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.
baseten/mammoth-1Runs on your balance at the prices above. New accounts start with free usage.
Settings
Baseten: Mammoth 1 is a decision model from Baseten, developed by Base Labs, Baseten's research team. It is built on Qwen3.5-27B, a 27B parameter base, and its provider release date is 2026-10-21. Its main category is decisions, and it is designed around answering typed questions rather than producing free-form prose.
The model takes text as its input and produces decisions as its output. It works from a state, supplied as text or JSON, together with typed questions. The supported question types are yes/no, multiple choice, and ordinal questions. The context window is 16,384 tokens, and the maximum output is 14,745 tokens. No request parameters are listed as supported for this model.
The practical use cases follow directly from that shape. Because it accepts a state plus typed questions, it fits workflows where you need a structured judgement rather than a generated paragraph: classifying a record with a yes/no answer, selecting one option from a set of choices, or placing an item on an ordinal scale. Supplying the state as JSON makes it straightforward to feed in application data, logs, or configuration and get back a decision. The 16,384 token context window bounds how much state and how many questions you can present in a single call.
You call it through api14's OpenAI-compatible API using the model id "baseten/mammoth-1". Because the interface is OpenAI-compatible, you can point an existing OpenAI client at api14 and set that model id in your request. The model accepts text input and returns decisions, and no request parameters are listed as supported, so plan your integration around the default request shape rather than relying on optional knobs.
Since the model is scoped to decisions and takes only text input, it is not the right fit when you need generated text, image or audio input, or tool-style interactions. If your task is producing prose, code, or other free-form output, a text generation model will serve you better. Mammoth 1 is the choice when the output you want is a decision over a supplied state.
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": "baseten/mammoth-1",
"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 Baseten: Mammoth 1.