LFM2.5-2.6B overview
LFM2.5-2.6B by Liquid AI
LFM2.5-2.6B is a compact reasoning model that prioritizes logical steps before generating responses. It is optimized for agent workflows, data extraction, RAG, and long-context processing.
LFM2.5-2.6B specs
- Model ID
liquid/lfm-2.5-2.6b- Developer
- Liquid AI
- Context window
- 128,000 tokens
- Max output
- 8,192 tokens
- Input
- Text
- Output
- Text
- API
- OpenAI-compatible, base URL
https://api.aimlapi.com/v1
What Is LFM2.5-2.6B API?
LFM2.5-2.6B is a compact chat model developed by Liquid AI. It is engineered to perform reasoning before providing answers to ensure accuracy in complex tasks.
The model supports text to text modalities and is built to handle extensive information through its large context window. It is well suited for specialized data processing and retrieval tasks.
Reasoning First
The model consistently reasons before answering to improve output quality.
Large Context Window
It supports a context window of 128K tokens for processing long documents.
Structured Output
The model is capable of generating structured data for integration into workflows.
Tool Integration
It supports tools and streaming to enhance interactive performance.
Use cases
Automating complex agent workflows.
Extracting data from large documents.
Enhancing retrieval augmented generation systems.
Processing long-context information.
Capabilities
- Reasoning
- Streaming
- Structured outputs
- Function calling
LFM2.5-2.6B benchmarks by
Artificial Analysis
See how LFM2.5-2.6B scores on independent evaluations. Data retrieved Nov 4, 2026.
Benchmark results
Compare 13 models available on AI/ML API across 4 independent benchmarks.
Humanity's Last Exam
Expert-written questions across academic subjects.
GPQA Diamond
Graduate-level science questions written to resist web search.
AA-LCR
Reasoning across long documents of about 100k tokens.
SciCode
Python coding tasks drawn from scientific research.
LFM2.5-2.6B API pricing
| Usage | Price | Unit |
|---|---|---|
| Input | $0.3703 | 1M tokens |
| Output | $0.529 | 1M tokens |
| Cached input | $0.0423 | 1M tokens |
Prices from the AI/ML API price list, checked on Nov 4, 2026.
LFM2.5-2.6B vs other models: token prices
AI/ML API input and output rates for 5 models, per million tokens.
| Model | Input | Output |
|---|---|---|
| $0.3703 | $0.529 | |
| $0.525 | $0.525 | |
| Ternary Bonsai 2 27B | $0.0794 | $0.529 |
| Cydonia 24B V4.1 | $0.3174 | $0.529 |
| $0.1323 | $0.529 |
How to use the LFM2.5-2.6B API
View docsBuild with your agent
Give your agent the model details, code and documentation.
1Get your API key
Create API keyexport AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"2Make your first request
curl 'https://api.aimlapi.com/v1/chat/completions' \
-H "Authorization: Bearer $AIMLAPI_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "liquid/lfm-2.5-2.6b",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "liquid/lfm-2.5-2.6b",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}
response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "liquid/lfm-2.5-2.6b",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}),
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());Related articles
LFM2.5-2.6B FAQ
How much does LFM2.5-2.6B cost?
LFM2.5-2.6B costs $0.3703 / 1M for input and $0.529 / 1M for output on AI/ML API. Cached input is billed at $0.04232 / 1M.
What is the primary focus of LFM2.5-2.6B?
The model focuses on reasoning before answering to support complex workflows.
Is this model suitable for coding tasks?
Liquid AI advises against using this model for agentic coding.
How much text can the model process at once?
The model features a context window of 128K tokens.
What modalities does this model support?
LFM2.5-2.6B supports text to text modalities.
What is the LFM2.5-2.6B model ID?
Use liquid/lfm-2.5-2.6b as the model parameter. Requests go to the OpenAI-compatible endpoint with your AI/ML API key.
What is the context window of LFM2.5-2.6B?
LFM2.5-2.6B accepts up to 128,000 tokens of context and returns up to 8,192 output tokens.


