Make structured decisions
Use the stable ShareAI endpoint /api/v1/decisions.
On this page
https://api.shareai.now/api/v1/decisionsMake structured decisions
- Base URL
https://api.shareai.now- Authentication
- Bearer API key or approved OAuth access token
- Required scope
inferenceormonetization_gateway
Use the stable ShareAI endpoint /api/v1/decisions. Provide a nonempty state array and named questions with noul, choice or score types and matching criteria. Up to 100 questions and 256 state entries are accepted, within the 2 MiB request limit.
Before you start#
Set SHAREAI_API_KEY on your server and replace the model placeholder with a currently enabled model. Never expose the API key in browser code. The model, account, credential and provider must all permit this operation. Optional settings below require model support; the API safety bounds are not a promise that every model supports every value.
Send a request#
cURL
curl --fail-with-body --request POST "https://api.shareai.now/api/v1/decisions" \
-H "Authorization: Bearer $SHAREAI_API_KEY" \
-H "Content-Type: application/json" \
--data '{
"model": "YOUR_ENABLED_DECISIONS_MODEL",
"state": [
"A bicycle with light wear."
],
"questions": {
"category": {
"type": "choice",
"instructions": "Classify this item.",
"criteria": {
"bicycle": "A complete bicycle",
"other": "Anything else"
}
}
}
}'Python
import json
import os
import urllib.request
payload = {'model': 'YOUR_ENABLED_DECISIONS_MODEL',
'state': ['A bicycle with light wear.'],
'questions': {'category': {'type': 'choice',
'instructions': 'Classify this item.',
'criteria': {'bicycle': 'A complete bicycle',
'other': 'Anything else'}}}}
headers = {'Content-Type': 'application/json'}
headers["Authorization"] = "Bearer " + os.environ["SHAREAI_API_KEY"]
request = urllib.request.Request('https://api.shareai.now/api/v1/decisions', data=json.dumps(payload).encode(), headers=headers, method="POST")
with urllib.request.urlopen(request, timeout=180) as response:
result = json.load(response)
print(result)TypeScript
const response = await fetch("https://api.shareai.now/api/v1/decisions", {
method: "POST",
headers: { Authorization: `Bearer ${process.env.SHAREAI_API_KEY}`, ...{"Content-Type": "application/json"} },
body: JSON.stringify({
"model": "YOUR_ENABLED_DECISIONS_MODEL",
"state": [
"A bicycle with light wear."
],
"questions": {
"category": {
"type": "choice",
"instructions": "Classify this item.",
"criteria": {
"bicycle": "A complete bicycle",
"other": "Anything else"
}
}
}
}),
});
if (!response.ok) throw new Error(await response.text());
const result = await response.json();
console.log(result);Request fields#
| Field | Type | Meaning and limits |
|---|---|---|
model required | string | Exact enabled public model identifier. Must declare this operation and be allowed by your credential. |
state required | array | 1–256 text or model-supported typed media state entries. Combined request limit is 2 MiB. |
questions required | object | 1–100 named questions. Each has type noul, choice or score, instructions and matching criteria. choice uses a key-to-description map; score uses an ordered list; noul uses true/false criteria. |
provider | object | Optional provider routing preferences. Use provider.only for accepted provider tags, not a prefix in the model ID. Account and credential restrictions still apply. |
Read the result#
Success returns HTTP 200 with JSON. Use the stable ShareAI endpoint /api/v1/decisions. Provide a nonempty state array and named questions with noul, choice or score types and matching criteria. Up to 100 questions and 256 state entries are accepted, within the 2 MiB request limit.
Billing units#
Decision models use input-token or other explicitly published input/request units. Structured decision values are not output-token quantities. Only reported, validated measurements in the active tariff are billed.
Choose the exact enabled model identifier from Console. Its declared operation and input/output capabilities must match this endpoint; a text chat model cannot be substituted for another operation. Your credential, provider and account restrictions still apply.
Pricing and usage#
Rates are published in EUR AI credits for the selected model, provider, units and variants. Only the dimensions in its active tariff are charged. An estimate reserves credits before execution; final charges use measured usage. Prices can depend on resolution, output format or a usage band. Check Console Usage for the final ShareAI debit. Upstream cost fields and media bytes are not converted into invented token counts.
Access and errors#
Use inference for approved network-cost inference or monetization_gateway for an approved Builder markup and accepted billing terms. Identity-only access does not authorize spending. Validation, model authorization, insufficient credits, rate limits and execution failures return a structured error. After a timeout or uncertain submission, inspect Usage or the video job before creating another potentially paid request.
Last updated November 3, 2026