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.

rerank-2.5-lite vs Nemotron 3.5 Rerank 8B (free): API price, context & features · api14

VoyageAI by MongoDB: rerank-2.5-lite vs NVIDIA: Nemotron 3.5 Rerank 8B (free)

A side-by-side comparison of VoyageAI by MongoDB: rerank-2.5-lite (Free) and NVIDIA: Nemotron 3.5 Rerank 8B (free) (Free) using current USD prices and capabilities from the api14 catalog. Both run through the same OpenAI-compatible API.

Specifications

	VoyageAI by MongoDB: rerank-2.5-lite	NVIDIA: Nemotron 3.5 Rerank 8B (free)
Provider	VoyageAI by MongoDB	NVIDIA
Context window	32,000	32,768
Max output	28,800	29,491
Input	text	text, image
Output	rerank	rerank
Tool calling
Structured output
Reasoning control
Added	Jul 27, 2026	Oct 21, 2026

Switch with one string

Both models use the same endpoint and request shape. Change the model value from "mongodb/rerank-2.5-lite" to "nvidia/nemotron-3.5-rerank-8b:free" and prompts, streaming and tools keep working.

VoyageAI by MongoDB: rerank-2.5-lite details & playground →NVIDIA: Nemotron 3.5 Rerank 8B (free) 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("/rerank", { body: {
  "model": "nvidia/nemotron-3.5-rerank-8b:free",
  "query": "What is the capital of France?",
  "documents": [
    "Paris is the capital of France.",
    "Berlin is in Germany."
  ],
  "top_n": 1
} });
console.log(result.results);

VoyageAI by MongoDB: rerank-2.5-lite vs NVIDIA: Nemotron 3.5 Rerank 8B (free)

Specifications

Switch with one string

More comparisons