ModelPriceWatch.com
Last scan 2026-11-07 Models tracked 308 Providers 42 Cheapest paid pplx-decider-flash-v1.2 $0.010/Mtok in Every price links to its source

LFM2.5-24B-A2B

by Liquid AI · 24B (2B active) parameters

Current new · 25d budget open weights cheap tier
Email me when LFM2.5-24B-A2B gets cheaper
Availability: Sold per token by Liquid AI on Liquid Console (every new organization gets $2 of free credit), and at the same price through OpenRouter, where Liquid is the only provider, and Vercel AI Gateway. The open weights are on Hugging Face under the LFM Open License v1.0, which is free for businesses under $10M in annual revenue; larger companies need a paid licence to self-host.

Today's price · per 1M tokens

Input

$0.050

per 1M tokens

Output

$0.700

per 1M tokens

Blended

$0.212

blended $/1M — 3:1 weighted input:output

Cached input

$0.025

50% of input — prompt caching

How this price is scoped: Liquid AI's own rate card lists LFM2.5-24B-A2B at $0.05 / 1M input tokens, $0.025 / 1M cached input tokens and $0.70 / 1M output tokens, and states the price is the same on Liquid Console, OpenRouter and Vercel AI Gateway. It is a reasoning-only model, so its thinking tokens are billed as output.

Source: official Liquid AI pricing · read MODELPRICEWATCH.COM · 2026-11-07

Price receipt

We read Liquid AI's own pricing page on and found LFM2.5-24B-A2B listed with a price on the same row — that read is where the number above comes from, recorded as a new model. We keep the page text we read; its content hash is 5f49bf0d2d.

Overview

The largest and last model in Liquid AI's LFM2.5 family, a mixture-of-experts reasoning model with 24B total and 2B active parameters that always thinks before it answers. It is post-trained for tool calling and multi-step agent tasks, has a 131,072-token context window, and is built to run fast on-device as well as in the cloud. $0.05 input / $0.70 output per 1M tokens on Liquid's API.

Run it yourself

Deploy this open model on rented GPUs

Open weights mean you can self-host instead of paying per-token API prices. These platforms let you serve it on demand — often cheaper at scale.

RunPod →
Rent GPUs by the second and serve any open-weight model yourself.
Novita AI →
Serverless open-model inference billed per token — no GPU ops.
Vast.ai →
GPU marketplace — rent spot/on-demand GPUs cheaply and serve any open-weight model.

Partner links — we may earn a commission if you sign up, at no cost to you. We only list platforms we'd recommend regardless.

Capabilities

struck through = not supported
Input 1/4
Text ✓ Image Audio Video
Output
Text ✓
Features 5/9
Prompt caching ✓ Reasoning ✓ Coding Fast inference ✓ Long context ✓ Open weights ✓ Multimodal Web search Realtime

Benchmark performance

accuracy % · higher is better
GPQA Diamond vendor
74.42%
SWE-Bench Verified vendor
51%

Every per-benchmark score we hold for this model is reported by its own vendor, so none is counted toward an accuracy average or any ranking.

Source: Liquid AI LFM2.5-24B-A2B launch post (SWE-Bench Verified, OpenCode scaffold), Liquid AI LFM2.5-24B-A2B launch post (Table 1) · updated · See full rankings →

Specifications

Provider
Liquid AI
Context window
131K tokens
Modality
text
Parameters
24B (2B active)
Open source
Yes — open weights available
Released
Status
Current
Last updated
Tags
budgetopen-weightsreasoningagenticmoecachingfast

Availability verified: — listed on Liquid AI's own page

Try on Liquid AI Official pricing page