liquid/lfm-2-24b-a2b
32,768 context · $0.03/M input tokens · $0.12/M output tokens
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 token, it delivers high-quality generation while maintaining low inference costs. The model fits within 32 GB of RAM, making it practical to run on consumer laptops and desktops without sacrificing capability.
Bayar sesuai pemakaian
Tanpa biaya di muka, bayar hanya sesuai penggunaan
Gunakan contoh kode berikut untuk integrasi dengan API kami:
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://llm.wavespeed.ai/v1"
)
response = client.chat.completions.create(
model="liquid/lfm-2-24b-a2b",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)LFM2-24B-A2B is the largest model in the LFM2 family of hybrid architectures designed for efficient on-device deployment
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 token, it delivers high-quality generation while maintaining low inference costs. The model fits within 32 GB of RAM, making it practical to run on consumer laptops and desktops without sacrificing capability.
| Specification | Value |
|---|---|
| Provider | Liquid |
| Model Type | Large Language Model (LLM) |
| Architecture | N/A |
| Context Window | 32768 tokens |
| Max Output | tokens |
| Input | Text |
| Output | Text |
| Vision | Supported |
| Function Calling | Supported |
| Token Type | Cost per Million Tokens |
|---|---|
| Input | $0.0 |
| Output | $0.1 |
Base URL: https://llm.wavespeed.ai/v1 API Endpoint: chat/completions Model ID: liquid/lfm-2-24b-a2b
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://llm.wavespeed.ai/v1"
)
response = client.chat.completions.create(
model="liquid/lfm-2-24b-a2b",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)curl https://llm.wavespeed.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "liquid/lfm-2-24b-a2b",
"messages": [{"role": "user", "content": "Hello!"}]
}'liquid/lfm-2-24b-a2b
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 token, it delivers high-quality generation while maintaining low inference costs. The model fits within 32 GB of RAM, making it practical to run on consumer laptops and desktops without sacrificing capability.
Input
$0.03 /M
Output
$0.12 /M
Konteks
33K
Akses Lfm 2 24b A2b melalui API terpadu kami — kompatibel dengan OpenAI, tanpa cold start, harga transparan.
Harga di WaveSpeedAI: $0.03 per juta token input dan $0.12 per juta token output. Prompt caching dan batch processing ditagih terpisah dan mengurangi biaya efektif pada beban kerja yang panjang dan berulang.
Lfm 2 24b A2b mendukung hingga 33K token konteks dengan hingga — token output per permintaan.
Ya. WaveSpeedAI menyediakan Lfm 2 24b A2b melalui endpoint yang kompatibel dengan OpenAI di https://llm.wavespeed.ai/v1. Arahkan OpenAI SDK resmi ke base URL ini dengan API key WaveSpeedAI Anda — tanpa perubahan kode lainnya.
Masuk ke WaveSpeedAI, buat API key di Access Keys, lalu kirim permintaan ke https://llm.wavespeed.ai/v1/chat/completions dengan model id seperti ditampilkan di atas. Akun baru menerima kredit gratis untuk menguji Lfm 2 24b A2b.