Skip output decoding.
The model reads the input in a forward pass. It does not spend additional decoding steps writing an answer token by token.
decisionintelligence.
A language model for making deicisions when speed matters.
Explore the modelBuilt for application logic.Why a decisions model
The model
It’s like generative AI.
Without the generation.
In software, an AI response often becomes a branch, a field, or a score. The application needs the value to take its next step.
decision-machine-1 scores labels and extracts values directly from text. For these bounded tasks, it skips the token-by-token generation an LLM uses—even with structured outputs.
Read the model rationaleLanguage in
“Losing sales,
fix this today.”
Is the customer expressing urgency?
Decision outtrue
Probability of urgency 1.00
/yes-no response. Your code can use the boolean to raise a ticket’s priority.Define the task.
Supply labels to choose between, questions to answer from the source, or fields to extract.
See the alternatives.
A classification includes the full score distribution and confidence. Your code can see when two labels compete, instead of treating every winner alike.
Calls
One model.
Seven decisions.
Choose the labels, questions, or fields your application needs.
POST /yes-noRecorded API example
Request
Flag messages that need a faster response.
{ "text": "Losing sales, fix this today.",
"statement": "The customer expresses urgency." }Boolean
true
Use this flag to raise the ticket’s priority.
Probability of urgency1.00
View JSON response
{ "answer": true, "probability": 1 }POST /classifyRecorded API example
Request
Choose a destination from your support queues.
{ "text": "My card was charged twice this month.",
"labels": ["billing","shipping","technical","other"] }Label
billing
Use the label to select the billing queue.
Label probability0.74
billing0.74
other0.25
technical0.008
shipping0.001
View JSON response
{ "label": "billing", "probability": 0.74,
"confidence": 0.555,
"scores": { "billing": 0.74, "shipping": 0.001,
"technical": 0.008, "other": 0.25 } }POST /rateRecorded API example
Request
Turn customer frustration into a sortable score.
{ "text": "Third time I write. Nobody answers.",
"scale": ["calm","annoyed","angry","furious"] }Reported score · 0–3 scale
1.998
Nearly tied levels signal uncertainty. Keep it visible when ranking the queue.
Confidence0.208
0 · calm0
1 · annoyed0.334
2 · angry0.334
3 · furious0.332
View JSON response
{ "score": 1.998, "level": 1,
"confidence": 0.208,
"scores": [0, 0.334, 0.334, 0.332] }POST /answerRecorded API example
Request
Locate the shipment destination in a status update.
{ "text": "The shipment reached the Halifax warehouse on September 6, two days after the promised date.",
"questions": ["Where did the shipment arrive?"] }Text span
Halifax warehouse
Source offsets let your application show where the answer came from.
Answer probability0.992
View JSON response
{ "results": [ { "answer": "Halifax warehouse",
"probability": 0.992, "start": 25, "end": 42 } ] }POST /extractRecorded API example
Request
Map invoice text to the fields in your records.
{ "text": "Invoice #A-1042 from Nordik Supply, due 2026-10-01, total 4,250.00 CAD, net 30.",
"schema": { "type": "object", "properties": {
"invoice_number": { "type": "string" },
"vendor": { "type": "string" },
"total": { "type": "number" },
"currency": { "type": "string" } } } }Structured data
4 fields
Invoice fields ready for validation before writing a record.
- invoice number
- A-1042
- vendor
- Nordik Supply
- total
- 4250
- currency
- CAD
View JSON response
{ "data": { "invoice_number": "A-1042",
"vendor": "Nordik Supply",
"total": 4250, "currency": "CAD" } }POST /entitiesRecorded API example
Request
Identify people, organizations, and references in a claim note.
{ "text": "Marie Tremblay from Desjardins called about claim 44812 on March 3.",
"types": ["person","organization","claim_id","date"] }Entities
4 entities
Typed values for search and record matching.
- person
- Marie Tremblay
- organization
- Desjardins
- claim id
- claim 44812
- date
- March 3
View JSON response
{ "entities": [
{ "type": "person", "text": "Marie Tremblay", "probability": 0.999 },
{ "type": "organization", "text": "Desjardins", "probability": 0.997 },
{ "type": "claim_id", "text": "claim 44812", "probability": 0.714 },
{ "type": "date", "text": "March 3", "probability": 0.997 } ] }POST /verifyRecorded API example
Request
Check a proposed deductible against the policy text.
{ "text": "Policy holder: Jean Roy. Deductible $500.",
"field": { "name": "deductible" },
"value": "$1000" }Boolean
false
The source says $500. The proposed value is $1,000.
Probability of a match0.00
View JSON response
{ "matches": false, "probability": 0,
"found": ["$500"] }Recorded examples · 16 September 2026API quickstart
A place beside your LLMCall your LLM
Call your LLM
if you need to.
Use a decision call first, then accept results that meet your thresholds, and send ambiguous cases to an LLM or a person.
That can reduce large-model calls. It also adds a first step, so measure the cost and latency of the whole path on your traffic.
Build an LLM cascadeRecorded classificationbilling
Label probability 0.74Confidence 0.555
Your application’s gate
probability >= 0.90
confidence >= 0.70Meets both thresholdsUse the result
Below either · this exampleLLM or human review
03 — PricingBuilt for volume.
Small decisions.
At large scale.
Screen incoming messages. Check extracted fields. Cost follows the text you send, with no output-token charge.
Start building$0.04
per million input tokens
Output tokens$0
100 million input tokens cost $4. Each call bills its input, including repeated text.
04 — IntegrationDesigned for your stack.
Start with
a real task.
Try a classification or extraction call you already send to an LLM. Compare accuracy, latency, and cost on representative inputs.
Use plain HTTP, or reuse your OpenAI client for supported structured-output and tool-call requests.
Read the quickstartYour first request
curl https://api.milliseconds.ai/v1/decision-machine-1/yes-no \
-H "Content-Type: application/json" \
-d '{"text":"Losing sales, fix this today.",
"statement":"The customer expresses urgency."}'Recorded response
{ "answer": true, "probability": 1 }No API key required during launch. Standard usage pricing applies.
Important questions, fast answers.
Does structured output mean the answer is correct?
No. A well-formed response can still contain a wrong value. Evaluate on your own data, validate business rules, and review consequential or ambiguous results. Verification can check a value against the source; it is not a guarantee of correctness.
When should I use an LLM instead?
Use an LLM for writing, conversation, multi-step reasoning, or judgments that need knowledge beyond the supplied text. Use milliseconds when the task has defined labels, questions, or fields.
What do probability and confidence tell me?
For classification, probability is the winning label’s share of the scores. Confidence describes how concentrated the whole distribution is. Neither is a guarantee that the answer is right. Other capabilities return different scoring fields; tune thresholds for the task and the cost of a mistake.
Can I keep my OpenAI SDK?
Yes, for JSON-schema extraction and tool calls. Set the base URL to https://api.milliseconds.ai/v1 and select decision-machine-1. This is not a drop-in chat model: plain chat is unsupported, and the compatibility layer reads user turns only.