LiquidAI/LFM2-2.6B

Other chattool_use

API ID: liquid/lfm-2.2-6b

Input Price
$0.01
/1M tokens
Output Price
$0.02
/1M tokens

About LiquidAI/LFM2-2.6B

LFM2 is a new generation of hybrid models developed by Liquid AI, specifically designed for edge AI and on-device deployment. It sets a new standard in terms of quality, speed, and memory efficiency.

๐Ÿ“Š
Price Ranking
#585 lowest price among 1240 Chat models

Model Specifications

Context Length
33k
Max Output
โ€”
Release Date
2025-10-20
Capabilities
chat tool_use
Input Modalities
text
Output Modalities
text

Best For

  • Conversations, content writing, general assistance

Consider Alternatives For

  • Image understanding (needs vision capability)

๐Ÿ’ฐ Real-World Cost Examples

Estimated monthly costs for common use cases

Personal AI Assistant
$0.01
/month
50 conversations/day, ~500 tokens each
Customer Service Bot
$0.33
/month
1000 tickets/day, ~800 tokens each

Other Model Lineup

Compare all models from Other to find the best fit

Model Input Output Context Capabilities
LiquidAI/LFM2-2.6B Current Free Free 33k chat tool_use
Riverflow V2 Max Preview Free Free 8k chat vision image_gen
Riverflow V2 Standard Preview Free Free 8k chat vision image_gen
Riverflow V2 Fast Preview Free Free 8k chat vision image_gen
AFM 4.5B Free Free 66k chat
AFM 4.5B Free Free 66k chat

Similar Models from Other Providers

Cross-brand alternatives with similar capabilities

OpenAI Text Embedding 3 Small
Input: $0.02
Output: Free
Context: 8k
Alibaba Qwen Qwen3 Embedding 4B
Input: $0.02
Output: Free
Context: 33k
Meta Llama 3.2 3B Instruct
Input: $0.02
Output: $0.02
Context: 131k
Inclusionai Ling-2.6-flash
Input: $0.01
Output: $0.03
Context: 262k

๐Ÿš€ Quick Start

Get started with LiquidAI/LFM2-2.6B API

OpenAI-compatible SDK
from openai import OpenAI

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

response = client.chat.completions.create(
    model="liquid/lfm-2.2-6b",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)