Perplexity: Decider V1.2 API Reference

About

Perplexity Decider V1.2 is a 27B decision model served by Perplexity for classification, routing, and scoring over text, JSON, and images. It returns typed decisions and probabilities for Noul, Choice, and Score questions. The documented context window is 256K tokens, with 1–128 questions, up to 255 choice options, and up to 10 score levels. Questions normally share a pass and one billed copy of the state; overflow groups repeat that input usage.

1. Calling the API

Setup your API Key

To begin using Infron, create an account and generate your API Key.

export INFRON_KEY="YOUR_API_KEY"

Submit a request

Send JSON to POST https://llm.onerouter.pro/v1/decisions using your Infron API key. This is a runnable request example; route availability depends on your deployment.

curl --request POST "https://llm.onerouter.pro/v1/decisions" \
  --header "Authorization: Bearer $INFRON_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "perplexity/pplx-decider-v1.2",
  "state": "A customer reports being charged twice and asks for a refund today.",
  "questions": {
    "billing": {
      "type": "noul",
      "instructions": "Is this request about billing?"
    },
    "team": {
      "type": "choice",
      "instructions": "Which team should handle it?",
      "criteria": {
        "billing": "Payments and refunds",
        "technical": "Software support"
      }
    },
    "urgency": {
      "type": "score",
      "instructions": "How urgent is this request?",
      "criteria": [
        "Can wait",
        "Handle today",
        "Immediate emergency"
      ]
    }
  },
  "provider": {
    "only": [
      "perplexity"
    ],
    "allow_fallbacks": false
  },
  "usage": {
    "include": true
  }
}'

Response

The following single-answer response illustrates the schema. Its request ID, probabilities, and usage are placeholders, not a captured call.

{
  "id": "request_id_example",
  "request_id": "request_id_example",
  "model": "perplexity/pplx-decider-v1.2",
  "answers": {
    "billing": {
      "type": "noul",
      "noul": 0.97
    }
  },
  "usage": {
    "input_tokens": 100,
    "output_tokens": 1
  }
}

Routing and usage

provider and usage.include are Infron fields. They are not forwarded to the upstream provider. Set provider.only to ["perplexity"] and provider.service_tier to "standard" to select this route. usage.include=true includes cost information. Charges use the actual upstream usage.input_tokens; output tokens are free and their actual count is preserved. The model normally groups questions; if the context limit requires several groups, the state is billed once per group.

Errors

Invalid parameter types or configured limits are rejected before the upstream request. Perplexity rejects request bodies larger than 32 MiB with HTTP 413. Provider authentication, account, context, and media errors propagate through the existing gateway error handling. The service does not silently truncate the configured question or image arrays. Streaming and asynchronous task polling are unavailable.

2. Schema

Input

Question types

Noul returns a yes probability. Choice accepts 1–255 options; Score accepts 1–10 ordered levels, indexed from zero. Choice requires an option map; Score requires an array. Instructions and criteria describe the task according to the upstream contract; Noul requires a meaningful question through instructions or criteria. The official limit is described as under 256K tokens; no exact integer is supplied in the reviewed source.

Media inputs

Embed PNG, JPEG, or WebP data-URL image parts in state. Remote URLs are unsupported. Each question accepts up to eight images; each image must fit within 2,048 tiles of 32 × 32 pixels. Image tokens are included in upstream input usage.

Output

3. Detailed Pricing

This is the undiscounted base price; no promotional discount is configured. Charges use the actual upstream usage.input_tokens; output tokens are free and their actual count is preserved. The model normally groups questions; if the context limit requires several groups, the state is billed once per group. Official pricing.