Post-Cutoff

Perplexitypplx-decider familyCurrentLanguage modelReleased 1 Oct 2026

pplx-decider-v1-27b

Open-weights decision model behind Perplexity’s Decisions API. Send a request with your content plus typed questions to POST https://api.perplexity.ai/v1/decisions; output tokens are free.

Model idpplx-decider-v1-27b

Price$0.04 in per 1M tokens; output free

Checked3 October 2026

No published training cutoff

At least1,298events since its release on 1 October 2026

57 historic, 291 major. 49 days of news.

Perplexity doesn’t publish a training cutoff, so we count from its release date. The real gap is larger.

Five things it has never heard of

How to call it

2 ways to use pplx-decider-v1-27b, with the model id each provider expects.

Providers, model ids, endpoints and docs for pplx-decider-v1-27b
ProviderModel idEndpointDocs
Perplexity API pplx-decider-v1-27b https://api.perplexity.ai/v1/decisions docs.perplexity.ai
Hugging Face huggingface.co

Pricing

Prices for pplx-decider-v1-27b
Input$0.04 per 1M tokens
Output$0 per 1M tokens

As published: “per 1M tokens (output tokens free; Decisions API)”.

Source: docs.perplexity.ai, checked 3 October 2026.

Specs

Input
Text and images
Output
Text
Context window
262,144 tokens
Max output
Not published
Open weights
Yes
Licence
Apache-2.0
Training cutoff
Not published
Released
1 October 2026
Status
Current
Type
Language model

What stands out

What its maker marketed at launch, and what people found later, each with its source.

  • Decision model (probabilities over fixed answers)

    Returns a probability distribution over the allowed options for 1–128 typed questions per request instead of generating text; Perplexity reports 85.71% on its 11-benchmark panel vs 84.51% for Jev.

    Source: huggingface.co

Notes

Fine-tuned from Qwen3.8-27B. Context is the API’s 262,144-token input limit. Benchmarks are Perplexity’s own; Jev still leads on 4–6 of 11 tests.