Deployments: Decision
A decision deployment answers /v1/systemone. It reads a state and typed questions and returns typed answers. It is metered in input tokens.
Deployments has the fields that every kind shares, the listing statuses and the lifecycle. This page has what is special to this kind.
Register a deployment
Copy the request, set your provider key and change the names. Every endpoint here takes the provider key as a bearer token.
curl https://router.inference.ai.exchange/v1/provider/models \
-H "Authorization: Bearer $LIQUID_PROVIDER_KEY" \
-H "Content-Type: application/json" \
-d '{
"kind": "decision",
"deployment_name": "triage-1",
"creator": "acme",
"precision": "fp8",
"region": "eu-west",
"max_input_tokens": 32000,
"output_modalities": [
{
"type": "decision",
"max_options": 8
}
]
}'
import os
import requests
response = requests.post(
"https://router.inference.ai.exchange/v1/provider/models",
headers={"Authorization": f"Bearer {os.environ['LIQUID_PROVIDER_KEY']}"},
json={
"kind": "decision",
"deployment_name": "triage-1",
"creator": "acme",
"precision": "fp8",
"region": "eu-west",
"max_input_tokens": 32000,
"output_modalities": [
{
"type": "decision",
"max_options": 8
}
]
},
)
response.raise_for_status()
print(response.json()["status"])
const response = await fetch('https://router.inference.ai.exchange/v1/provider/models', {
method: 'POST',
headers: {
Authorization: `Bearer ${process.env.LIQUID_PROVIDER_KEY}`,
'Content-Type': 'application/json',
},
body: JSON.stringify({
kind: 'decision',
deployment_name: 'triage-1',
creator: 'acme',
precision: 'fp8',
region: 'eu-west',
max_input_tokens: 32000,
output_modalities: [
{
type: 'decision',
max_options: 8,
},
],
}),
})
if (!response.ok) throw new Error(await response.text())
console.log((await response.json()).status)
The answer is 201 with the registration. A new registration is UNLISTED. kind cannot change: a new kind returns 409 kind_changed.
What you declare
| Field | Meaning |
|---|---|
max_options |
The most options that it reads in one choice question. At least 2. |
max_input_tokens |
The context limit for the state and the questions. |
Quote and serve
Quote input.text only. A decision deployment generates no tokens. A job can read the prompt more than once, so the cap counts the prompt as many times as the job allows. Your answers must cover each question by id.
{ "billable": "input.text", "unit": "mtok", "usd": 0.1 }
Charge
The charge is the input tokens that you report, summed over every read, up to the cap.
Next
- Quote the deployment: Quote over the session.
- Get it on the public book: Deployments.