Ask, don't generate.
Get the probability.
Decider 27B is Perplexity's decision model. It never writes text. You send a situation, text or image, and typed questions, and it returns typed answers with probabilities: noul for yes/no, choice for a label, score for a rubric. $0.04 per million input tokens, and output tokens are free.
Also available: Jev by TypeSafe, same contract.
Category, urgency and escalate-to-human before any model writes a reply.
Free starter credits cover thousands of decisions. Or copy the code below and run it with your own key.
Answers arrive here as probabilities, one card per question. No text to parse, nothing invented outside the options you gave.
Jev decides in ~100 ms, then a chat model drafts only the tickets a bot may answer.
What to do with the numbers
- urgent > 0.7 and category = billing → billing on-call queue.
- escalate < 0.4 → let companyfabric/cheap draft the reply; otherwise a human answers.
- escalate between 0.4 and 0.6 is unsure: fail closed, human.
- Log churn_risk with the ticket; tune thresholds from the log, not from guesses.
This exact request, in code
curl https://api.companyfabric.com/v1/decisions \
-H "Authorization: Bearer $COMPANYFABRIC_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "perplexity/decider-27b",
"state": "Second time this month my card was charged twice. I want a refund today or I'\''m cancelling and disputing with my bank.",
"questions": {
"category": {
"type": "choice",
"instructions": "What is this ticket about?",
"criteria": {
"billing": "Charges, invoices, refunds, double charges",
"technical": "Bugs, errors, outages, something not working",
"account": "Login, access, password, settings",
"other": null
}
},
"urgent": {
"type": "noul",
"instructions": "Does this need a human reply within the hour?",
"criteria": {
"true": "Money lost, service blocked, or a stated deadline",
"false": "Can wait for the next business day"
}
},
"escalate": {
"type": "noul",
"instructions": "Should a human handle this instead of an automated reply?"
},
"churn_risk": {
"type": "score",
"instructions": "How likely is this customer to leave?",
"criteria": [
"No signal",
"Frustrated",
"Threatens to cancel or dispute"
]
}
}
}'Needs a CompanyFabric key, or add your own TypeSafe key in the BYOK vault and pay them directly at 0% fee. Cost comes back in usage.cost_usd.
One call.
Many answers.
Perplexity serves Decider 27B through its Decisions API. CompanyFabric puts it on the same endpoint as Jev, so the request you write once runs on either.
Send a state
A ticket, a brief, a transcript, a JSON record, or an image. It is sent once, whatever you ask about it.
Ask typed questions
noul is a yes/no probability. choice picks one label from criteria you describe. score places on a rubric you define, from zero. Ask several in one call.
Threshold the numbers
Answers are probabilities and distributions, never prose. Act above a threshold, hand to a human below it, and treat a noul near 0.5 as unsure.
Decider next to every other model.
One key, one balance
The same API key and prepaid balance as every chat model in the catalog. No separate Perplexity account to open or top up.
Same contract as Jev
Both decision models answer POST /v1/decisions with the same request and the same answer shapes. Switch between them by changing one field, "model".
Bring your own key
Have a Perplexity API key? Add it in the BYOK vault and Decider 27B runs on your own account at 0% platform fee.
A cap on every key
Set a spend cap per API key, so one service or agent can never run past the budget you gave it.
One field picks the model.
The support triage starter, sent to Decider 27B. Change "model" to "typesafe/jev-latest" and the same request runs on Jev.
curl https://api.companyfabric.com/v1/decisions \
-H "Authorization: Bearer $COMPANYFABRIC_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "perplexity/decider-27b",
"state": "Second time this month my card was charged twice. I want a refund today or I'\''m cancelling and disputing with my bank.",
"questions": {
"category": {
"type": "choice",
"instructions": "What is this ticket about?",
"criteria": {
"billing": "Charges, invoices, refunds, double charges",
"technical": "Bugs, errors, outages, something not working",
"account": "Login, access, password, settings",
"other": null
}
},
"urgent": {
"type": "noul",
"instructions": "Does this need a human reply within the hour?",
"criteria": {
"true": "Money lost, service blocked, or a stated deadline",
"false": "Can wait for the next business day"
}
},
"escalate": {
"type": "noul",
"instructions": "Should a human handle this instead of an automated reply?"
},
"churn_risk": {
"type": "score",
"instructions": "How likely is this customer to leave?",
"criteria": [
"No signal",
"Frustrated",
"Threatens to cancel or dispute"
]
}
}
}'- Model id
- perplexity/decider-27b
- Provider
- Perplexity
- Price
- $0.04 / M input · $0 / M output
- Endpoint
- POST /v1/decisions
- Question types
- noul · choice · score
- State
- text, JSON or image
Metered on input, billed to your prepaid balance; each response carries its exact cost in usage.cost_usd. With your own Perplexity key it is 0% platform fee.
Questions about Decider 27B.
What is Perplexity Decider 27B?
Decider 27B is Perplexity's decision model. It does not write text: you send a state and typed questions, and it returns one typed answer per question with a probability attached. noul is a yes/no probability, choice picks one label from criteria you describe, and score places the state on a rubric you define. Perplexity serves it through its Decisions API; on CompanyFabric you call it as "perplexity/decider-27b" on POST /v1/decisions.
How is Decider 27B different from Jev?
Both take the same /v1/decisions request and answer the same three question types, so a request moves between them by changing "model". Decider 27B also reads images in state; Jev reads text and JSON. Decider 27B costs $0.04 per million input tokens and Jev (by TypeSafe) costs $0.042; output is free on both. Jev is the default when you omit "model". The playground runs any starter on either, so you can compare the answers on your own data.
Do I need a Perplexity account?
No. Your CompanyFabric API key and balance work for Decider 27B the same way they do for every chat model. If you already have a Perplexity API key, add it under Perplexity in the BYOK vault and /v1/decisions routes Decider 27B on your own Perplexity account at 0% platform fee.
How much does Decider 27B cost?
$0.04 per million input tokens, and output tokens are free. You are metered on what you send (state and questions), and the exact figure for each call comes back in usage.cost_usd. It is billed to the same prepaid balance as chat, and the welcome credit covers it.
Can I use Decider 27B commercially?
Commercial use per Perplexity API terms. Open weights published as pplx-decider-v1-27b.
Put a decision
in front of the spend.
POST /v1/decisions with "model": "perplexity/decider-27b" from your code, or let your agent call the decide tool on our MCP server before every expensive step.