Skip to content
OpenKey

LFM2-24B-A2B

Liquid AIReleased Feb 25, 2026

LFM2-24B-A2B is the largest model in the LFM2 family of hybrid architectures designed for efficient on-device deployment. Built as a 24B parameter Mixture-of-Experts model with only 2B active parameters per...

Try in playground
Context window
128K tokens
Input
text
Output
text
Tokenizer
Other
Released
Feb 25, 2026

Pricing

Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.

Per 1M tokensProvider+ 3% feeYou pay
Input$0.030$0.0009$0.031
Output$0.120$0.0036$0.124

Supported parameters

  • frequency_penalty
  • logit_bias
  • max_tokens
  • min_p
  • presence_penalty
  • repetition_penalty
  • response_format
  • stop
  • temperature
  • top_k
  • top_p

Call it

OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model liquid/lfm-2-24b-a2b.

Code sample language
curl https://api.openkey.ai/v1/chat/completions \
  -H "Authorization: Bearer $OPENKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "liquid/lfm-2-24b-a2b",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.openkey.ai/v1",
    api_key=os.environ["OPENKEY_API_KEY"],
)

completion = client.chat.completions.create(
    model="liquid/lfm-2-24b-a2b",
    messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.openkey.ai/v1",
  apiKey: process.env.OPENKEY_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);

Questions

How much does LFM2-24B-A2B cost via API?
Through OpenKey, LFM2-24B-A2B costs $0.031 per 1M input tokens and $0.124 per 1M output tokens. That is the provider price ($0.030 / $0.120) plus a flat 3% fee — nothing else.
What is LFM2-24B-A2B's context window?
LFM2-24B-A2B accepts up to 128K tokens of context.
Is LFM2-24B-A2B OpenAI-compatible?
Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "liquid/lfm-2-24b-a2b" using any OpenAI SDK — only the base URL and API key change.
What inputs does LFM2-24B-A2B support?
LFM2-24B-A2B accepts text input and produces text output.

More from Liquid AI

All Liquid AI models →