Decide 1 | EmpirioLabs AI Docs

POST /v1/decisions

Answers yes or no, choice, score, and tool questions about text, JSON, images, and video with calibrated probabilities in one request.

At a glance

Field	Value
Model id	`decide-1`
Model release date	2026-09-27
Input modalities	Text, Image, Video
Output modalities	Decision
Context window	60K
Weight precision	BF16 weights
Features	classification, calibrated_probabilities, tool_selection, vision, video, multimodal
Native inference	Yes
New	Yes
Supported endpoints	`POST /v1/decisions`
Alternate model ids	`empiriolabs/decide-1`

Pricing

Charge	Spec	Rate
Input	per 1M prompt tokens	$0.04
Output	per 1M generated tokens	Free

Example request

curl https://api.empiriolabs.ai/v1/decisions \
  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"model": "decide-1", "state": "Customer: I was charged twice for my subscription this month and I need a refund today.", "questions": {"is_urgent": {"type": "noul", "instructions": "Does the customer need a resolution today?"}, "department": {"type": "choice", "instructions": "Which team should handle this message?", "criteria": {"billing": null, "technical": null, "sales": null}}}}'

Parameters

Decision models take a state and typed questions instead of chat parameters. The request fields, question types, and answers are in the Decisions API guide.

Notes

Requests

Send content in state (a string, a JSON object, or an array) and 1 to 128 questions in questions to POST /v1/decisions. Each question is answered on its own, with probabilities and a confidence value. No text is generated.

Question types

noul: yes or no, answered with the probability of yes.
choice: one of 2 to 255 options, answered with the chosen option and the full distribution.
score: 2 to 10 ordered levels, answered with the expected level and the distribution.
tool: which of 1 to 254 function tools to call, with distributions over its enum and boolean arguments.

Limits

The state plus the longest question: up to 60,000 tokens.
At most 512 evaluated questions per request. A tool question counts as one plus one per enum or boolean argument.
Media: up to 16 images (20 MB each) and 4 videos (100 MB and 10 minutes each), as public HTTPS URLs or inline base64. Audio is not accepted; use Decide 1 Omni.

Billing

Input tokens only: the state once per request, each question’s own text, and each media item’s tokens. Output is always zero.

Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/decide-1.