opendunes

LFM2.5-24B-A2B

New

by LiquidReleased 13 October 2026

LFM2.5-24B-A2B is a Liquid AI model that thinks before it answers. You send text along with descriptions of your tools, and it thinks first, then either answers or uses a tool. It reads about 128 pages and writes up to 8 pages, so use it for automated helpers that use tools. Liquid recommends giving it document search or web search on questions that rest on facts, so pick a larger model when you have no search to offer.

TakesText
GivesText
Open in chatCreate API keyCompare

What it costs

You pay for what each request uses. No subscription, no minimum.

≈ 0,13 DA per message3 000 DA buys about 22 000 messages

One message, the ordinary use

1 000 tokens sent× 16,64 DA per 1M0,017 DA
500 tokens back× 232,98 DA per 1M0,12 DA
Total≈ 0,13 DA

Every rate

Meter↑ you send↓ comes back
Text tokens16,64 DA232,98 DA
Cached tokens read8,32 DA

per 1M tokens

Extracting structured fields from invoices into a fixed JSON schema≈ 0,17 DA
Summarising a cached system prompt plus a fresh user query on a repeat request≈ 0,24 DA
A tool-calling loop where the model plans a step, invokes a function and reads the result≈ 0,29 DA
Drafting a reasoned answer to a hard technical question with the chain of thought shown≈ 0,72 DA
An agent that reads a long support thread and reasons out the next action to take≈ 1,13 DA
When you pay
After the answer, from your balance. Nothing is held.
Why it varies
A longer question or a longer answer costs more.
After each one
The exact charge shows on the request.
DepositDeposits from 50 DA, with Edahabia or CIB.

Where your request runs

One company runs this model. OpenDunes sends every request to it. DA per 1M tokens: ↑ what you send · ↓ what comes back.

Liquid…
↑ Sent, per 1M
16,64 DA
↓ Back, per 1M
232,98 DA
Cache read
8,32 DA
Latency
…
Throughput
…
Provider↑ Sent↓ BackCache readLatencyThroughputUptime
Liquid16,64 DA232,98 DA8,32 DA………

You pay the price of the provider that served your request. Prices read 15:19 · speed over the last 30 minutes · uptime over 3 days.

See it in action

Real requests, real replies. Try any of them yourself — one click, pre-filled.

Structured output
You send

Turn this customer email into JSON with intent, urgency and order_id.

customer-email.txt
It replied

{ "intent": "refund", "urgency": "high", "order_id": "OD-58421" }

Try in Chat Lab
Writing
You send

Two lines to welcome a shop in Oran.

It replied

Welcome to our new shop in Oran — fresh bread every morning, and coffee the way the city likes it. Come in, the first cup is on us.

Try in Chat Lab

Try your own request — same model, pre-selected.

Open Chat Lab

Call it in code

Swap the base URL and the key. Your OpenAI code runs unchanged.

POST /v1/chat/completions
Base URL
https://opendunes.com/v1
Model ID
liquid/lfm-2.5-24b-a2b
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://opendunes.com/v1",
    api_key=os.environ["OPENDUNES_API_KEY"],
)

resp = client.chat.completions.create(
    model="liquid/lfm-2.5-24b-a2b",
    messages=[{"role": "user", "content": "Two lines to welcome a shop in Oran."}],
)

print(resp.choices[0].message.content)
pip install openaiFull reference for this route
Sign in to run it

Runs this request once on your balance.

Parameters you can send

Standard OpenAI fields, grouped by what they control. Anything not listed is accepted and ignored.

Shaping the reply

How long, how varied, where to stop.

max_tokenstemperaturetop_ptop_kmin_pstopseedfrequency_penaltypresence_penaltyrepetition_penaltylogprobstop_logprobs

Reasoning

Let it think before answering — and see the thinking.

reasoninginclude_reasoning

Structured output

Get JSON you can parse instead of prose.

response_formatstructured_outputs

Tools

Let the model call your functions.

toolstool_choice

Other

Also accepted by this model.

max_completion_tokens

Questions about LFM2.5-24B-A2B

  • How much does LFM2.5-24B-A2B cost in dinars?

    About 0,13 DA per message. ↑ 16,64 DA · ↓ 232,98 DA per 1M tokens.

  • Is LFM2.5-24B-A2B free? Can I try it?

    No. You pay per use from your balance, with no subscription. Try it in Chat at the same price.

  • What is LFM2.5-24B-A2B best for?

    LFM2.5-24B-A2B is a Liquid AI model that thinks before it answers. You send text along with descriptions of your tools, and it thinks first, then either answers or uses a tool. It reads about 128 pages and writes up to 8 pages, so use it for automated helpers that use tools. Liquid recommends giving it document search or web search on questions that rest on facts, so pick a larger model when you have no search to offer.

  • LFM2.5-24B-A2B or LFM2.5-2.6B?

    LFM2.5-2.6B costs 0,070 DA more for the same message.

  • How do I pay for LFM2.5-24B-A2B without an international card?

    Deposit dinars with your Edahabia or CIB card. Every model, LFM2.5-24B-A2B included, is paid from that balance. No foreign card, no conversion.

  • Does LFM2.5-24B-A2B work in Arabic, French or Darja?

    Liquid names no languages for LFM2.5-24B-A2B. Arabic, French and Darja: not stated.

  • Can it read PDFs, images or a whole book?

    It reads text. Up to 128K tokens in one request, about 120 pages. It writes up to 6 000 words at once.

  • Is LFM2.5-24B-A2B open source?

    Yes, its weights are public. Open weights on Hugging Face

  • Who makes LFM2.5-24B-A2B, and when was it released?

    Liquid. Released 13 October 2026.

Other Liquid models, priced in dinars

See all Liquid models
d1Liquid · Oct 1, 2026

Liquid d1 takes a situation described in text and pictures, plus questions of a fixed kind, and answers each with a yes or no, a score or a pick from options, with a probability and never with written text. Use it to route requests, sort items and run policy checks where you want a fast, scored answer to act on. It reads about 65 pages at once.

65 pages per call
≈0,0067 DAper case
View model
d1-ultraLiquid · Oct 15, 2026

Liquid d1-ultra is the largest decision model from Liquid AI. You send a situation made of words and pictures with questions of a fixed kind, and for each one you get a yes or no, a score or a pick from a list, with a probability and no written text. It suits moderation, routing, sorting and checks on pictures.

32 pages per call
≈0,014 DAper case
View model
d1.1Liquid · Oct 27, 2026

This model accepts both text and images to understand a current situation. It can process up to 65 pages of information and generate up to 58 pages of structured choices. Its primary purpose is to act as a decision-making system, taking a defined state and specific questions to output a clear choice. Because it is built for structured outcomes, it is not suited for tasks requiring open-ended creative generation.

65 pages per call
≈0,0067 DAper case
View model
LFM3-1.7BLiquid · Nov 6, 2026

This model processes text input and generates text responses, capable of handling up to 260 pages of reading material and producing outputs up to 8.1 pages long. It is specifically designed to think through problems before providing an answer, making it suitable for complex tasks that require careful consideration. This approach sets it apart from other models by prioritizing internal reasoning. However, it cannot access real-time information from the internet.

Thinks firstUses your tools260 pages at once
≈0,060 DAper message
View model