Skip to main content
idapt
HomeAI ModelsExploreResourcesPricing
Sign inUse for Free
  • Home
  • Pricing
  • AI Models
  • Skills
  • Image models
  • Voice models
  • Video models
  • Music models
  • Embedding models
  • Rankings
  • Multi-Model Chat
  • Agents
  • Computers
  • Drive
  • Actions
  • AI Gateway
  • All features →
  • Blog
  • About
  • Comparisons
  • Benchmarks
  • Demos
  • Help center
  • FAQ
  • Privacy
  • Support
  • Developers
  • Quickstarts
  • API reference
  • API pricing
  • CLI
  • MCP
  • Migrate
  • Downloads
  • Desktop
© idapt[email protected]TermsPrivacy PolicyLegal noticeReport content
X (Twitter)Discord
Help Center
🎯

Decision models

Found this helpful? Share it:

A decision model does not write text. You send it a state (the content to judge) and one or more named, closed questions, and it answers with typed values: a probability, a label, a score, or a bounding box. There is nothing to read and nothing to parse out of prose, which is the point: a gate that has to be read is a gate that can be argued with.

The four answer types

noul returns yes or no as a single calibrated probability. choice returns one label out of a closed set, with a probability per label. score returns a number on a rubric you supply, for thresholding. box returns a bounding box, for locating the thing you asked about in an image. Not every model answers every type; the model page lists what each one supports.

What it costs

Pricing follows from the shape. The model bills per input token only: there are no output tokens to charge for, because the answer is a handful of numbers. The model directory prints that single price per model.

Calling one

The native endpoint is POST /api/v1/decisions. The body is a state plus a record of named questions, and the response carries typed answers and usage. The same class is reachable through the OpenRouter-compatible door, so an SDK pointed at the OpenRouter base URL can call it without a special case.

Routing, privacy floors and bring-your-own-key apply to a decision call exactly as they do to every other modality: the request goes to the provider your workspace is allowed to reach, and a floor that excludes a provider excludes it here too. A decision model that cannot be served under your floor is not offered rather than silently substituted.

Measuring one

Decision models are captured and compared in the evals pipeline like every other modality. A capture records which question was asked, the answers that came back, and the token cost, so two models can be compared on the same probe rather than on a vendor's claim. The directory page carries a static preview of the request shape; it makes no model call, so you can see the wire format before spending anything.

Was this helpful?