Skip to content

Inception · Text

Mercury Decide API pricing

inception/mercury-decide

Structured decisions. Mercury Decide by Inception, routed through INFRO on a Inception account you connect — alongside every other provider you run. Inception bills you for it directly, on that account and at your own rate. INFRO adds routing, failover, request logs, cost attribution and policy around it, and takes no part of what you pay Inception.

Pricing

Per 1M tokensUSD · updated 2026-10-05

Inception rate

$0.02

per 1M input tokens, output free, billed to you by Inception

INFRO adds

$0

0% markup on model spend

Per-token rates

$0.02 / 1M input tokens·$0.00 / 1M output tokens

Output tokens are free, so the headline figure above is the input rate, as Inception publishes it.

Calling Mercury Decide

POST /v1/decisions
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["INFRO_API_KEY"],
    base_url="https://api.infro.io/v1",
)

decision = client.decisions.create(
    model="inception/mercury-decide",
    input="I was charged twice. Please fix this.",
    questions=[{
        "type": "predicate",
        "name": "refund_request",
        "instructions": "Is the customer asking for a refund?",
    }],
)

What a decision model answers

  • Typed questions about the evidence you send: yes or no, one option of a closed set, a level on a rubric.
  • Probabilities on every answer, and a confidence for choice and score. No generated text.
  • Every INFRO decision feature runs on it: decision policies, rerank, classifier guardrails, the route classifier and evals.

OpenAI's or TypeSafe's request body, on your own Inception connection or an OpenRouter one: your INFRO gateway key, spend limits checked before the call, and an estimated cost on every response.

Decision modelsGet a key