pplx-decider-flash is a 4B decision model from Perplexity, built on Qwen3.5-4B and distilled from the pplx-decider models: the same request format and the same text and image support, at about one seventh of the size. Give it a state (text, JSON, or images) and a set of typed questions, and it returns a calibrated probability for every answer in a single forward pass. It doesn’t generate text.

It’s compatible with the Jev and System One APIs, so it works through Ollama’s /v1/systemone endpoint and ollama run --ask.

ollama pull pplx-decider-flash

Highlights

• Most of the accuracy, a fraction of the size: Perplexity’s evaluation puts it at 58.88 overall on the Decision Index 0.3 (60.05 with one question per request) and 72.53 on the vision suite, against 68.09 and 77.43 for pplx-decider.
• Built for latency: Perplexity positions it for cases where latency or cost matters more than the last points of accuracy.
• Multimodal: decide over text, JSON, or images such as screenshots, receipts, and forms.
• One forward pass: every option of every question is scored together, with no output tokens.
• Apache 2.0 license

What you can build

CLI

ollama run pplx-decider-flash --ask "Is a refund being requested?" < ticket.txt

ollama run pplx-decider-flash --ask "Which team should handle this?" \
  --choice billing="Payments and refunds" \
  --choice technical="Outages and errors" < ticket.txt

ollama run pplx-decider-flash --ask "How urgent is this?" \
  --level "Routine" \
  --level "Soon" \
  --level "Immediate" < ticket.txt

The state can also follow the model name instead of coming from stdin.

API

Decision models use Ollama’s /v1/systemone endpoint, documented here. Put the text you want judged in state and your questions in questions. Ollama builds pplx-decider-flash’s prompt for you.

Every question has a type, instructions, and usually criteria:

confidence runs from 0 to 1 and shows how strongly the probabilities favor one answer. It isn’t the chance that the answer is right.

cURL

curl http://localhost:11434/v1/systemone -d '{
  "model": "pplx-decider-flash",
  "state": "Our app crashes on launch for every user since this morning'\''s update. Please fix it now.",
  "questions": {
    "urgent": {"type": "noul", "instructions": "Is this support request urgent?"},
    "team": {
      "type": "choice",
      "instructions": "Which team should handle this request?",
      "criteria": {
        "billing": "Payments, invoices, and refunds",
        "technical": "Outages, errors, and configuration",
        "sales": "Plans and upgrades"
      }
    },
    "severity": {
      "type": "score",
      "instructions": "How severe is the customer impact?",
      "criteria": ["No impact", "Minor", "Major", "Critical"]
    }
  }
}'

Response:

{
  "model": "pplx-decider-flash",
  "answers": {
    "urgent": {"type": "noul", "noul": 0.996},
    "team": {
      "type": "choice",
      "choice": "technical",
      "probabilities": {"billing": 0.001, "technical": 0.998, "sales": 0.001},
      "confidence": 0.998
    },
    "severity": {
      "type": "score",
      "score": 2.91,
      "legend": {"0": "No impact", "1": "Minor", "2": "Major", "3": "Critical"},
      "probabilities": {"0": 0.001, "1": 0.005, "2": 0.076, "3": 0.918},
      "confidence": 0.91
    }
  },
  "usage": {"input_tokens": 185, "output_tokens": 0}
}

Python

Use TypeSafe’s official Python SDK and point it at Ollama. The SDK requires an API key, but Ollama ignores it, so any value works.

pip install typesafe-sdk
export TYPESAFE_BASE_URL=http://localhost:11434
export TYPESAFE_API_KEY=ollama
export TYPESAFE_DEFAULT_MODEL=pplx-decider-flash

from typesafe_sdk import Choice, Noul, Score, TypeSafeClient

questions = {
    "urgent": Noul(instructions="Is this support request urgent?"),
    "team": Choice(
        instructions="Which team should handle this request?",
        criteria={"billing": "Payments, invoices, and refunds", "technical": "Outages, errors, and configuration", "sales": "Plans and upgrades"},
    ),
    "severity": Score(instructions="How severe is the customer impact?", criteria=["No impact", "Minor", "Major", "Critical"]),
}

with TypeSafeClient(timeout=120) as client:
    result = client.system_one(state="Our app crashes on launch for every user since this morning's update. Please fix it now.", questions=questions)

print(result.choices["team"].choice)  # technical

Images

curl http://localhost:11434/v1/systemone -d '{
  "model": "pplx-decider-flash",
  "state": "The agent wants to submit the attached form.",
  "images": ["<base64-encoded image>"],
  "questions": {
    "complete": {"type": "noul", "instructions": "Are all required fields filled in?"},
    "kind": {
      "type": "choice",
      "instructions": "What kind of document is this?",
      "criteria": {"invoice": null, "receipt": null, "contract": null, "other": null}
    }
  }
}'

Benchmarks

Accuracy reported by Perplexity, measured through the Perplexity API. See the model card for the evaluation method.

On the vision suite, with images up to 1.6 MP, it scores 72.53 (pplx-decider: 77.43).

License

Apache 2.0