Perplexity Decider 1.2

by Perplexity

Perplexity Decider 1.2 is an open-weight decision model built on a Qwen3.8-27B backbone. It reads text, JSON and images and answers named yes/no, choice and rubric-score questions with probabilities rather than generated prose. Its joint request format can answer related questions about one state in a single pass. Use it for classification, routing, grading and other decisions where nuanced judgments matter more than Flash's lower latency and input price. Related questions can share the state and inform one another; independent candidates should generally be sent separately because grouping can change their scores. Perplexity recommends evaluating accuracy and decision thresholds on your own labeled examples.

Call Perplexity Decider 1.2 on Opper through the System One evaluation API. Sign up without a credit card. Get started

Key info

Input
Output
Features
Context window
262K
Max output
—
Input price
$0.02 /1M
Output price
$0 /1M
  • No training by default

Available routes

Perplexity Decider 1.2 runs on 1 route through the Opper gateway. Compare residency, zero data retention and training posture at a glance, with full data-handling detail per route below.

ProviderRegionZero data retentionTrainingInputOutputCache read
Multi—Not establishedNo$0.02$0Input price

Live routes and prices as JSON: api.opper.ai/v3/models?q=perplexity%2Fpplx-decider-v1.2

Uptime and availability

Perplexity Decider 1.2 runs on a single route through the Opper gateway today, so its availability is that provider's availability.

99.91%route uptime, last 30 days
Single route, no failover target within this model.

Name a second model in the same request and the gateway tries it on retriable errors, so a busy hour never has to reach your users. Set up a fallback chain.

Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. See uptime for every provider Opper monitors.

Data handling per route

Each route hosting Perplexity Decider 1.2 has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

Perplexity — Multi-region

Zero data retention posture is not established for this route. No training on customer data. GLOBAL; unknown.

Zero data retention
Not established.
Training
No training on customer data.
Transfer mechanism
unknown

Benchmarks

Perplexity Decider 1.2 played 100 games of Pac-Man against the four arcade ghosts.

JevMan: the Pac-Man benchmark for AI decision models

Watch Perplexity Decider 1.2's JevMan game
Rank in our runs4 of 15
Mean score3,100
Best game8,340
Games100
See the JevMan benchmark →Compare all decision modelsScores from Opper's own runs. Updated Oct 24, 2026.

Get started

Call Perplexity Decider 1.2 through the Opper gateway with one API key. Evaluate state against typed questions using TypeSafe’s System One API for yes/no decisions, classification, and rubric scoring.

See the Opper evaluation guide and the TypeSafe API reference for question types and response formats. Compare every decision model, on one API.

Perplexity Decider 1.2 is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

Set it up with your agent

Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up Opper for you.

Or call it directly

curl https://api.opper.ai/v3/compat/v1/systemone \
-H "Authorization: Bearer $OPPER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "perplexity/pplx-decider-v1.2",
"state": "The customer cannot sign in and needs help immediately.",
"questions": {
"is_urgent": {
"type": "noul",
"instructions": "Does the customer need urgent help?"
}
}
}'

Use Perplexity Decider 1.2 in your apps

Pick your tool, then choose Perplexity Decider 1.2 to see how to run it through Opper.

Compare Perplexity Decider 1.2 with…

Side-by-side on privacy, EU hosting, pricing, and benchmarks.

Other models from Perplexity

Start building with 700+ models

One API key for every major provider, up and running in minutes.

Get startedView Documentation