The Decisions API from LLM Gateway — 1 operation(s) for decisions.
Every API here is available over the APIs.io API and to AI agents over MCP.
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
find_apisBrowse and filter every API in the catalog.get_api_artifactsOne API's artifacts, grouped by type.get_openapiThe primary OpenAPI for this API.find_similar_apisAPIs that look like this one.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.curl "https://apis.io/api/v1/apis/llmgateway-io:llmgateway-io-decisions-api"curl "https://apis.io/api/v1/apis?limit=25"Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.
openapi: 3.2.0
info:
version: 1.0.0
title: LLM Gateway Decisions API
description: 'OpenAI-compatible LLM gateway: chat completions, embeddings, images, audio, video, moderation, OCR, rerank, web search and typed decisions across providers with one API key.'
servers:
- url: https://api.llmgateway.io
- url: http://localhost:4001
tags:
- name: Decisions
paths:
/v1/decisions:
post:
operationId: v1_decisions
summary: Decisions
description: Evaluate text or images against typed questions and get calibrated predicate, choice and score answers back. OpenAI-compatible API.
security:
- bearerAuth: []
requestBody:
content:
application/json:
schema:
type: object
properties:
model:
type: string
description: ID of the decision model to use, optionally prefixed with a provider (`openai/gpt-6-luna-decisions`, `azure/microsoft-decision-1`, `typesafe/jev-1.13.0`).
example: gpt-6-luna-decisions
input:
anyOf:
- type: string
- type: array
items:
type: object
properties:
type:
type: string
enum:
- message
role:
type: string
enum:
- user
content:
anyOf:
- type: string
- type: array
items:
oneOf:
- type: object
properties:
type:
type: string
enum:
- input_text
text:
type: string
required:
- type
- text
- type: object
properties:
type:
type: string
enum:
- input_image
image_url:
type: string
description: A base64-encoded image in a data URL or a publicly accessible HTTP(S) image URL.
detail:
type:
- string
- 'null'
enum:
- low
- high
- auto
- original
required:
- type
- image_url
required:
- role
- content
description: 'The text or images to evaluate for every question: a string, or user messages with `input_text` and `input_image` parts. Image input depends on the model.'
example: I was charged twice for my order.
questions:
type: array
items:
oneOf:
- type: object
properties:
type:
type: string
enum:
- predicate
name:
type: string
instructions:
type: string
required:
- type
- instructions
- type: object
properties:
type:
type: string
enum:
- choice
name:
type: string
instructions:
type: string
choices:
type: array
items:
type: object
properties:
value:
anyOf:
- type: string
- type: boolean
description:
type: string
required:
- value
minItems: 2
maxItems: 255
description: 'Between 2 and 255 unique options. Values are typed: a string and a boolean with the same text are distinct.'
required:
- type
- instructions
- choices
- type: object
properties:
type:
type: string
enum:
- score
name:
type: string
instructions:
type: string
levels:
type: array
items:
type: object
properties:
label:
type: string
description:
type: string
required:
- label
minItems: 2
description: Ordered levels, lowest first.
required:
- type
- instructions
- levels
description: 'A typed question: `predicate` (probability a condition is true), `choice` (one option from a set) or `score` (rating across ordered levels).'
minItems: 1
description: Questions to evaluate against the input. Answers come back in the same order, echoing each question's `name`.
safety_identifier:
type:
- string
- 'null'
maxLength: 128
description: Opaque identifier for the end user making the request.
required:
- model
- input
- questions
responses:
'200':
description: Typed answers for the submitted questions.
headers:
RateLimit-Policy:
schema:
type: string
description: Quota policy as an HTTP Structured Fields list, e.g. "requests";q=60;w=60.
RateLimit:
schema:
type: string
description: Available quota and reset delay, e.g. "requests";r=59;t=60.
RateLimit-Limit:
schema:
type: string
description: Request limit for the current window.
RateLimit-Remaining:
schema:
type: string
description: Requests remaining in the current window.
RateLimit-Reset:
schema:
type: string
description: Seconds until the current window resets.
content:
application/json:
schema:
type: object
properties:
model:
type: string
answers:
type: array
items:
type: object
properties:
type:
type: string
enum:
- predicate
- choice
- score
- refusal
name:
type:
- string
- 'null'
probability:
type: number
description: Probability from 0 to 1 that the condition is true, on a predicate answer.
choice:
anyOf:
- type: string
- type: boolean
description: Highest-probability option, on a choice answer.
score:
type: number
description: Probability-weighted average of the level indices, on a score answer.
probabilities:
type: array
items:
type: object
properties:
value:
anyOf:
- type: string
- type: boolean
- type: number
label:
type: string
probability:
type: number
required:
- value
- probability
confidence:
type: number
required:
- type
usage:
type: object
properties:
input_tokens:
type: integer
output_tokens:
type: integer
total_tokens:
type: integer
required:
- input_tokens
- output_tokens
- total_tokens
required:
- model
- answers
description: One typed answer per question, in question order.
'400':
description: Invalid request body or parameters.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIError'
'401':
description: Missing or invalid API key.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIError'
'402':
description: Insufficient credits or plan limits reached.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIError'
'403':
description: Forbidden request or upstream response.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIError'
'404':
description: Unknown model or upstream not-found response.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIError'
'408':
description: Request timeout.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIError'
'410':
description: Archived or unavailable project.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIError'
'413':
description: Request too large.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIError'
'415':
description: Unsupported media type.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIError'
'429':
description: Rate limited. Response headers describe only LLMGateway-enforced limits; upstream provider headers are not forwarded. Honor Retry-After when present.
headers:
RateLimit-Policy:
schema:
type: string
description: Quota policy as an HTTP Structured Fields list, e.g. "requests";q=60;w=60.
RateLimit:
schema:
type: string
description: Available quota and reset delay, e.g. "requests";r=59;t=60.
RateLimit-Limit:
schema:
type: string
description: Request limit for the current window.
RateLimit-Remaining:
schema:
type: string
description: Requests remaining in the current window.
RateLimit-Reset:
schema:
type: string
description: Seconds until the current window resets.
Retry-After:
schema:
type: string
description: Seconds to wait before retrying.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIError'
'500':
description: Internal server error.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIError'
'502':
description: Failed to connect to the upstream provider.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIError'
'503':
description: Service unavailable upstream response.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIError'
'504':
description: Upstream provider timeout.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIError'
'529':
description: Gateway overloaded.
headers:
Retry-After:
schema:
type: string
description: Seconds to wait before retrying.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIError'
tags:
- Decisions
components:
schemas:
OpenAIError:
type: object
properties:
error:
type: object
properties:
message:
type: string
type:
type: string
param:
type:
- string
- 'null'
code:
type:
- string
- 'null'
required:
- message
- type
- param
- code
required:
- error
description: OpenAI-compatible error object.
securitySchemes:
bearerAuth:
type: http
scheme: bearer
description: Bearer token authentication using API keys
externalDocs:
url: https://docs.llmgateway.io
description: LLMGateway Documentation