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.

New here? See how it works A 1-minute tour of the playground, models and your API key.

Tev1 4B Experimental vs Jev 1.13: API price, context & features · api14

Together: Tev1 4B Experimental vs TypeSafe: Jev 1.13

A side-by-side comparison of Together: Tev1 4B Experimental ($0.15 / 1M tokens) and TypeSafe: Jev 1.13 ($0.15 / 1M tokens) using current USD prices and capabilities from the api14 catalog. Both run through the same OpenAI-compatible API.

Specifications

	Together: Tev1 4B Experimental	TypeSafe: Jev 1.13
Provider	Together	TypeSafe
Input	$0.15 / 1M tokens	$0.15 / 1M tokens
Context window	32,768	262,144
Max output	8	235,929
Input	text	text, image
Output	decisions	decisions
Tool calling
Structured output
Reasoning control
Added	Sep 30, 2026	Sep 18, 2026

Key differences

Both have about the same input price.
TypeSafe: Jev 1.13 reads 8.0× more context (262,144 tokens).
A request with 1,000 input and 500 output tokens costs $0.000147 with Together: Tev1 4B Experimental and $0.000147 with TypeSafe: Jev 1.13.

In depth

Together: Tev1 4B Experimental is a model from Together, listed under the decisions category, and it takes text as input and returns decisions as output. TypeSafe: Jev 1.13 comes from TypeSafe and sits in the same decisions category, also returning decisions, but it accepts both text and images as input. Both are decision oriented models rather than general chat models, so you should expect them to be used where the result you want is a choice or a verdict rather than a long piece of prose.

The clearest difference between them is context. TypeSafe: Jev 1.13 supports a context window of 262144 tokens, while Together: Tev1 4B Experimental supports 32768 tokens, so Jev 1.13 is the larger context option by a wide margin. Jev 1.13 also accepts image input alongside text, whereas Tev1 4B Experimental is text only. On price, the qualitative comparison marks input cost as a tie, so neither model is meaningfully cheaper than the other on the input side, and the live price table on this page is the place to check current numbers. Neither model lists supported parameters, so you should not plan on tuning sampling or tool style options through the request body.

For practical selection, reach for TypeSafe: Jev 1.13 when the decision depends on a large amount of material, such as a long document, a big log, or a whole repository of text that has to be weighed at once, and also when part of the input is an image that the model needs to consider. Reach for Together: Tev1 4B Experimental when the input is plain text and fits comfortably inside 32768 tokens, which covers many everyday decision tasks where a shorter prompt is enough. If you are unsure, the larger context and image support of Jev 1.13 make it the more flexible default, while Tev1 4B Experimental is the simpler choice when you know your input is text only and modest in size.

Calling either model through api14 works the same way because the API is OpenAI compatible. You point your client at the api14 base URL, send a chat completions style request, and set the model field to the id you want. To switch between them you change only that model id, using togethercomputer/tev1-4b-experimental for the Together model and typesafe/jev-1.13 for the TypeSafe model. Everything else in the request, including your messages and any other fields you normally send, stays as it is, so you can compare the two by editing a single string.

There is one case where Together: Tev1 4B Experimental remains the better pick even though Jev 1.13 is larger and accepts images. If your task is text only and your prompt fits inside 32768 tokens, the extra context of Jev 1.13 buys you nothing, and since input pricing is a tie you are not saving money by switching either way. In that situation the smaller, text only model is a perfectly reasonable call, and you can keep it as your default for short text decisions while reserving typesafe/jev-1.13 for the long or image bearing cases.

Switch with one string

Both models use the same endpoint and request shape. Change the model value from "togethercomputer/tev1-4b-experimental" to "typesafe/jev-1.13" and prompts, streaming and tools keep working.

Together: Tev1 4B Experimental details & playground →TypeSafe: Jev 1.13 details & playground →

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": "typesafe/jev-1.13",
  "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);

Together: Tev1 4B Experimental vs TypeSafe: Jev 1.13

Specifications

Key differences

In depth

Switch with one string

More comparisons