LLM Perks

LFM2.5-2.6B

Liquid AI · All LFM models
Free right now Small
Open weights

LFM2.5-2.6B is a language model with 2.6B parameters from Liquid AI. It is currently free at 2 providers with up to 128K tokens of context. Its weights are open, so it can also run locally.

Developer
Liquid AI
Parameters
2.6B
Context
128K tokens
Type
Text
License
Open weights

Where to use LFM2.5-2.6B for free

Each row is a separate free endpoint with its own limits.

ProviderContextLimitCard
OpenRouter
liquid/lfm-2.5-2.6b:free
66K Free tier No Open
UnoRouter
lfm-2.5-2.6b:free
128K No-card free models use shared capacity and per-model limits; availability can change. No Open

Quick start

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "liquid/lfm-2.5-2.6b:free",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Example for OpenRouter. Any OpenAI-compatible client works: Cursor, Cline, OpenCode, Open WebUI.

Benchmarks

Intelligence Index
8.4
GPQA Diamond
55.8%
Humanity's Last Exam
6.2%
Long context (LCR)
5.7%

Source: Artificial Analysis · LFM2.5-2.6B

FAQ

Is LFM2.5-2.6B free?

Yes. As of September 26, 2026, LFM2.5-2.6B is free at OpenRouter, UnoRouter. Each provider has its own limits — see the table above.

What is the context window of LFM2.5-2.6B?

The largest context among free routes is 128,000 tokens. Some providers cap it lower.

How do I call LFM2.5-2.6B via API?

Use any OpenAI-compatible client with base URL https://openrouter.ai/api/v1, model ID liquid/lfm-2.5-2.6b:free, and a OpenRouter key.

How good is LFM2.5-2.6B?

Artificial Analysis Intelligence Index: 8.4, GPQA Diamond: 56%. For comparison, the strongest free model in the catalog right now is GLM 5.3.

Is LFM2.5-2.6B open-weight?

Yes, the weights are published — you can download and run it locally, for example with Ollama or LM Studio.