PriceIndex
LI

LFM2.5-24B-A2B Pricing & API Specs

lfm-2.5-24b-a2b
APIProvider site

LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid... Built by Liquid.

Prices updated

Input price

$0.05

per 1M tokens · Standard

Output price

$0.70

per 1M tokens · Standard

Input limit

128K

tokens

Output limit

8K

tokens

Input formats

TextImageVideoAudioPDF

Output formats

TextImageVideoAudioPDF
Compare

LFM2.5-24B-A2B price history

2 price records since 10/18/2026

LFM2.5-24B-A2B cost calculator

Input20M tokens
Output5M tokens

$4.50/month

Standard pricing

    Overview

    What is LFM2.5-24B-A2B?

    LFM2.5-24B-A2B is a text & reasoning model from Liquid priced at $0.05 input and $0.70 output per 1M tokens, with a 128K context window. Its low input price suits high-volume work; no AA Intelligence score has been published yet.

    Price: Qwen3 30B A3B (+$0.003)Price: Qwen3 8B (−$0.011)Price: Claude Haiku 5.5 (−$0.012)

    Rates

    LFM2.5-24B-A2B pricing

    Pricing is based on token usage. Provider-specific caching, batch, regional, and tool charges may affect the final cost.

    Input · Standard

    $0.05

    Per 1M tokens

    Cached input · Standard

    $0.03

    Per 1M tokens

    Capabilities

    LFM2.5-24B-A2B Tools

    Tools available when using LFM2.5-24B-A2B through supported provider APIs.

    JSON mode

    Supported

    Reasoning

    Supported

    Strengths and limitations

    Strengths

    • Price rank 69 of 330 tracked models (1 = cheapest, by blended price).
    • Blended price at 3 input : 1 output is $0.21 per 1M tokens.
    • 1M input + 250K output tokens costs about $0.22.
    • Context window 128K vs a median of 262K (2.0× smaller).

    Limitations

    • Generated tokens cost 14× more than input tokens, which matters for verbose responses.
    • The 128K context window is smaller than several long-context alternatives.
    • Benchmarks are directional; test accuracy, latency and reliability on your own workload before committing.

    Public listed prices, checked Nov 9, 2026. Benchmarks as published by their sources. Confirm with the provider.

    Frequently asked questions about LFM2.5-24B-A2B

    LFM2.5-24B-A2B is a text & reasoning model from Liquid. LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid...

    LFM2.5-24B-A2B costs $0.05 per million input tokens and $0.70 per million output tokens on standard pricing. A workload of 20M input and 5M output tokens a month is about $4.50.

    LFM2.5-24B-A2B accepts up to 128,000 tokens (128K) of input and can return up to 8,192 tokens in one response.

    Yes, LFM2.5-24B-A2B supports function/tool calling and structured (JSON) outputs. Supported tools: Function calling, Structured outputs, JSON mode, Reasoning, Log probabilities, Deterministic seed, Prompt caching.

    LFM2.5-24B-A2B accepts Text as input and produces Text as output.

    LFM2.5-24B-A2B is available from 1 API provider: Liquid. Prices can differ by provider.

    LFM2.5-24B-A2B was released by Liquid in 2026-10-13.