Perplexity pplx-decider
Perplexity's open decision model: typed yes/no, choice and score answers with probabilities, by API or open weights
pplx-decider is Perplexity's decision model. Given a state (text, JSON or images) and named questions, it returns a probability for each answer instead of generated text: yes/no, one of up to 255 options, or a level on a rubric. A request can carry up to 262K input tokens.
The Decisions API serves pplx-decider-v1.1-27b and the earlier v1 at $0.02 per 1M input tokens, output free (October 2026). Both are on Hugging Face under Apache-2.0; v1 is fine-tuned from Qwen3.8 27B and needs a CUDA GPU with about 49 GiB free.
Pricing: Free (open weights); usage-based on Perplexity API
Choosing a decision model right now?
One click, anonymous. Helps us know our visitors.
Thanks, that helps.
Choosing a decision model right now?
One click, anonymous. Helps us know our visitors.
Thanks, that helps.
Perplexity pplx-decider prices by model
Per 1M tokens, read off Perplexity pplx-decider's own pricing page on the date shown.
| Model | Input / 1M | Cached / 1M | Output / 1M | Checked | Notes |
|---|---|---|---|---|---|
| pplx-decider v1.1 27B | $0.02 | – | $0.00 | 15 Oct 2026 | Output tokens are free. v1 is the same price. |
Perplexity pplx-decider Alternatives
Explore 150 products in the Inference APIs category. View all Perplexity pplx-decider alternatives.
Kev
Open decision models from 0.8B to 27B, built on Qwen and compatible with TypeSafe's Jev API.
Laya
Open-source multilingual decision model: typed choices, scores and yes/no answers in one forward pass.
SaladCloud
Container GPU cloud on a distributed network of consumer RTX GPUs, billed per second by priority tier
Work on Perplexity pplx-decider? Feature it at the top of Inference APIs.
Is your product missing?