LFM 2 24B A2B is Liquid AI's language model with a 128K context window, starting at $0.030 / 1M input and $0.120 / 1M output. A 24B-parameter Mixture-of-Experts Liquid Foundation Model with only 2B active parameters, designed for efficient on-device deployment.
Specifications
Canonical IDliquid-lfm-2-24b-a2b
TypeLanguage
StatusActive
CreatorLiquid AILiquid AI
Providers
Context Window128K tokens
Input ModalitiesText
Output ModalitiesText
Parameters24B
Release Date · 3 months ago
Benchmarks
Intelligence Index
10.5
#383
Coding Index
3.6
#354
GPQA
0.5
#326
HLE
0.0
#342
IFBench
0.5
#163
Time to First Token
0.29s
#215
SciCode
0.1
#389
LCR
0.0
#367
TerminalBench Hard
0.0
#361
TAU2
0.1
#346
Output TPS

Capabilities

Input1/5
Text
Image·
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

ProviderStandard
Input
$ / 1M
Output
$ / 1M
OpenRouter logo
OpenRouter
liquid/lfm-2-24b-a2b
$0.030$0.120

Cost Calculator

Preset:

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
LFM 2 24B A2B128K$0.030$0.120Current
LFM 2.5 1.2B Thinking33KAvailable
LFM 2.5 1.2B Instruct33KAvailable
LFM 2 2.6BAvailable
LFM 2 8B A1BAvailable
LFM 2 1.2BAvailable
LFM 2.5 1.6B VLAvailable
LFM 40B131K$0.100$0.200Available
LFM 7B131K$0.025$0.040Available

Model IDs