04, land 0.01)	0.03 false
6	battery 0.56, wind 8.9 m/s, 500 m from home	continue 0.71, confidence 0.61 (continue 0.71, hold 0.22, return 0.06, land 0.01)	0.06 false
7	battery 0.54, wind 11.8 m/s, 530 m from home	hold 0.62, confidence 0.49 (continue 0.27, hold 0.62, return 0.09, land 0.02)	0.14 false
8	battery 0.52, wind 12.6 m/s, 535 m from home	hold 0.71, confidence 0.61 (continue 0.19, hold 0.71, return 0.08, land 0.02)	0.17 false
9	battery 0.51, wind 12.2 m/s, 535 m from home	latest wins: skipped, a newer frame came in
10	battery 0.50, wind 11.4 m/s, 540 m from home	latest wins: skipped, a newer frame came in
11	battery 0.48, wind 9.6 m/s, 565 m from home	continue 0.58, confidence 0.44 (continue 0.58, hold 0.33, return 0.07, land 0.02)	0.09 false
12	battery 0.45, wind 9.2 m/s, 635 m from home	continue 0.69, confidence 0.59 (continue 0.69, hold 0.23, return 0.06, land 0.02)	0.06 false
13	battery 0.42, wind 10.1 m/s, 705 m from home	continue 0.62, confidence 0.49 (continue 0.62, hold 0.21, return 0.15, land 0.02)	0.06 false
14	battery 0.39, wind 10.6 m/s, 770 m from home	continue 0.44, confidence 0.25 (continue 0.44, hold 0.17, return 0.37, land 0.02)	0.07 false
15	battery 0.36, wind 11.0 m/s, 835 m from home	return 0.52, confidence 0.36 (continue 0.31, hold 0.14, return 0.52, land 0.03)	0.08 false
16	battery 0.34, wind 11.2 m/s, 830 m from home	return 0.71, confidence 0.61 (continue 0.17, hold 0.09, return 0.71, land 0.03)	0.08 false
17	battery 0.31, wind 11.4 m/s, 820 m from home	return 0.84, confidence 0.79 (continue 0.09, hold 0.05, return 0.84, land 0.02)	0.07 false
18	battery 0.29, wind 11.9 m/s, 750 m from home	return 0.88, confidence 0.84 (continue 0.06, hold 0.04, return 0.88, land 0.02)	0.06 false
19	battery 0.27, wind 12.3 m/s, 670 m from home	return 0.90, confidence 0.87 (continue 0.05, hold 0.03, return 0.90, land 0.02)	0.06 false
20	battery 0.25, wind 12.8 m/s, 585 m from home	return 0.91, confidence 0.88 (continue 0.04, hold 0.03, return 0.91, land 0.02)	0.06 false

console

Your decisions, live.

The console every workspace gets, shown with sample data: volume, confidence, latency and every action your software took on its own.

decisions per hour, last 7 days

decisions per hour, last 7 days, per hour
hours	wed	thu	fri	sat	sun	mon	tue
00 to 03	2.3k	2.5k	2.4k	2.0k	1.8k	2.6k	2.7k
03 to 06	1.5k	1.7k	1.6k	1.3k	1.1k	1.8k	1.9k
06 to 09	4.0k	4.3k	3.9k	2.3k	2.0k	4.4k	4.6k
09 to 12	11.2k	12.1k	11.0k	4.8k	4.2k	12.6k	13.0k
12 to 15	15.6k	16.4k	14.8k	6.3k	5.7k	17.1k	17.4k
15 to 18	14.1k	15.2k	13.0k	6.0k	5.5k	15.8k	later today
18 to 21	8.8k	9.6k	8.1k	4.6k	4.3k	10.0k	later today
21 to 24	4.5k	4.9k	4.6k	3.1k	2.9k	5.1k	later today

acted on at once

Share of decisions acted on at once this hour: 84%

of decisions cleared the 0.70 threshold

actions taken, live

2784 re-checked by DecisionNode this hour

confidence over the week

acted on at onceat once
re-checked firstre-checked

Average confidence per day: answers acted on at once stay near 0.92, answers re-checked by DecisionNode came in near 0.55, under the 0.70 threshold. Use the arrow keys to read each day.
day	acted on at once	re-checked first
wed	0.90	0.52
thu	0.92	0.56
fri	0.89	0.49
sat	0.93	0.58
sun	0.94	0.61
mon	0.91	0.54
tue	0.92	0.55

server latency, last hour

Request in to answer out, both models.

Histogram of server latency over the last hour, both models: p50 7 milliseconds, p99 21 milliseconds.
ms	of requests
0 to 2	1%
2 to 4	9%
4 to 6	24%
6 to 8	22%
8 to 10	15%
10 to 12	10%
12 to 14	7%
14 to 16	5%
16 to 18	3%
18 to 20	2%
20 to 22	1%
22 to 24	1%

Every workspace gets this console from its first request.

Open the console Get API key

benchmarks

How accurate it is, measured.

15 suites of real decisions, from policy rules to web tasks and prompt injection. Every system answered the same items.

15-suite mean

Mean accuracy over every text suite, one dot per system.

25,134 items

Preliminary results, October 2026

3Cloudflare Clef 27B0.786, 95% interval 0.778 to 0.794
5Cloudflare Clef-flash 9B0.759, 95% interval 0.750 to 0.767
7Cygnet (Gemma 4 12B)0.718, 95% interval 0.710 to 0.726
1DecisionNode-1.0ours0.817, 95% interval 0.809 to 0.825
4DecisionNode-1.0 Flashours0.780, 95% interval 0.771 to 0.789
2TypeSafe Jev 1.13^{, note 1}0.803, 95% interval 0.795 to 0.811
8Kev-4B0.717, 95% interval 0.708 to 0.726
6pplx-decider-27b0.746, 95% interval 0.738 to 0.755
9Strands Decider 2B^{, note 2}0.621, 95% interval 0.612 to 0.630

accuracy, the line across each dot is its 95% interval

Note 1, TypeSafe Jev 1.13: called through its official API. Reads text only, so it has no image results.
Note 2, Strands Decider 2B: its published training data contains items of two of our test sets.

where we lead

Pick a suite to rank every system.

where we trail

DecisionNode-1.0Jevline length is the gap in points

flash, end to end

19 ms

5 ms of it on our side

28× to 214× faster than 8 general LLMs on the same decision, timed from one client. A speed comparison against other decision APIs comes at launch.

against general llms

Eight general LLMs, the same 2,000 decisions.

Asked for JSON, a chat model sometimes returns something your code cannot use, or routes the same ticket two ways. DecisionNode returns the shape you asked for, the same way, every time.

ours
OpenAI
Anthropic
Google
tap or hover a dot

Compare with general LLMs

Preliminary results, October 2026

invalid answers

0.00%

DecisionNode-1.0 and Flash

general LLMs0.30% to 3.85%

same answer twice

100%

DecisionNode-1.0 and Flash

general LLMs91.4% to 97.3%

per 1,000 decisions

$0.0038

DecisionNode-1.0 Flash

general LLMs$0.057 to $33.30

2,000 requests per system, LLMs prompted for the JSON shape, list prices, October 2026.

15 text suites, 25,134 items. Accuracy with 95% intervals by a paired bootstrap. Jev was called through its official API; open models ran on our GPUs as their authors serve them. October 2026.

DecisionNode is not affiliated with TypeSafe AI, Cloudflare, OpenAI, Anthropic, Google or the other model publishers. Their names identify the systems measured.

See every suite

pricing

You pay for input, not for output.

Answers generate no text, so output costs nothing. Pay per million input tokens from a prepaid balance. No seats, no minimums.

estimate

How many input tokens do you send a month?

about 2,000,000 requests at 500 input tokens each

DecisionNode-1.0, a month

Flash, a month

output tokens$0.00

batch jobshalf price

Get API key

DecisionNode-1.0 Flash
$0.021
per 1M input tokens
batch jobs $0.0105, multi-hour delay
decisionnode-flash-latest
- our fastest tier, about 5 ms
- half the price per token
- the same answer shapes
- one field to switch models
Get API key
DecisionNode-1.0
full model
$0.042
per 1M input tokens
batch jobs $0.021, multi-hour delay
decisionnode-latest
- our most accurate model
- best on subtle calls
- reads small print in images
- the playground default
Get API key
Dedicated
Custom
capacity reserved for you
both models
- capacity on our own GPUs
- custom rate limits
- same API, no code changes
- a direct line to our engineers
Talk to us

both models

text and images in one request
up to 64k tokens of context
output always free
one API

faq

Questions developers ask.

The short answers. The docs have the long ones, with the request and response for every case.

Read the docs

A chat model writes its answer token by token, so a short answer takes half a second to several seconds and rarely answers the same way twice. DecisionNode reads your input once and answers your typed questions in one pass: a choice, a score or a Truth probability, each with how sure the model is. It generates no text, so it answers 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). Choice picks one option from the list you send and returns a probability for each. Score places the input on your ordered scale, for example routine to critical, and returns the expected level. Truth (truth in the API) asks whether a statement is true: DecisionNode returns one calibrated probability from 0.00 to 1.00 that it is, so 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. Number (number in the API) asks: How many, or what value? One value on a grid you set (min, max and an optional step), with a calibrated probability for every value: the most probable value, the expected value and the confidence. A count of cars in a photo, overdue invoices in a statement, a year, a rating out of ten.
More than 10 decisions a second? Use a session. It is built for loops: survey, inspection and delivery drones, simulators and games, machine monitoring, long-running agents. You open it once with the instructions, the fixed state and the questions, then stream frames (text, JSON or an image) over one WebSocket and get a typed decision back for each frame. Your context stays loaded for the whole session, so each frame costs only its own tokens, and a client that falls behind gets the newest frame answered, never a backlog, with the skipped frames reported. A session is a decision layer that feeds your controller: the vehicle's own control loop keeps flying it.
- Read the sessions docs
Get an API key, paste one curl and branch on the typed answer. The quickstart takes under five minutes, and the playground runs any request in your browser first.
Requests are processed to return your answers and to run the service. We do not train our models on your data without your written consent. Inputs and answers are deleted 30 days after each request by default, and zero retention is available on request. The Privacy Policy and the Data Processing Addendum have the details; questions go to privacy@bynn.com.
- Privacy Policy
- Data processing

Typed decisions in milliseconds.

Typed decisions in milliseconds.

How a decision runs

Four ways to ask

One request answers every question

Confidence you can act on

Text and images in one call

We build the decision modeland the machine it runs on.

Every hop is ours

One fleet, two models

Done before an LLM writes a word

decisions per hour, last 7 days

acted on at once

actions taken, live

confidence over the week

server latency, last hour

15-suite mean

where we lead

where we trail

Eight general LLMs, the same 2,000 decisions.

DecisionNode-1.0 Flash

DecisionNode-1.0

Dedicated

Questions developers ask.

What is a decision model, and how is it different from a chat model?

What are the question types?

How does pricing work, and why is output free?

Which model should I pick, DecisionNode-⁠1.0 or DecisionNode-⁠1.0 Flash?

Can it read images?

When should I use a session?comingcoming soon

Is it deterministic?

How do I start?

What data do you keep?

How a decision runs

Four ways to ask

One request answers every question

Confidence you can act on

Text and images in one call

We build the decision modeland the machine it runs on.

Every hop is ours

One fleet, two models

Done before an LLM writes a word

decisions per hour, last 7 days

acted on at once

actions taken, live

confidence over the week

server latency, last hour

15-suite mean

where we lead

where we trail

Eight general LLMs, the same 2,000 decisions.

DecisionNode-1.0 Flash

DecisionNode-1.0

Dedicated

Questions developers ask.

What is a decision model, and how is it different from a chat model?

What are the question types?

How does pricing work, and why is output free?

Which model should I pick, DecisionNode-⁠1.0 or DecisionNode-⁠1.0 Flash?

Can it read images?

When should I use a session?comingcoming soon

Is it deterministic?

How do I start?

What data do you keep?