GenAIWiki

Perplexity Decider v1.2

CurrentLatest

pplx-decider-v1-2 is the 27B model behind Perplexity's Decisions API, released in October 2026 (alias pplx-decider-latest).

Provider

Perplexity

Model family

Perplexity Decider

Decision model

Cost tier

Decider

Status

Current

Technical specs

Inputs
text, image
Outputs
text
License
Proprietary API
Api Alias
pplx-decider-latest
Max Images
8
Parameters
27B
Max Input Tokens
256,000
Input Usd Per Million
0.02
Output Usd Per Million
0
Capabilities
  • Structured decisions via POST /v1/decisions
  • Text and up to 8 images per question
  • Under 256K input tokens

Why teams choose it

🧠

Complex reasoning

Useful for workflows that require structured thinking, multi-step logic, and deeper analysis than lightweight models provide.

📎

Long-context analysis

Helps teams summarize, compare, and extract insights from long documents without losing important nuance.

⚙️

Perplexity roadmap vigilance

Use published model pages—not stale marketing blurbs—for modalities, quotas, pricing, and policy; schedule revalidation tied to vendor release notes.

✍️

Cost-efficient routing

Useful as part of a routing stack where cheap models handle drafts and confirmations and this tier handles genuinely hard passages.

Tradeoffs to know

  • Not a chat or generation model.

When not to use this

  • Perplexity's docs do not give an exact release day.

Benchmarks

No independent or vendor benchmark scores in this catalog entry.

See comparisons →


Perplexity Decider family lineup


Related models

Perplexity Decider v1.2 FAQ

What is Perplexity Decider v1.2?

pplx-decider-v1-2 is the 27B model behind Perplexity's Decisions API, released in October 2026 (alias pplx-decider-latest). You send a question with candidate answers to POST /v1/decisions and it returns a decision rather than free-form text. It accepts text and image input, under 256K input tokens and up to 8 images per question. Pricing is $0.02 per million input tokens; output is free.

When does Perplexity Decider v1.2 fit best?

LLM-as-judge and grading pipelines

What should teams watch out for with Perplexity Decider v1.2?

Not a chat or generation model.

Explore next

Models, tools, and comparisons that connect to this reference.