All models

LFM2.5 Thinking

by Liquid AI

Chat Tools Thinking

Liquid AI's LFM2.5 Thinking (lfm2 family) — tool use, reasoning; 128K context.

Publisher
Liquid AI
Context window
125K tokens
Sizes
1.2B
Licence
Custom licence
Model card on Hugging Face

Run LFM2.5 Thinking

Install it on a Pendra worker, then call it through the OpenAI-compatible API with a pdr_sk_ key.

from pendra import Pendra

client = Pendra(api_key="pdr_sk_...")

response = client.chat.completions.create(
    model="lfm2-5-thinking:1.2b",
    messages=[{"role": "user", "content": "Hello!"}],
)

print(response.choices[0].message.content)

Run LFM2.5 Thinking on your own UK infrastructure

Deploy a worker, install LFM2.5 Thinking, and start serving it through one sovereign API endpoint.