LFM2.5-1.2B-Instruct is a compact, high-performance instruction-tuned model built for fast on-device AI. It delivers strong chat quality in a 1.2B parameter footprint, with efficient edge inference and broad runtime support.
- Modalities
- text → text
- In / out per 1M
- Free / Free
- Context
- 33K tokens
- Added
- Jan 20, 2026
- Tokenizer
- Other
Pricing
Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.
| Per 1M tokens | Provider | + 3% fee | You pay |
|---|---|---|---|
| Input | Free | — | Free |
| Output | Free | — | Free |
Providers
No provider breakdown is published for LFM2.5-1.2B-Instruct (free) in the current catalog snapshot (Jul 28, 2026). Browse all providers
Supported parameters
- frequency_penalty
- max_tokens
- min_p
- presence_penalty
- repetition_penalty
- seed
- stop
- structured_outputs
- temperature
- top_k
- top_p
Call it
OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use
model liquid/lfm-2.5-1.2b-instruct:free.
curl https://api.openkey.ai/v1/chat/completions \
-H "Authorization: Bearer ***" \
-H "Content-Type: application/json" \
-d '{
"model": "liquid/lfm-2.5-1.2b-instruct:free",
"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-2.5-1.2b-instruct:free",
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-2.5-1.2b-instruct:free",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);About LFM2.5-1.2B-Instruct (free)
LFM2.5-1.2B-Instruct is a 1.2B-parameter instruction-tuned model from Liquid AI, built on liquid neural network architecture instead of a standard transformer stack. It's aimed at on-device and edge inference where memory and latency matter more than raw benchmark scores. With a 32,768-token context window and text-only input/output, it fits chat, short-document Q&A, and structured-output tasks that don't need a large model. It supports structured outputs, tool-relevant parameters like seed and repetition_penalty, and runs through OpenKey at no cost.
This is one of OpenKey's 25 free models, so both prompt and completion tokens cost $0.0 per 1M via the API. Its 32,768-token context window is larger than only 5% of catalog models — small by current standards, but ahead of the smallest models in the 329-model catalog. At 1.2B parameters it's built for edge inference, not for competing on context length; Liquid AI's own LFM2-24B-A2B sibling costs $0.03/1M input and $0.12/1M output for a much bigger model. No public benchmark scores or knowledge cutoff are listed for this model.
Questions
- How much does LFM2.5-1.2B-Instruct cost via API?
- It's free — $0.0 per 1M input tokens and $0.0 per 1M output tokens from the provider, and OpenKey's flat 3% fee on $0.0 is still $0.0. It's one of 25 free models available on OpenKey, so there's no cost math to do here.
- What is LFM2.5-1.2B-Instruct's context window?
- The context window is 32,768 tokens. That's enough for a moderate chat history or a short document, though OpenKey's catalog data shows this window is larger than only 5% of the 329 models tracked — most models on the platform support more context than this one.
- Is LFM2.5-1.2B-Instruct free to use?
- Yes. Both input and output tokens are priced at $0.0 per 1M via the provider, and OpenKey passes that through with no markup since 3% of $0.0 is still $0.0. It's listed among OpenKey's 25 free models.
- Does LFM2.5-1.2B-Instruct support structured outputs?
- Yes, structured_outputs is listed among its supported parameters, alongside temperature, top_p, top_k, seed, frequency_penalty, presence_penalty, and repetition_penalty. It does not support vision — input and output modalities are text-only.
- How does LFM2.5-1.2B-Instruct compare to LFM2.5-1.2B-Thinking?
- Both are free on OpenKey, priced at $0.0 per 1M for input and output tokens. The Instruct version is built for direct instruction-following and chat responses, while the Thinking sibling (liquid/lfm-2.5-1.2b-thinking:free) is Liquid AI's variant in the same 1.2B parameter class — choose based on whether you need direct answers or a reasoning-oriented workflow.
More from Liquid AI
All Liquid AI models →
Liquid AILFM2-24B-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...
ctx 128K in $0.031 out $0.124
Liquid AIFreeLFM2.5-1.2B-Thinking (free)
LFM2.5-1.2B-Thinking is a lightweight reasoning-focused model optimized for agentic tasks, data extraction, and RAG—while still running comfortably on edge devices. It supports long context (up to 32K tokens) and is...
ctx 33K in Free out Free