Decide in one pass.
Act on the probability.
Gemini Decision 1 is Google's decision model. It never writes text. You send a situation, as text or as an image, audio, video or PDF, and typed questions, and it returns typed answers with calibrated probabilities: noul for yes/no, choice for a label, score for a rubric. $0.10 per million input tokens, and output tokens are free.
Also available: Jev by TypeSafe, Decider 27B by Perplexity and Microsoft-Decision-1 by Microsoft, same contract.
1,000
questions in one request
262,144
tokens of shared input
5
input types: text, image, audio, video, PDF
$0.10
per million input tokens, output free
Limits as documented in Google's Decisions API guide, released 11 Nov 2026.
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": "google/gemini-decision-1",
"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.
Google serves Gemini Decision 1 through the Gemini API. CompanyFabric takes the same request as for Jev, Decider 27B and Microsoft-Decision-1, so the request you write once runs on any of them.
Send a state
A ticket, a transcript, a JSON record, or an image, audio clip, video or PDF. 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.
Google's decision model, next to every other model.
One key, one balance
The same API key and prepaid balance as every chat model in the catalog. No Google account, key or quota to set up. Already have a Google AI Studio key? Add it to the BYOK vault and decisions run on it at 0% fee.
Same contract as the others
Every decision model here answers POST /v1/decisions with the same request and the same answer shapes. Switch between them by changing one field, "model".
Compare on your own data
The playground runs each starter, or your own state, on Gemini Decision 1, Jev, Decider 27B and Microsoft-Decision-1. Benchmarks are someone else's data; yours is the one that counts.
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 Gemini Decision 1. 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": "google/gemini-decision-1",
"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
- google/gemini-decision-1
- Provider
- Price
- $0.1 / M input · $0 / M output
- Endpoint
- POST /v1/decisions
- Question types
- noul · choice · score
- State
- text, JSON, image, audio, video or PDF
Metered on input, billed to your prepaid balance; each response carries its exact cost in usage.cost_usd.
Questions about Gemini Decision 1.
What is Gemini Decision 1?
Gemini Decision 1 is Google's decision model, released on 11 November 2026 in the Gemini API. It does not write text: you send a state and typed questions, and it returns one typed answer per question with a calibrated 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. On CompanyFabric you call it as "google/gemini-decision-1" on POST /v1/decisions.
What can Gemini Decision 1 read?
Text, JSON, images, audio, video and PDFs. Google documents up to 1,000 independent questions in one request over shared input of up to 262,144 tokens, with up to 255 options on a choice question. Those are Google's limits. Send media as a content block (a type, a mime_type, and either inline data or a public HTTPS uri); any other JSON in state is sent as text.
How does Gemini Decision 1 compare with Jev and other decision models?
Google publishes its own benchmark comparison in its launch post; we have not measured it and do not restate it. All four decision models on CompanyFabric take the same /v1/decisions request and answer the same question types, so the playground runs any starter on each and you can compare them on your own data by changing "model".
Do I need a Google or Gemini API account?
No. CompanyFabric serves Gemini Decision 1 on its own Gemini API access, so your CompanyFabric API key and prepaid balance work for it the same way they do for every chat model. If you already have a Google AI Studio key, add it to the BYOK vault and decisions run on it at 0% fee.
How much does Gemini Decision 1 cost?
$0.10 per million input tokens, and output tokens are free. Text, image, audio, video and PDF input are priced the same. 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 Gemini Decision 1 commercially?
Commercial use per Gemini API paid-tier terms; Google does not use paid-tier prompts to train its models.
Put a decision
in front of the spend.
POST /v1/decisions with "model": "google/gemini-decision-1" from your code, or let your agent call the decide tool on our MCP server before every expensive step.