NOUMENOpen app
NOUMEN

liquid · Efficient

LFM2.5 24B A2B

Added Oct 14, 2026

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Use in the app

Liquid AI's text-only mixture-of-experts model for reasoning and tool-using agents, with 24B total and 2.45B active parameters. It always thinks before answering and supports structured output. Pair it with retrieval for knowledge-heavy tasks. Open weights use the LFM Open License v1.0, with a $10M annual-revenue commercial threshold; hosted API use is subject to separate service terms that permit retention and use of prompts and responses for model training.

  • Reasoning
  • Tools
  • Structured output
Input
Text
Output
Text
Discovery tier
Efficient

Pricing

USD per 1M tokens
Input
$0.05
Output
$0.70
Cache read
$0.025

Reference prices as published by the model provider. API example

Specifications

Context window
128K
Max output
8.2K
Average output (7 days)
5.1K tokens
Longer than 99% of 465 models

Side by side

LFM2.5 24B A2B compared

Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

LFM2.5 24B A2BliquidThis modelSolar Mini 4upstageRemove
Providerliquidupstage
Discovery tierEfficientEfficient
AddedOct 14, 2026Sep 23, 2026
Limits
Context window128K524.29KBest
Max output8.19K131.07KBest
Average output5.1K tokens561 tokens
Pricing, USD per 1M tokens
Input$0.05$0.05
Output$0.70$0.20Best
Cache read$0.025$0.005Best
Performance
Throughput—90.6 tok/s
Time to first token—2.2 s
Request success (24h)100.0%Best89.1%
Benchmark indexes
Intelligence Index—24.1
Capabilities
ReasoningYesNo
ToolsYesYes
Structured outputYesYes
Reasoning effort——

Public evaluations

Benchmarks

Independent evaluation results, with how each score ranks among the models in the Noumen catalog.

  • LFM2.5 24B A2B
  • Solar Mini 4

Intelligence Index

  • LFM2.5 24B A2B—
  • Solar Mini 424.1
3.8Catalog models by score55.1

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • LFM2.5 24B A2B: —
    • Solar Mini 4: 22.3%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • LFM2.5 24B A2B: —
    • Solar Mini 4: 2.4%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • LFM2.5 24B A2B: —
    • Solar Mini 4: 867 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • LFM2.5 24B A2B: —
    • Solar Mini 4: 1,085 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • LFM2.5 24B A2B: —
    • Solar Mini 4: 5.0%

  • AA-LCRv1.1

    Reasoning across long documents

    • LFM2.5 24B A2B: —
    • Solar Mini 4: 83.3%

  • MLCR-AA

    Long-context reasoning over medical records

    • LFM2.5 24B A2B: —
    • Solar Mini 4: 6.7%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • LFM2.5 24B A2B: —
    • Solar Mini 4: 25.8%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • LFM2.5 24B A2B: —
    • Solar Mini 4: 1.0%

  • SciCode

    Scientific computing in Python

    • LFM2.5 24B A2B: —
    • Solar Mini 4: 47.6%

Legacy evaluations

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • LFM2.5 24B A2B: —
    • Solar Mini 4: 83.3%

Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis

Live routing data

Performance and reliability

Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.

Request success (24h)
100.0%
Reliable
Hourly request success · last 72 hoursLowest hour 100.0%
  • Healthy (98% or more)
  • Degraded (90–98%)
  • Down (under 90%)
  • No requests

Developers

Use it through the API

Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart
curl https://www.noumen.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $NOUMEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "liquid/lfm-2.5-24b-a2b",
    "messages": [{ "role": "user", "content": "Explain this stack trace." }]
  }'
import os
from openai import OpenAI

client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
    model="liquid/lfm-2.5-24b-a2b",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

liquid

Other liquid models, starting with the same family.