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.

DeepSeek: DeepSeek V4 Flash 0423 vs LiquidAI: LFM3-1.7B

A side-by-side comparison of DeepSeek: DeepSeek V4 Flash 0423 ($0.32 / 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

	DeepSeek: DeepSeek V4 Flash 0423	LiquidAI: LFM3-1.7B
Provider	DeepSeek	LiquidAI
Input	$0.32 / 1M tokens	$0.28 / 1M tokens
Output	$0.64 / 1M tokens	$0.70 / 1M tokens
Cache read	$0.06 / 1M tokens	$0.07 / 1M tokens
Context window	1,048,576	262,144
Max output	943,717	8,192
Input	text	text
Output	text	text
Tool calling
Structured output
Reasoning control
Added	Apr 24, 2026	Nov 6, 2026

Key differences

LiquidAI: LFM3-1.7B is 12% cheaper on input tokens.
DeepSeek: DeepSeek V4 Flash 0423 is 9% cheaper on output tokens.
DeepSeek: DeepSeek V4 Flash 0423 reads 4.0× more context (1,048,576 tokens).
A request with 1,000 input and 500 output tokens costs $0.000637 with DeepSeek: DeepSeek V4 Flash 0423 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 "deepseek/deepseek-v4-flash" to "liquid/lfm-3-1.7b" and prompts, streaming and tools keep working.

DeepSeek: DeepSeek V4 Flash 0423 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

DeepSeek V4 Flash 0423 vs LFM3-1.7B: API price, context & features · api14