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.

ByteDance: UI-TARS 7B vs LiquidAI: LFM3-1.7B

A side-by-side comparison of ByteDance: UI-TARS 7B ($0.35 / 1M tokens) and LiquidAI: LFM3-1.7B ($0.28 / 1M tokens) using current USD prices and capabilities from the api14 catalog. Both run through the same OpenAI-compatible API.

Specifications

	ByteDance: UI-TARS 7B	LiquidAI: LFM3-1.7B
Provider	ByteDance	LiquidAI
Input	$0.35 / 1M tokens	$0.28 / 1M tokens
Output	$0.70 / 1M tokens	$0.70 / 1M tokens
Cache read	$0.35 / 1M tokens	$0.07 / 1M tokens
Context window	128,000	262,144
Max output	2,048	8,192
Input	image, text	text
Output	text	text
Tool calling
Structured output
Reasoning control
Added	Jul 22, 2025	Nov 6, 2026

Key differences

LiquidAI: LFM3-1.7B is 20% cheaper on input tokens.
LiquidAI: LFM3-1.7B reads 2.0× more context (262,144 tokens).
Only LiquidAI: LFM3-1.7B supports tool calling.
Only LiquidAI: LFM3-1.7B supports reasoning effort control.
A request with 1,000 input and 500 output tokens costs $0.000700 with ByteDance: UI-TARS 7B and $0.000630 with LiquidAI: LFM3-1.7B.

Switch with one string

Both models use the same endpoint and request shape. Change the model value from "bytedance/ui-tars-1.5-7b" to "liquid/lfm-3-1.7b" and prompts, streaming and tools keep working.

ByteDance: UI-TARS 7B details & playground →LiquidAI: LFM3-1.7B 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.chat.completions.create({
  "model": "liquid/lfm-3-1.7b",
  "messages": [
    {
      "role": "user",
      "content": "Explain vector databases in two sentences."
    }
  ]
});
console.log(result.choices[0].message.content);

More comparisons

UI-TARS 7B vs LFM3-1.7B: API price, context & features · api14