Decisions

/api/v1/decisions

Beta: This endpoint is currently in beta and may be unstable. Request/response schemas and behavior may change without notice.

Evaluate a state against a map of typed questions and get back structured answers, one per question. Question types: noul (yes/no probability), choice (pick one option with full probability distribution), and score (probability-weighted position on an ordered rubric). Every question is evaluated in parallel against the same state. This endpoint returns typed judgments, not generated text. It is also available at /api/v1/systemone for drop-in compatibility with TypeSafe SDKs (set TYPESAFE_BASE_URL=https://api.venice.ai/api).

Authentication: This endpoint accepts either a Bearer API key or a SIGN-IN-WITH-X header for x402 wallet-based authentication. The legacy X-Sign-In-With-X header is also accepted during migration. When using x402, a 402 Payment Required response indicates insufficient balance and includes top-up instructions.

post/api/v1/decisions

Request

  • Base URL: https://api.venice.ai
  • URL: https://api.venice.ai/api/v1/decisions
  • Auth: one of:
    • HTTP bearer
    • API key in header SIGN-IN-WITH-X

Headers

Accept-Encodingstring
Example:gzip, br

Supported compression encodings (gzip, br)

Request body

questionsobject required

Map of typed questions, keyed by an id you choose. At least one question is required. Answers come back under the same ids. Every question is evaluated in parallel and in isolation against the same state. Question ids are not sent to the model.

Example request

{
  "questions": {
    "is_urgent": {
      "type": "noul",
      "instructions": "Does this message convey urgency?"
    }
  }
}

Response

OK

modelstring required

The model that performed the evaluation.

answersobject required

One answer per question, keyed by the same ids used in the request.

Example response

{
  "model": "jev-latest",
  "answers": {
    "is_urgent": {
      "type": "noul",
      "noul": 0.92
    }
  },
  "usage": {
    "input_tokens": 312,
    "output_tokens": 48
  }
}

Changes

No recorded changes to this operation across all 1 revision of this API.