Atlas / Models / Liquid / LiquidAI: LFM2-8B-A1B

LiquidAI: LFM2-8B-A1B✓ Catalog verified

liquid/lfm2-8b-a1b

LFM2-8B-A1B is an efficient on-device Mixture-of-Experts (MoE) model from Liquid AI’s LFM2 family, built for fast, high-quality inference on edge hardware. It uses 8.3B total parameters with only ~1.5B active per token, delivering strong performance while keeping compute and memory usage low—making it ideal for phones, tablets, and laptops.

Input price
$0.01 /1M
Output price
$0.02 /1M
Context
33K
Modalities
text
Released
Oct 20, 2025
Tool calling
Atlas signal
74/100
01

Overview

LFM2-8B-A1B is an efficient on-device Mixture-of-Experts (MoE) model from Liquid AI’s LFM2 family, built for fast, high-quality inference on edge hardware. It uses 8.3B total parameters with only ~1.5B active per token, delivering strong performance while keeping compute and memory usage low—making it ideal for phones, tablets, and laptops.

Access: available through the official Liquid API. Context window: 33K.

Pricing and metadata from the ModelsAtlas catalog.Last refreshed Aug 5, 2026
02

Specifications

API identifierliquid/lfm2-8b-a1b
ProviderLiquid
Model typeText LLM
Context window33K catalog
Input modalitiestext
Output modalitiestext
ReleasedOct 20, 2025
ModeratedNo
Architecture modalitytext->text
Supported parameters
frequency_penaltymax_tokensmin_ppresence_penaltyrepetition_penaltyseedstoptemperaturetop_ktop_p
Source: provider documentation + catalog feedMethodology →

API defaults

Default parameters
{
  "top_p": null,
  "temperature": null,
  "frequency_penalty": null
}
03

Pricing

Live pricing components for liquid/lfm2-8b-a1b as published in the catalog.

$0.01
Input /1M
$0.02
Output /1M
Per request
Per image
Pricing componentRaw unit priceNormalizedUnit
Prompt tokens$1e-8$0.01 / 1MPer input token
Completion tokens$2e-8$0.02 / 1MPer output token
Request feeN/AN/APer request
Image feeN/AN/APer image unit
Web search feeN/AN/APer search request
Source: catalog pricing feedCompare all pricing →Cheapest models →
04

Cost calculator

Estimate monthly spend from your own token volumes.

Scale / Volume

Estimated Total Cost

$0.01Calculated from current list pricing in the ModelsAtlas catalog.
05

Capabilities

CapabilityStatusWhat it means
Visual UnderstandingNot advertisedImage and document analysis support
Audio ProcessingNot advertisedSpeech and voice aligned flows
Tool CallingNot advertisedSupports tools / function calling
Self-HostingNot advertisedDeploy outside managed APIs
Derived from catalog capability tags and supported parameters
06

Capability signals

Directional signals derived from model metadata and capability tags — not official benchmark submissions.

LiquidAI: LFM2-8B-A1B
MMLU Signal (Reasoning)
74signal
Coding Signal (HumanEval proxy)
74signal
Math Signal (GSM8K proxy)
74signal
Science Signal (GPQA proxy)
74signal
Estimated from metadata — not an official benchmark runAll benchmarks →Methodology →
07

Quick start

Call LiquidAI: LFM2-8B-A1B through an OpenAI-compatible client.

from openai import OpenAI

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

response = client.chat.completions.create(
    model="liquid/lfm2-8b-a1b",
    messages=[{"role": "user", "content": "Explain quantum physics."}]
)

print(response.choices[0].message.content)
08

Alternatives

Closest models by context window from a different provider.

09

Sources & attribution

Pricing and metadata are maintained in the ModelsAtlas catalog.

Capability bars use metadata tags — directional estimates onlyHow we source and verify data →
10

Frequently asked questions

How much does LiquidAI: LFM2-8B-A1B cost?

$0.01 per 1M input tokens and $0.02 per 1M output tokens on the official Liquid API.

What is the context window of LiquidAI: LFM2-8B-A1B?

LiquidAI: LFM2-8B-A1B supports up to 33K tokens of context.

Does LiquidAI: LFM2-8B-A1B support tool / function calling?

LiquidAI: LFM2-8B-A1B does not advertise first-class tool/function calling. Check vendor docs for the latest capabilities.

How do I access LiquidAI: LFM2-8B-A1B?

Use the official Liquid API with the model id `liquid/lfm2-8b-a1b`. See the Quick start section above for code examples.