LFM2.5-2.6B

LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or knowledge-heavy tasks.

Provider: Liquid AI
Released: 2026-08-11
Size: SMALL
Free API (OpenRouter): Yes, 1 provider (via OpenRouter)
Per 1M tokens: $0.00 in · $0.00 out
Rival’s tab: $0.00; 56/56 receipts survived

Free API endpoint listed

LFM2.5-2.6B has a free endpoint in Rival’s OpenRouter listings. Free requests have usage limits and depend on provider availability.

Provider data: 9 Sep 2026OpenRouter usage limits

View free endpoint

Get API accessProvider and language code samples

Provider

fromimport openai  OpenAI

client = OpenAI(
"https://openrouter.ai/api/v1"    base_url=,
"$OPENROUTER_API_KEY"    api_key=,
)

response = client.chat.completions.create(
"liquid/lfm-2.5-2.6b:free"    model=,
"role""user""content""Hello!"    messages=[{: , : }],
)
print(response.choices[0].message.content)

Set OPENROUTER_API_KEY with your OpenRouter API key from openrouter.ai/keys.

Deep analysisPsychometrics, taste index, writing DNA

Writing DNA

Stylometric Fingerprint

Based on 26 text responses

Tick = global average

Vocabulary Diversity54%

Unique words vs. total words. Higher = richer vocabulary.

Sentence Length18.4 words

Average words per sentence.

Hedging0.42

"Might", "perhaps", "arguably" per 100 words.

Bold Formatting4.1

**Bold** markers per 1,000 characters.

List Usage3.3

Bullet and numbered list items per 1,000 characters.

Section Structure0.53

Markdown headings per 1,000 characters.

Emoji Usage0.00

Emoji per 1,000 characters.

Transitions0.23

"However", "moreover", "furthermore" per 100 words.

Opening Habits

Consistency

77%

Across 26 responses

Favorites

Movie

The Godfather

19728.7

Album

Thriller

Michael Jackson

Book

Nineteen Eighty-Four

George Orwell

City

Kyoto

Japan

Game

The Legend of Zelda: Breath of the Wild

Adventure, Action4.5

Model Responses

51 outputs · $0.00 tracked across 51 receipts

Keep exploring

COMPARE

LFM2.5-2.6B vs MiniMax M2.7

Real outputs compared side by side

RANKINGS

Best AI for Data Visualization

Two colliding black holes rendered as an animated grid, a labelled world map,...

Compare LFM2.5-2.6B

Alternatives to LFM2.5-2.6B

LFM2.5-2.6B

Free API endpoint listed

Stylometric Fingerprint

Favorites

Model Responses

LFM2.5-2.6B vs MiniMax M2.7

Best AI for Data Visualization

Compare LFM2.5-2.6B

Alternatives to LFM2.5-2.6B

LFM2.5-2.6B

Free API endpoint listed

Stylometric Fingerprint

Favorites

Model Responses

LFM2.5-2.6B vs MiniMax M2.7

Best AI for Data Visualization