LiquidAI: LFM2.5-2.6B (free)

LiquidAI: LFM2.5-2.6B (free)

liquid · Released Aug 11, 2026
Intelligence #670 / 756
13.1 our score
Speed #38 / 333
199.8 tok/s
Input Price
Not priced
Output Price
Not priced
Context #565 / 779
65,536 tokens

Analysis Summary

LFM2.5-2.6B is LiquidAI's small free model, designed for compact deployments rather than demanding reasoning. It provides a 65K context window plus tool and function-calling interfaces, which are useful structural features for simple applications.

The model may suit classification, short extraction tasks, routing, and low-risk interface automation where operating cost and footprint matter more than nuanced output. Its measured reasoning, coding, and agentic capability is limited, so it should not handle client-facing strategy, complex SEO briefs, software engineering, or autonomous workflows without substantial safeguards.

Use it only for tightly scoped, high-volume tasks where free access and compact operation outweigh the need for language depth.

Assessed September 7, 2026

Editorial notes

LFM2.5-2.6B is a free, compact model with basic tool and function-calling support, a 65K context window, and low resource demands. Its limited reasoning and coding capability restrict it to lightweight automation.

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

DFO Verdict

LFM2.5-2.6B is a free, compact model with basic tool and function-calling support, a 65K context window, and low resource demands. Its limited reasoning and coding capability restrict it to lightweight automation.

#670 of 756 overall

How LiquidAI: LFM2.5-2.6B (free) compares

LiquidAI: LFM2.5-2.6B (free) ranks #274 of 438 AI models we track for overall intelligence, #194 of 210 for coding, #149 of 192 for agentic tasks. Its 66K-token context window is larger than 27% of the models we list. LiquidAI: LFM2.5-2.6B (free) is currently free to use via OpenRouter.

Position in the field
Intelligence: smarter than 11% of models #670
Speed: faster than 89% of models #38
Context: larger than 27% of models #565
worst in fieldmedianbest in field
Price vs frontier peers · $ per 1M tokens
LiquidAI: LFM2.5-2.6B (free) $0.00 in $0.00 out
OpenAI: GPT-6 Astra $10.00 in $50.00 out
Anthropic: Claude Fable 5.1 $10.00 in $50.00 out
Claude Opus 5 $5.00 in $25.00 out

Dark bar = input · light bar = output, scaled to the priciest peer.

Context window vs peers · tokens
LiquidAI: LFM2.5-2.6B (free) 66K

1M tokens ≈ 8 full-length novels or ~2,500 pages of business documents in a single request.

Intelligence0.8Technical1Value0Content3
Performance profile

Strongest on business fit. The pulled-in value corner is the trade-off, and if the shape matters more than the price, this is your model.

Compare shapes side-by-side →

About LiquidAI: LFM2.5-2.6B (free)

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..

Frequently asked questions about LiquidAI: LFM2.5-2.6B (free)

How much does LiquidAI: LFM2.5-2.6B (free) cost?

LiquidAI: LFM2.5-2.6B (free) is currently available for free via OpenRouter.

What is the context window of LiquidAI: LFM2.5-2.6B (free)?

LiquidAI: LFM2.5-2.6B (free) has a context window of 65,536 tokens (66K).

Is LiquidAI: LFM2.5-2.6B (free) good for coding?

On our coding benchmark index, LiquidAI: LFM2.5-2.6B (free) ranks #194 of 210 models, placing it in the broader range of the field for code generation and debugging.

What can LiquidAI: LFM2.5-2.6B (free) do?

LiquidAI: LFM2.5-2.6B (free) supports tool use and function calling.

Who created LiquidAI: LFM2.5-2.6B (free)?

LiquidAI: LFM2.5-2.6B (free) is developed by LiquidAI and was released on August 11, 2026.

© 2026 Design for Online Ltd. Registered in England and Wales No. 10328553. VAT Registered. Design for Online® and Forerunner® are registered trademarks.