> ## Documentation Index
> Fetch the complete documentation index at: https://docs.aireserve.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Typed decision (yes/no, choice, score)

> Send a state (text, JSON, or images) and a schema of typed questions — `noul` (yes/no), `choice` (pick one of your options), `score` (rate against an ordered rubric) — and get a calibrated probability for every allowed answer in one forward pass. No free-form text, no reasoning tokens. Jev / System One compatible. Billed per input token under `clef` (27B, 64K context) or `clef-flash` (9B, 24K context); output tokens are free.



## OpenAPI

````yaml /api-reference/openapi.json post /v1/decisions
openapi: 3.0.3
info:
  title: AI Reserve Gateway API
  description: >-
    The AI Reserve API surface — OpenAI-compatible chat completions,
    Anthropic-compatible messages, Bedrock Converse, images, video, files,
    text-to-speech, realtime voice sessions, and provider-hidden GPU
    infrastructure — all behind one endpoint and one API key.
  version: 1.0.0
servers:
  - url: https://api.aireserve.com
security:
  - bearerAuth: []
tags:
  - name: Customers
    description: >-
      Per-end-customer usage, cost, and billable amounts for organizations that
      tag requests with their own customers.
  - name: GPU Infrastructure
    description: >-
      Provision and manage provider-hidden GPU instances. The recommended
      Instances API accepts workload requirements and an hourly price ceiling;
      AI Reserve handles provider placement internally. Every mutation is
      asynchronous and returns an operation to poll.
  - name: Customer keys
    description: >-
      Mint, list, and revoke API keys pinned to your own end customers (and
      their organizations), so spend splits per customer without per-request
      tagging.
paths:
  /v1/decisions:
    post:
      tags:
        - Decisions
      summary: Typed decision (yes/no, choice, score)
      description: >-
        Send a state (text, JSON, or images) and a schema of typed questions —
        `noul` (yes/no), `choice` (pick one of your options), `score` (rate
        against an ordered rubric) — and get a calibrated probability for every
        allowed answer in one forward pass. No free-form text, no reasoning
        tokens. Jev / System One compatible. Billed per input token under `clef`
        (27B, 64K context) or `clef-flash` (9B, 24K context); output tokens are
        free.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              additionalProperties: false
              type: object
              required:
                - model
                - state
                - questions
              properties:
                model:
                  description: >-
                    Decision model: `clef` (27B, 64K context, highest precision)
                    or `clef-flash` (9B, 24K context, fastest and cheapest).
                  anyOf:
                    - type: string
                      enum:
                        - clef
                    - type: string
                      enum:
                        - clef-flash
                state:
                  description: >-
                    The situation to decide on: a string, or structured JSON
                    (records, chat logs, application state). Long text is
                    truncated upstream to fit the model's context.
                questions:
                  minProperties: 1
                  maxProperties: 64
                  description: >-
                    Map of question id → typed question (`noul`, `choice`,
                    `score`); 1 to 64 questions. Answers come back under the
                    same ids.
                  type: object
                  additionalProperties:
                    additionalProperties: true
                    type: object
                    required:
                      - type
                    properties:
                      type:
                        anyOf:
                          - type: string
                            enum:
                              - noul
                          - type: string
                            enum:
                              - choice
                          - type: string
                            enum:
                              - score
                      instructions:
                        maxLength: 20000
                        type: string
                      criteria:
                        anyOf:
                          - type: object
                            additionalProperties:
                              type: string
                          - maxItems: 255
                            type: array
                            items:
                              type: string
                images:
                  maxItems: 4
                  description: >-
                    Up to 4 embedded PNG / JPEG / WebP images placed before the
                    state (Cloudflare's System One extension; remote URLs are
                    not accepted). Each image bills at most 1,024 input tokens.
                  type: array
                  items: {}
      responses:
        '200':
          description: Default Response
components:
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: >-
        Your AI Reserve API key (aireserve_api_…) from the API Keys page in the
        portal (https://portal.aireserve.com/keys).

````

This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.