Decisions

Evaluate classification and scoring questions

Evaluate one input against predicate, choice and score questions. Answers follow question order and may include per-question refusals. Use a provider-qualified decision model or a compatible routing alias with a project-scoped Aixy API key. Native decision requests preserve provider extensions. Aixy translates compatible decision formats; an image or extension that cannot be represented returns an explicit compatibility error. Conversation-only models are not converted to decision models. Streaming and output-token caps are unsupported. Hard budgets reject public decisions with hard_budget_decision_unbounded because no enforced completion bound is available. Decision content is processed transiently and is excluded from Activity content capture.

POST

decisions

curl --request POST \
  --url https://api.aixy-gateway.com/v1/decisions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "openai/gpt-6-luna",
  "input": "The package arrived with a broken screen.",
  "questions": [
    {
      "type": "predicate",
      "name": "damaged",
      "instructions": "Does the customer report a damaged item?"
    }
  ]
}
'

import requests

url = "https://api.aixy-gateway.com/v1/decisions"

payload = {
    "model": "openai/gpt-6-luna",
    "input": "The package arrived with a broken screen.",
    "questions": [
        {
            "type": "predicate",
            "name": "damaged",
            "instructions": "Does the customer report a damaged item?"
        }
    ]
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'openai/gpt-6-luna',
    input: 'The package arrived with a broken screen.',
    questions: [
      {
        type: 'predicate',
        name: 'damaged',
        instructions: 'Does the customer report a damaged item?'
      }
    ]
  })
};

fetch('https://api.aixy-gateway.com/v1/decisions', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

{
  "answers": [
    {
      "type": "predicate",
      "name": "damaged",
      "probability": 0.98
    }
  ]
}

{
  "error": {
    "code": "invalid_gateway_api_key",
    "message": "Gateway API key is invalid or revoked"
  }
}

{
  "error": {
    "code": "invalid_gateway_api_key",
    "message": "Gateway API key is invalid or revoked"
  }
}

{
  "error": {
    "code": "invalid_gateway_api_key",
    "message": "Gateway API key is invalid or revoked"
  }
}

{
  "error": {
    "code": "invalid_gateway_api_key",
    "message": "Gateway API key is invalid or revoked"
  }
}

{
  "error": {
    "code": "invalid_gateway_api_key",
    "message": "Gateway API key is invalid or revoked"
  }
}

{
  "error": {
    "code": "invalid_gateway_api_key",
    "message": "Gateway API key is invalid or revoked"
  }
}

{
  "error": {
    "code": "invalid_gateway_api_key",
    "message": "Gateway API key is invalid or revoked"
  }
}

{
  "error": {
    "code": "invalid_gateway_api_key",
    "message": "Gateway API key is invalid or revoked"
  }
}

{
  "error": {
    "code": "gateway_rate_limit_exceeded",
    "message": "The configured rate limit was reached. Retry later."
  }
}

Internal Server Error

{
  "error": {
    "code": "invalid_gateway_api_key",
    "message": "Gateway API key is invalid or revoked"
  }
}

{
  "error": {
    "code": "invalid_gateway_api_key",
    "message": "Gateway API key is invalid or revoked"
  }
}

{
  "error": {
    "code": "invalid_gateway_api_key",
    "message": "Gateway API key is invalid or revoked"
  }
}

{}

Authorizations

Authorization

string

header

required

A project-scoped Aixy API key. Create keys in the dashboard and send the secret as a Bearer token.

Headers

X-Request-ID

string

Optional caller-generated request identifier for end-to-end tracing.

Maximum string length: 255

X-Aixy-Client

string

Optional application[/version] for Activity attribution. Overrides User-Agent detection. Use a product name, not personal data or credentials. Names are 1-64 ASCII letters, digits, spaces, dots, underscores or hyphens, starting with a letter or digit. Optional versions start with a digit and use up to 32 letters, digits, dots, underscores, plus signs or hyphens. Invalid values are ignored. This self-declared label grants no permissions and is not forwarded.

Maximum string length: 97

Example:

"Acme Support/1.2.3"

X-Aixy-Session

string

Optional opaque session identifier for virtual routes with session affinity. Scoped to the authenticated caller and alias; never forwarded or recorded. Send full conversation history. Invalid values return 400 when affinity is enabled. Omission retains the route's normal strategy.

Required string length: 1 - 128

Pattern: ^[A-Za-z0-9._:-]+$

Example:

"conversation-82"

X-Aixy-Session-ID

string

Optional opaque conversation identifier recorded in Activity metadata. Reuse it for every call in a conversation. Sessions are isolated by organization, project, user and API key. Use no personal data or secrets. Invalid values are ignored. The header is not forwarded, grants no permissions and does not change routing affinity.

Required string length: 1 - 128

Pattern: ^[A-Za-z0-9._:-]+$

Example:

"conversation-82"

X-Provider

string

Select a configured provider without changing an unqualified model identifier. A provider-qualified model is preferred for new integrations.

Body

application/json

model

string

required

Provider-qualified decision model or compatible Aixy routing alias.

Required string length: 1 - 1048576

input

required

Evidence evaluated for every question. Only user messages containing text and images are accepted. At most 128 images per request; image input requires a matching native Decisions provider.

questions

object[]

required

Required array length: 1 - 200 elements

Option 1
Option 2
Option 3

Show child attributes

safety_identifier

string | null

Maximum string length: 128

stream

boolean

default:false

Response

Structured decision answers.

answers

object[]

required

One answer per question, in request order.

Option 1
Option 2
Option 3
Option 4

Show child attributes

model

string

usage

object

Show child attributes

Evaluate classification and scoring questions

curl --request POST \
  --url https://api.aixy-gateway.com/v1/decisions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "openai/gpt-6-luna",
  "input": "The package arrived with a broken screen.",
  "questions": [
    {
      "type": "predicate",
      "name": "damaged",
      "instructions": "Does the customer report a damaged item?"
    }
  ]
}
'

import requests

url = "https://api.aixy-gateway.com/v1/decisions"

payload = {
    "model": "openai/gpt-6-luna",
    "input": "The package arrived with a broken screen.",
    "questions": [
        {
            "type": "predicate",
            "name": "damaged",
            "instructions": "Does the customer report a damaged item?"
        }
    ]
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'openai/gpt-6-luna',
    input: 'The package arrived with a broken screen.',
    questions: [
      {
        type: 'predicate',
        name: 'damaged',
        instructions: 'Does the customer report a damaged item?'
      }
    ]
  })
};

fetch('https://api.aixy-gateway.com/v1/decisions', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

{
  "answers": [
    {
      "type": "predicate",
      "name": "damaged",
      "probability": 0.98
    }
  ]
}

{
  "error": {
    "code": "invalid_gateway_api_key",
    "message": "Gateway API key is invalid or revoked"
  }
}

{
  "error": {
    "code": "invalid_gateway_api_key",
    "message": "Gateway API key is invalid or revoked"
  }
}

{
  "error": {
    "code": "invalid_gateway_api_key",
    "message": "Gateway API key is invalid or revoked"
  }
}

{
  "error": {
    "code": "invalid_gateway_api_key",
    "message": "Gateway API key is invalid or revoked"
  }
}

{
  "error": {
    "code": "invalid_gateway_api_key",
    "message": "Gateway API key is invalid or revoked"
  }
}

{
  "error": {
    "code": "invalid_gateway_api_key",
    "message": "Gateway API key is invalid or revoked"
  }
}

{
  "error": {
    "code": "invalid_gateway_api_key",
    "message": "Gateway API key is invalid or revoked"
  }
}

{
  "error": {
    "code": "invalid_gateway_api_key",
    "message": "Gateway API key is invalid or revoked"
  }
}

{
  "error": {
    "code": "gateway_rate_limit_exceeded",
    "message": "The configured rate limit was reached. Retry later."
  }
}

Internal Server Error

{
  "error": {
    "code": "invalid_gateway_api_key",
    "message": "Gateway API key is invalid or revoked"
  }
}

{
  "error": {
    "code": "invalid_gateway_api_key",
    "message": "Gateway API key is invalid or revoked"
  }
}

{
  "error": {
    "code": "invalid_gateway_api_key",
    "message": "Gateway API key is invalid or revoked"
  }
}

{}

OpenAI

Decisions

Anthropic

Models

Evaluate classification and scoring questions

Authorizations

Headers

Body

Response