Using pplx-decider-flash-v1.2 on Vercel AI Gateway

Implementation guide · PPLX Decider · Perplexity Labs

ServerlessOpen Source

Vercel AI Gateway exposes pplx-decider-flash-v1.2 through model ID perplexity/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
Create an account at Vercel AI Gateway and generate an API key.
2
Use the Vercel AI Gateway SDK or REST API to call perplexity/pplx-decider-flash-v1.2 — see the documentation for request format.
3
You'll be billed $0.01/1M input, Free/1M output tokens. See full pricing.

API Portal Documentation Pricing Model Card

Code Examples

Install

pip install openai

API key

AI_GATEWAY_API_KEY

Model ID

perplexity/pplx-decider-flash-v1.2

creator/model-name e.g. kwaipilot/kat-coder-pro-v2

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AI_GATEWAY_API_KEY"],
    base_url="https://ai-gateway.vercel.sh/v1"
)
response = client.chat.completions.create(
    model="perplexity/pplx-decider-flash-v1.2",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

Pricing on Vercel AI Gateway

Type	Price (per 1M)
Input tokens	$0.01
Output tokens	Free
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

Vercel