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.
parallel/decisions-fast:freeRuns on your balance at the prices above. New accounts start with free usage.
Settings
Parallel: Decisions Fast (free) is a model from Parallel, listed on api14 under the decisions category. It is built for decision tasks rather than conversation, and its provider describes it as Parallel's web-grounded Decisions model. The model was released by the provider on 2026-11-06.
The model takes text as input and returns decisions as output. It does not generate prose. Instead, it reads the content passed as state, which can be text or JSON, researches the live web, and returns typed answers. The context window is 32,000 tokens, and the maximum output is 28,800. Because the input modality is text only, any material the model should consider has to arrive as text or JSON in the request.
The practical use cases follow from that shape. If your application needs a typed answer rather than a paragraph, such as classifying a record, choosing between options, or resolving a question against current web information, this model is designed for that pattern. Passing structured state as JSON lets you hand it the fields it should reason over, and the typed decision that comes back can be consumed directly by code without parsing free text. The web grounding matters when the correct answer depends on information that changes over time, since the model researches the live web as part of producing its answer.
You call it through api14's OpenAI-compatible API using the model id "parallel/decisions-fast:free". The model supports no request parameters beyond what the API itself requires, so there are no sampling or formatting options to configure on the request. The free variant carries the same model id suffix shown above, so you can point an existing OpenAI-compatible client at api14 and select this id without changing your integration code.
Consider whether a text-generating model fits better when you need an explanation, a summary, or any natural language response, since this model returns decisions rather than text. It also accepts text input only, so image or audio inputs are out of scope. Within those bounds, it is a straightforward choice for applications that want a typed, web-grounded answer to a decision problem.
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": "parallel/decisions-fast:free",
"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);
This community has no topics yet. Open the first one about Parallel: Decisions Fast (free).