Model tracker / Decision models / Perplexity
Perplexity Decider V1.2
Open-weight 27B decision model on Qwen3.8-27B for typed questions about text and images
Perplexity Decider V1.2 is an open-weight decision model from Perplexity (Apache 2.0, 27B parameters): it answers typed questions, such as yes or no, pick one or pick several, with probabilities instead of writing text. It costs $0.02 per million input tokens (OpenRouter, Vercel AI Gateway), and output is free. It scores 81.7 (self-hosted; seconds are the board's estimate; not capability-ranked, as its cost is above the board's cap) on the independent JevBench Capability Score (board v1.7.46), where Jev, the reference, scores 77.1.
- Made by
- Perplexity
- Weights
- Open, Apache 2.0
- Size
- 27B
- Where
- OpenRouter, Vercel AI Gateway
- Images
- Yes
- Context
- 262,144 (trained on up to about 32K)
- Fine-tuning
- Not stated
Perplexity Decider V1.2 price
US dollars per million input tokens. Decision models don't write text, so none of the hosted ones charge for output.
| Where | Input | Output | Notes | Checked |
|---|---|---|---|---|
| OpenRouter, Vercel AI Gateway | $0.02 | Free | Output is free. Price on OpenRouter and Vercel's AI Gateway; succeeds Decider V1.1 27B. | 2026-10-24 |
Perplexity Decider V1.2 benchmarks
| Benchmark | Result | What it measures | Reported by |
|---|---|---|---|
| JevBench v1.7.46 | 81.7 | Capability Score: accuracy and calibration on typed decisions, with Jev as the reference system | Independent |
| JevBench time | 0.43 s | Seconds per decision: measured end to end for hosted APIs, the board's estimate for self-hosted models | Independent |
| Reported speed | 96 ms median for a Decision Index request on one GB200 | Latency on the maker's own hardware | Perplexity |
Makers' speeds are measured on their own hardware and aren't comparable with each other or with JevBench's timings.
Decision models like Perplexity Decider V1.2
Every other decision model we track, by independent JevBench score.
| Model | Input / M | JevBench | Weights |
|---|---|---|---|
| Perplexity Decider V1.2 | $0.02 | 81.7 | Open |
| d1-ultra Liquid AI | $0.042 | 80.5 | Closed |
| Clef Cloudflare | $0.24 | 75.3 | Open |
| Jev 1.14 TypeSafe AI | $0.042 | 75.0 | Closed |
| d1 Liquid AI | $0.02 | 74.4 | Closed |
| OpenAI Decisions (GPT-6 Luna) OpenAI | $0.10 | 73.5 | Closed |
| Microsoft-Decision-1 Microsoft | $0.042 | 70.8 | Closed |
| Clef-flash Cloudflare | $0.038 | 63.8 | Open |
| Perplexity Decider Flash V1.2 Perplexity | $0.01 | 62.5 | Open |
| Clef-omni Cloudflare | $0.15 | 58.3 | Open |
| d1-3B Liquid AI | Self-host | 49.5 | Open |
| d1-omni-600M (experimental) Liquid AI | Self-host | 32.8 | Open |
| Laya Convai Innovations | Free | 32.5 | Open |
| CLM-8B Stanford and NVIDIA | Self-host | 20.1 | Open |
| Clairic Cloudflare | $0.10 | – | Closed |
| Elephant-1 Baseten (Base Labs) | Free | – | Open |
| Mammoth-1 Baseten (Base Labs) | Free | – | Open |
| Strands Decider 2B AWS Strands Labs | Self-host | – | Open |
Compare them all in the decision models table →
Perplexity Decider V1.2 FAQ
How much does Perplexity Decider V1.2 cost?
Perplexity Decider V1.2 costs $0.02 per million input tokens at OpenRouter, Vercel AI Gateway. Output is free. Price on OpenRouter and Vercel's AI Gateway; succeeds Decider V1.1 27B. Checked 24 October 2026.
Is Perplexity Decider V1.2 open weight?
Yes. Perplexity publishes the weights under Apache 2.0, so you can run and fine-tune it yourself.
How fast is Perplexity Decider V1.2?
Perplexity reports 96 ms median for a Decision Index request on one GB200, measured on its own hardware. JevBench gives 0.43 seconds per decision, its estimate for self-hosting.
How does Perplexity Decider V1.2 compare with Jev?
On JevBench's Capability Score (board v1.7.46), Perplexity Decider V1.2 scores 81.7 against Jev's 77.1. Jev costs $0.042 per million input tokens; Perplexity Decider V1.2 costs $0.02. JevBench is a one-person project that uses Jev as its reference, which favours cheap hosted models.