Using pplx-decider-flash-v1.2 on Perplexity Labs

Implementation guide · PPLX Decider · Perplexity Labs

ServerlessOpen Source

Perplexity Labs exposes pplx-decider-flash-v1.2 through model ID pplx-decider-flash-v1.2. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-10-17. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at Perplexity Labs and generate an API key.
  2. 2
    Use the Perplexity Labs SDK or REST API to call pplx-decider-flash-v1.2 — see the documentation for request format.
  3. 3
    You'll be billed $0.01/1M input, Free/1M output tokens. See full pricing.
API PortalDocumentationPricingModel Card

Code Examples

See Perplexity Labs documentation for integration details.

Pricing on Perplexity Labs

TypePrice (per 1M)
Input tokens$0.01
Output tokensFree
Image input$1.00

Capabilities

VisionMultimodalStructured Outputs

About pplx-decider-flash-v1.2

pplx-decider-flash-v1.2 is Perplexity's 4B multimodal decision model, released 2026-10-16. It is fine-tuned from Qwen3.5-4B and distilled from Perplexity's 27B decision models on their training requests. Like the other PPLX Decider models it returns probabilities instead of text. It reads a state of text, JSON, or images and answers 1 to 128 named questions per request (noul for yes/no, choice with up to 255 options, or score with up to 10 levels). It is called via POST https://api.perplexity.ai/v1/decisions with model pplx-decider-flash-v1.2 or the alias pplx-decider-flash-latest. Input must stay under 256K tokens.

Full model details →

Model Specs

Released2026-10-16
Parameters4B
Context256K

More Models on Perplexity Labs

pplx-decider-v1-27bpplx-decider-v1.1-27bpplx-decider-v1.2
All models on Perplexity Labs →

Also available on(2)

OpenRouter$0.01/1MVercel AI Gateway$0.01/1M
Compare all providers →

Provider

Perplexity Labs

Perplexity

San Francisco, California, United States