LFM2-24B-A2B
VerifiedOpen-weight LLM from Liquid AI with 128k context for long text tasks.
About LFM2-24B-A2B
Designed as an open-weight LLM, LFM2-24B-A2B allows full access to its parameters for local deployment and modification. The 128000-token context window enables processing of extended documents and conversations without frequent truncation. This architecture prioritizes handling lengthy inputs efficiently.
Its strengths lie in accessibility for researchers and developers seeking customizable text models. Typical usage includes document summarization, code assistance, and building conversational systems that maintain coherence over many turns.
Capabilities
How LFM2-24B-A2B compares
LFM2-24B-A2B (striped bar) vs other language models on intelligence, speed and price.
Price
USD per 1M output tokens · Lower is better · LFM2-24B-A2B ranks #5 of 78
Sources: Artificial Analysis (intelligence, speed) · OpenRouter (price).
Best for
Long Document Analysis
Processes and reasons over inputs up to 128000 tokens, making it effective for reviewing lengthy legal contracts or research papers.
Multi-Step Instruction Execution
Follows complex instructions reliably for generating detailed reports or structured outputs from extended prompts.
Contextual Question Answering
Delivers accurate responses by drawing on large context windows, supporting tasks like summarizing books or answering queries from technical manuals.
Strengths & limitations
Strengths
- +Large 128k token context window
- +Focused text-only design
- +Suitable for extended document tasks
- +Balanced parameter scale for language work
Limitations
- –No vision or multimodal support
- –Text inputs and outputs only
- –Standard LLM computational requirements
Cost calculator
Estimate what LFM2-24B-A2B would cost for your usage.
Based on LFM2-24B-A2B's $0.03/1M input · $0.12/1M output. Estimate only — actual cost varies by provider and caching.
Quick start
OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. Only the model slug changes between models.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://openrouter.ai/api/v1",
apiKey: process.env.OPENROUTER_API_KEY,
});
const completion = await client.chat.completions.create({
model: "liquid/lfm-2-24b-a2b",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(completion.choices[0].message.content);Model slug: liquid/lfm-2-24b-a2b
Editor's verdict
LFM2-24B-A2B is Liquid AI's open-weight language models with a 128K-token context window.
At $0.12 per 1M output tokens, it is very cost-efficient for its class.
As an open-weight model you can self-host it or call it through a hosted API.
Best suited to large 128k token context window and focused text-only design.
Frequently asked questions
The model provides a context window of 128000 tokens.
User reviews
Real, verified reviews from the community shape this model's rating.
Loading reviews…
Similar models
Other language models worth comparing.