We use cookies. Cookies and browser storage keep you signed in and remember your preferences. With your permission we also measure how the site is used. You can any time. See our cookie policy.
Perplexity: Decider Latest
~perplexity/pplx-decider-latestTry Perplexity: Decider Latest now
Runs on your balance at the prices above. New accounts start with free usage.
Results will appear here.
Settings
Perplexity: Decider Latest at a glance
- Input price is 52% lower than the median of 25 Decisions models.
- Context window of 262,144 tokens, enough for long documents and multi-turn conversations.
- A typical request (1,000 input / 500 output tokens) costs about $0.000070.
About Perplexity: Decider Latest
Perplexity: Decider Latest is a model from Perplexity, listed on api14 under the decisions category. Its model id is ~perplexity/pplx-decider-latest, and the provider describes it as a model that always redirects to the latest model in the Decider family. That means the id is a moving target: when Perplexity updates the Decider family, this id points at the newest member rather than a frozen snapshot. The provider release date for this entry is 2026-10-14.
The model accepts text and image inputs and produces decisions as its output. Its context window is 262,144 tokens, and the maximum output is 235,929 tokens. Because the output modality is decisions rather than free form text, the model is built to return a choice or verdict rather than prose you would display directly to an end user. The large context window means you can supply long documents, transcripts or image plus text bundles in a single request without chunking them first.
Practical use cases follow from that shape. You can route classification and triage work to it, such as deciding which queue a support ticket belongs to, whether a flagged item needs human review, or which of several candidate actions to take next. With image input, the same decision step can include screenshots, scanned pages or photos alongside text instructions. The long context suits decision tasks over lengthy material, for example picking the relevant clause from a contract, choosing between options after reading a full incident report, or selecting a next step from a long tool output.
You call it through api14's OpenAI-compatible API using the model id ~perplexity/pplx-decider-latest. Because the endpoint follows the OpenAI chat completions shape, you can point an existing OpenAI client at api14 and change only the model field. The model lists no supported parameters, so do not rely on sampling controls, tool definitions or response format options being honoured; send your instructions and inputs in the messages and read the decision from the response. The page shows a live price table for current rates.
The main caveat is the redirect behaviour. Since the id always resolves to the latest Decider model, behaviour can change without you editing your code, which is convenient for staying current but awkward if you need reproducible outputs for evaluation or regression tests. If you need stable, versioned behaviour, or if your task needs generated text rather than a decision, another model on api14 will fit better.
How to call the Perplexity: Decider Latest API
- Create an API key in your dashboard.
- Install the official openai SDK for your language.
- Set baseURL to https://api14.com/api/v1 and model to "~perplexity/pplx-decider-latest".
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api14.com/api/v1",
apiKey: process.env.API14_API_KEY,
});
const result = await client.post("/decisions", { body: {
"model": "~perplexity/pplx-decider-latest",
"state": "Customer: I was charged twice for my order and want my money back.",
"questions": {
"team": {
"type": "choice",
"instructions": "Which team should handle this message?",
"criteria": {
"billing": "Payments, refunds, invoices",
"support": "Product questions and bugs",
"sales": "Pricing and new purchases"
}
},
"urgent": {
"type": "noul",
"instructions": "Does this need a reply today?",
"criteria": {
"true": "Money, outage or legal risk",
"false": "Can wait"
}
}
}
} });
console.log(result.answers);
Specifications
- Context length
- 262,144
- Max output
- 235,929
- Input
- text, image
- Output
- decisions
Requests on api14 · last 7 days
Perplexity: Decider Latest: frequently asked questions
- How much does the Perplexity: Decider Latest API cost?
- Perplexity: Decider Latest costs Input $0.07 / 1M tokens. It is charged from your USD balance only for successful requests; failed requests are free.
- What is the context window of Perplexity: Decider Latest?
- Perplexity: Decider Latest reads up to 262,144 tokens per request: prompt, history and documents together. It writes up to 235,929 output tokens per response.
- What can Perplexity: Decider Latest do?
- Perplexity: Decider Latest accepts text, image and returns decisions.
- How do I call Perplexity: Decider Latest from my code?
- Point any OpenAI SDK at https://api14.com/api/v1 and set the model to "~perplexity/pplx-decider-latest". No other code changes. Copy a ready example from the code panel on this page.
- What are alternatives to Perplexity: Decider Latest?
- Comparable Decisions models at a similar price: Perplexity: Decider V1.2, Inception: Mercury Decide, Respan: Span-01. Each runs through the same API key, so switching is one string.
Perplexity: Decider Latest community
New topicThis community has no topics yet. Open the first one about Perplexity: Decider Latest.