api14
Get API key

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.

LiquidAI: LFM2.5-2.6B vs Mistral: Saba

A side-by-side comparison of LiquidAI: LFM2.5-2.6B ($1.22 / 1M tokens) and Mistral: Saba ($0.70 / 1M tokens) using current USD prices and capabilities from the api14 catalog. Both run through the same OpenAI-compatible API.

Specifications

LiquidAI: LFM2.5-2.6BMistral: Saba
ProviderLiquidAIMistral
Input$1.22 / 1M tokens$0.70 / 1M tokens
Output$1.75 / 1M tokens$2.10 / 1M tokens
Cache read$0.14 / 1M tokens$0.07 / 1M tokens
Context window128,00032,768
Max output8,19226,214
Inputtexttext, file
Outputtexttext
Tool calling
Structured output
Reasoning control
AddedAug 11, 2026Feb 17, 2025

Key differences

  • Mistral: Saba is 43% cheaper on input tokens.
  • LiquidAI: LFM2.5-2.6B is 17% cheaper on output tokens.
  • LiquidAI: LFM2.5-2.6B reads 3.9× more context (128,000 tokens).
  • Only LiquidAI: LFM2.5-2.6B supports reasoning effort control.
  • A request with 1,000 input and 500 output tokens costs $0.00210 with LiquidAI: LFM2.5-2.6B and $0.00175 with Mistral: Saba.

Switch with one string

Both models use the same endpoint and request shape. Change the model value from "liquid/lfm-2.5-2.6b" to "mistralai/mistral-saba" and prompts, streaming and tools keep working.

LiquidAI: LFM2.5-2.6B details & playground →Mistral: Saba 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": "mistralai/mistral-saba",
  "messages": [
    {
      "role": "user",
      "content": "Explain vector databases in two sentences."
    }
  ]
});
console.log(result.choices[0].message.content);

More comparisons